Learning from earlier synthesis and microscopy data guided a human-supervised nanoparticle campaign. Researchers reported the desired structures for 18 of 19 selected candidates, including complex multielement particles. This success rate concerns a curated experimental set, not the full predicted composition space. Structural synthesis was demonstrated; catalytic and device performance were not.
Technology: Bayesian optimization of composition and morphology
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Synthesized candidates were examined by microscopy and elemental analysis.
- Still unknown: Functional performance, general search-space success and independent replication were not established.
- AI role: Bayesian optimization of composition and morphology supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8694626/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary article metadata, affiliations, selected experimental Results and discussion; supplements not reviewed..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An interpretable hybrid unsupervised/supervised learning analysis of experimental snapshots from a programmable Rydberg-atom array mapped phase regions on a square lattice and identified signatures of two previously undetected phases: boundary-ordered and rhombic. The rhombic pattern had been predicted theoretically, so the result is its experimental-data signature rather than a wholly unanticipated theoretical phase; the boundary-ordered phase was revealed from edge correlations.
Technology: Hybrid-correlation convolutional neural network (Hybrid-CCNN) with PCA and clustering
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: An interpretable hybrid unsupervised/supervised learning analysis of experimental snapshots from a programmable Rydberg-atom array mapped phase regions on a square lattice and identified signatures of two previously undetected phases: boundary-ordered and rhombic.
- Still unknown: The study reanalyzes experimental quantum-simulator snapshots; the rhombic phase was previously predicted by theory, while the paper reports its finite-size experimental manifestation. The paper characterizes phases using data and numerical interpretation, not bulk material synthesis.
- AI role: Unsupervised clustering exposed phase regions in experimental snapshots; interpretable supervised correlator networks refined boundaries and identified edge and multi-point correlation motifs characteristic of the previously undetected boundary-ordered and rhombic regions.
Evidence sources: https://arxiv.org/abs/2112.10789
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 38 of works of the same type, year and subfield (OpenAlex work metrics, 3 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The SARA agent combined robotic laser spike annealing, optical characterization and nested active learning to map synthesis phase boundaries of Bi2O3. It reached orders-of-magnitude faster establishment of the phase diagram and identified conditions that stabilize metastable delta-Bi2O3. Validation is experimental but restricted to one oxide system.
Technology: Scientific Autonomous Reasoning Agent (SARA) with hierarchical active learning and uncertainty quantification
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The SARA system autonomously mapped Bi2O3 synthesis phase boundaries with robotic synthesis and optical characterization, and the phase diagram was established experimentally.
- Still unknown: Not reported.
- AI role: Nested active learning cycles directed robotic laser spike annealing and optical characterization to map the phase diagram.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1126/sciadv.abg4930&resultType=core&format=json
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 123 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Retrosynthesis software proposed alternative chemical supply routes for the antiviral umifenovir and eleven other antiviral and anti-inflammatory drugs. The authors experimentally validated four routes to umifenovir and one route to bromhexine, one of which converts six C-H bonds. The work is a proof of route feasibility for supply-chain resilience, not a new therapeutic claim.
Technology: Computer-aided retrosynthesis software with exclusion of known starting materials
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The authors experimentally validated four routes to umifenovir and one route to bromhexine proposed by the software.
- Still unknown: Not reported.
- AI role: Retrosynthesis software proposed alternative supply routes for umifenovir and other antiviral and anti-inflammatory drugs.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41467-021-27547-3&resultType=core&format=json
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 87 of works of the same type, year and subfield (OpenAlex work metrics, 38 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The neural network estimates the mass, spin, position, inclination and distance of binary black holes in seconds rather than hours or months, with about ten days of training, and was tested on eight events from LIGO and Virgo’s O1 and O2 runs. Published in Physical Review Letters; extension to neutron stars is only promising; source reviewed was a Max Planck doctoral-program page.
Technology: DINGO (Bayesian inference with neural networks)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Parameter estimates for eight LIGO-Virgo events agree closely with standard inference codes, with inference times cut from days to about 20 seconds.
- Still unknown: The article says extension to neutron stars and complex signals is promising but not demonstrated.
- AI role: Neural network acted as a surrogate for Bayesian posterior distributions for gravitational-wave parameters.
Evidence sources: https://imprs.is.mpg.de/news/machine-learning-decodes-tremors-of-the-universe · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1103/PhysRevLett.127.241103&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 348 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A neural network represents the functional used in DFT and addresses two longstanding errors of traditional functionals: excessive electron delocalization and spin-symmetry breaking during bond breaking. Published in Science with open code; the post gives no benchmark figures and DFT remains an approximation.
Technology: DM21 (neural network for the exchange-correlation functional)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: DM21 is compared with traditional functionals on benchmarks for main-group atoms and molecules and on bond-breaking and charge-localisation examples.
- Still unknown: The page gives no numerical benchmark figures and says DFT remains an approximation.
- AI role: Neural network represents the exchange-correlation functional in density functional theory.
Evidence sources: https://deepmind.google/discover/blog/simulating-matter-on-the-quantum-scale-with-ai/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1126/science.abj6511&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 416 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Learned soundscape features predicted occurrence for 34 of 39 surveyed bird and herpetofaunal species across a forest-degradation gradient in Sabah. Predictions used the broader acoustic environment rather than direct identification of every species call. Site-level evaluation supports a bounded monitoring result, not proof of causal habitat quality or a replacement for species surveys.
Technology: Convolutional audio embeddings and Gaussian-mixture occurrence models
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Occurrence predictions were compared with field point counts using cross-validation.
- Still unknown: Transfer to other ecosystems and causal interpretation are not established by this study.
- AI role: Convolutional audio embeddings and Gaussian-mixture occurrence models supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://nsojournals.onlinelibrary.wiley.com/doi/10.1111/oik.08525
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary publisher metadata, affiliations, abstract and selected Methods/Results; supplements not reviewed..
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
With mathematicians Williamson (Sydney) and Lackenby and Juhász (Oxford), supervised-learning techniques revealed patterns leading to an unexpected link between a knot’s algebraic signature and its geometry (the ‘natural slope’), and to a new algorithm for the combinatorial invariance conjecture. The conjectures and proofs are the mathematicians’; the algorithm was checked on over 3 million examples, not proved in general.
Technology: Supervised learning and attribution techniques
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Conjectures and proofs were established by mathematicians, and the new algorithm was computationally verified on over 3 million examples.
- Still unknown: Certain patterns still elude ML, and the representation-theory structure appears only at 100s or 1000s of vertices.
- AI role: Supervised learning revealed patterns that led to the knot and representation-theory results and a new algorithm.
Evidence sources: https://deepmind.google/discover/blog/exploring-the-beauty-of-pure-mathematics-in-novel-ways/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1038/s41586-021-04086-x&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 551 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The network predicted about 2,000 new sequences as foldable; over 100 were produced in the lab, and for three, nuclear magnetic resonance and X-ray crystallography confirmed the predicted shapes. Only three proteins were characterized in detail; using the method to create useful functions (drugs, enzymes) is a future goal.
Technology: Neural network for structure prediction (hallucination)
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: 129 hallucinated sequences were synthesised, 27 gave monodisperse proteins, and three structures determined by X-ray crystallography or NMR matched the hallucinated models.
- Still unknown: Only three proteins were characterised in detail, and using the method for useful functions is a future goal.
- AI role: Neural network hallucinated new protein sequences predicted to fold.
Evidence sources: https://newsroom.uw.edu/news-releases/deep-learning-dreams-new-protein-structures · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1038/s41586-021-04184-w&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 653 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A workflow built on only five experimental data points screened 348 phosphine ligands and predicted ligands that favour dinuclear Pd(I) complexes over Pd(0) and Pd(II) species. The authors experimentally verified the predictions, including ligands that had never been synthesized before. The evidence is limited to the Pd speciation system studied, not a general catalyst performance gain.
Technology: Unsupervised machine learning workflow with clustering on generalized parameter databases and in silico data
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The authors experimentally verified the predicted phosphine ligands, including ligands never synthesized before, and they gave dinuclear Pd(I) complexes. The ligand predictions were checked by laboratory experiments.
- Still unknown: Not reported.
- AI role: Unsupervised machine learning workflow built on five experimental data points, screened 348 phosphine ligands and predicted those favouring dinuclear Pd(I) complexes.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1126/science.abj0999&resultType=core&format=json
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 167 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The ExoMiner neural network, run on the Pleiades supercomputer, validated 301 planets from the remaining Kepler candidates, adding to the 4,569 already validated; none is Earth-like or in the habitable zone. “Validated” is statistical, not confirmed; NASA’s 2026 count gives 370 for the same work, an unexplained discrepancy.
Technology: ExoMiner (deep neural network)
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: retrospective or benchmark
- Tested: ExoMiner was evaluated on a test set (recall 0.936 at 99% precision in the arXiv abstract) and used to validate 301 new planets.
- Still unknown: Validation is statistical rather than confirmation, the article gives no false-positive rates, and none of the planets is Earth-like.
- AI role: Deep learning classifier vetted transit signals from Kepler.
Evidence sources: https://www.nasa.gov/missions/kepler/new-deep-learning-method-adds-301-planets-to-keplers-total-count/ · https://arxiv.org/abs/2111.10009
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Two machine-learning-guided directed-evolution series for sortase A were run with and without the known high-activity 5M variant in the initial training set. The authors report new variants with higher activity than 5M in a GFP/YFP cross-linking assay. This is not a 2.2–2.5-fold improvement over wild type; the known 5M comparator is already engineered. Feature selection used ability to find 5M and may bias exploration. The related GB1 analysis uses an existing dataset, not a second laboratory discovery. Sequence-level comparison with later sortase work remains open.
Technology: Gaussian-process Bayesian selection model
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Constructed variants were assayed for SrtA-catalyzed GFP/YFP cross-linking; resulting variants exceeded the 5M comparator.
- Still unknown: The assay is specific; 5M is an already high-activity engineered comparator; feature selection may bias to 5M; independent sequence-level overlap/replication open.
- AI role: A Gaussian-process ML model ranked variants from initial and second-round data to design subsequent SrtA mutant libraries.
Evidence sources: https://pubs.acs.org/accacs/article/11/23/14615/417029/Machine-Learning-Guided-Library-Design-Cycle-for · https://www.eng.tohoku.ac.jp/news/detail-%2C-id%2C2033.html
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary ACS indexed full article and Tohoku research announcement; methods/results and journal timing..
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A machine-learning-assisted search of WISE time-series images helped identify the high-proper-motion object CWISE J052306.42-015355.4. Its colors suggest an extreme T-subdwarf candidate, while spectral classification, parallax, distance and metallicity remain uncertain. Human and citizen-science pathways also contributed. The candidate result was public in the November 2021 preprint before the January 2022 journal article.
Technology: Machine-learning proper-motion search
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: retrospective or benchmark
- Tested: Archival astrometry and multi-survey photometry support the object and candidate classification.
- Still unknown: Spectroscopic classification and measured parallax are not established in the reviewed study.
- AI role: Machine-learning proper-motion search supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://arxiv.org/abs/2111.08182v1 · https://ntrs.nasa.gov/citations/20220005456
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary v1 preprint metadata and abstract; NASA publication record, abstract, affiliations and journal date..
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A reactivity-seeking neural network coupled to an autonomous reaction platform navigated unknown chemical mixtures using real-time analytical data. Among the reactions it identified, follow-up characterization revealed an unreported photochemical reaction and a new reactivity mode for p-toluenesulfonylmethyl isocyanide (TosMIC): six equivalents of TosMIC underwent a multistep single-substrate cascade yielding a trimeric product in 47% unoptimized yield and forming five C–C bonds.
Technology: Reactivity-seeking neural network and junction-tree neural network integrated with an autonomous robotic synthesis and analytics platform
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Among the reactions it identified, follow-up characterization revealed an unreported photochemical reaction and a new reactivity mode for p-toluenesulfonylmethyl isocyanide (TosMIC): six equivalents of TosMIC underwent a multistep single-substrate cascade yielding a trimeric product in 47% unoptimized yield and forming five C–C bonds.
- Still unknown: The source describes several found reactions, some previously known; this entry is limited to the distinct unreported TosMIC reactivity result. The reported 47% yield was unoptimized. The platform identified candidate reactions, while follow-up analyses and manual chemical investigation established the product and mechanism; no broad claim of fully autonomous mechanistic proof is made.
- AI role: A convolutional neural network classified reaction signatures from online NMR/IR/analytical data and a junction-tree neural network encoded reagent structures to help prioritize new experiments. The closed-loop system surfaced reactions; chemists then manually investigated and characterized selected outcomes, including the TosMIC trimer-forming cascade.
Evidence sources: https://pubmed.ncbi.nlm.nih.gov/34849401/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 82 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
MutCompute predicted substitutions in Bst DNA polymerase; the authors constructed and tested variants in loop-mediated isothermal amplification assays. The Mut235 triple variant showed the highest activity among four tested triple-mutant variants and remained active at 73 °C; its reported melting temperature was 78.1 °C. The evidence is in vitro and does not establish clinical diagnostic performance. The journal article cites a bioRxiv v1 posted 2021-04-15, but that version’s full text was inaccessible in this review; this entry uses the verified journal result and does not claim when the Mut235 result first appeared.
Technology: MutCompute machine-learning amino-acid environment scoring
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The authors assayed ML-predicted Bst polymerase substitutions in LAMP/LAMP-OSD reactions. Mut235 showed the highest activity among four triple-mutant variants tested, supported amplification at 73 °C, and had a measured melting temperature of 78.1 °C versus 75.5 °C for parental Bst-LF in the reported thermal-shift assay.
- Still unknown: The article cites an earlier bioRxiv preprint dated 2021-04-15, but this check did not retrieve its full v1 text; no claim is made that every final-version assay/result was present in v1. Results are in-vitro amplification assays, not clinical diagnostic validation.
- AI role: MutCompute machine learning predicted amino-acid substitutions in Bst DNA polymerase; the authors constructed and assayed variants including Mut235.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC9514386/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 17 Nov 2026. Review scope: Primary PMC full journal text for MutCompute, LAMP assays, University of Texas affiliation and measured variants; primary bioRxiv v1 endpoint was attempted but blocked, so earlier-version result details remain bounded to what the journal and cited metadata support..
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A deep convolutional autoencoder trained on synthetic deformation and atmospheric-noise time series recovered millimeter-scale ground motion from real InSAR without being given the fault location. Applied to COSMO-SkyMed observations of the 2013 North Anatolian Fault slow-slip event, it detected about 2 mm of slip beyond the previously identified segment and revised the estimated along-strike event length from about 10 km to 15–20 km. The same paper used the approach to resolve transient millimeter-scale subsidence at California’s Coso geothermal field. This is one paper-level finding enabled by the model’s extraction of deformation signals from noisy satellite data.
Technology: Deep convolutional autoencoder trained on synthetic InSAR time series
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: A deep convolutional autoencoder trained on synthetic deformation and atmospheric-noise time series recovered millimeter-scale ground motion from real InSAR without being given the fault location.
- Still unknown: The newly resolved extension is a reanalysis of an existing 2013 InSAR event, not a newly occurring earthquake. The paper’s reported extension is model-derived; the original expert analysis had detected the larger slow-slip segment, while the autoencoder identifies an additional lower-amplitude portion. The model assumes atmospheric noise characteristics represented by its synthetic training data and omits some noise sources, including ionospheric perturbations. Coso results are a separate application within the same paper and are not counted separately.
- AI role: The deep autoencoder separated persistent ground deformation patterns from atmospheric noise in real InSAR data without prior fault-location information, resolving the additional 2 mm slow-slip segment; the model was trained on synthetic data and was not fine-tuned on the real case.
Evidence sources: https://arxiv.org/abs/2012.13849
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 136 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A machine-learning event detector combined with waveform cross-correlation produced a high-resolution catalog for injection-induced seismicity in the Weiyuan area, identifying one-third more earthquakes than the routine catalog and improving magnitude completeness. Spatial migration patterns show a pore-pressure diffusion front; a cluster outlines a potential unmapped fault that may have hosted the region’s largest recorded event, the September 2019 Mw 5.2 earthquake.
Technology: Machine-learning earthquake detector combined with waveform cross-correlation (the abstract does not name a particular detector architecture)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: A machine-learning event detector combined with waveform cross-correlation produced a high-resolution catalog for injection-induced seismicity in the Weiyuan area, identifying one-third more earthquakes than the routine catalog and improving magnitude completeness.
- Still unknown: The authors describe the fault as potential and state that it may have led to the September 2019 Mw 5.2 event; this is an interpretation, not a directly imaged fault or established causal proof. Results are from one field area and are limited by the station coverage.
- AI role: Detected additional earthquakes that enabled higher-resolution relocation and spatiotemporal mapping; authors use the denser catalog to infer a migrating pore-pressure front and identify a cluster outlining a potential fault trace.
Evidence sources: https://eppcgs.org/article/doi/10.26464/epp2021055?viewType=HTML
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 71 of works of the same type, year and subfield (OpenAlex work metrics, 20 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
EVE, an unsupervised deep generative model trained on evolutionary sequence variation across about 140,000 species, predicted pathogenicity for more than 36 million variants in 3,219 disease genes and classified over 256,000 variants of unknown significance. The authors report it outperforms methods trained on labelled disease data and performs on par with high-throughput experimental predictions. Caveat: the authors state EVE is not a diagnostic test.
Technology: EVE (deep generative evolutionary model, variational autoencoder)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: EVE's predictions were compared with methods trained on labelled disease data and with high-throughput experimental predictions.
- Still unknown: The authors state EVE is not a diagnostic test.
- AI role: An unsupervised deep generative model trained on evolutionary sequence variation across about 140,000 species, predicting pathogenicity for over 36 million variants.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41586-021-04043-8&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 855 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A random-forest classifier trained from molecular descriptors screened five databases containing about 23 million compounds for agonists of human olfactory receptors OR1A1 and OR2W1. Following docking and researcher selection, the paper reports in-vitro activation by ethyl 2-(3-bromophenyl)acetate and methyl 2-(2-methylphenyl)acetate at OR1A1 and 2-ethoxynaphthalene at OR2W1. These are cell-assay results; they do not establish human perception, tissue safety or clinical benefit. The compounds were selected after multiple filters, so the results are not a database-wide hit rate. Prior ML work on related receptors exists; this record is limited to the reported candidates and assays.
Technology: Random-forest classifier; molecular descriptors; homology-model docking
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Selected candidates were tested in vitro; the paper reports two active OR1A1 ligands and one active OR2W1 ligand.
- Still unknown: No in-vivo human olfaction or clinical effect is established. A 2018 study used ML for related human receptors; candidate-level overlap and priority remain bounded follow-up.
- AI role: The random-forest classifier screened chemical databases to rank candidates; docking and researcher selection further narrowed compounds for in-vitro validation.
Evidence sources: https://www.mdpi.com/1422-0067/22/21/11546
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 16 Nov 2026. Review scope: Primary publisher article, article metadata and author-affiliation block reviewed; summary is limited to reported assay results..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An automated continuous-flow polymer platform synthesized 397 copolymer compositions in a six-variable space, in iterative cycles guided by machine learning. Exploring under 0.9% of the compositional space, the models identified more than ten copolymers that outperformed state-of-the-art 19F MRI agents. Validation is experimental across hundreds of real syntheses, but the imaging performance claims are limited to the compositions tested.
Technology: Machine learning models guiding automated flow copolymer synthesis
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: An automated flow-synthesis platform made 397 copolymer compositions in a six-variable space; 10 compositions outperformed state-of-the-art 19F MRI agents.
- Still unknown: In vivo imaging performance is not reported in the abstract.
- AI role: Machine learning guided iterative synthesis cycles and identified non-intuitive design criteria.
Evidence sources: https://doi.org/10.1021/jacs.1c08181
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 165 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
ZTF observations identified AT2020xnd (ZTF20acigmel) at redshift 0.243 as the first unambiguous AT2018cow analogue found and confirmed in real time. Follow-up showed a rapid optical rise, persistently hot blue emission, luminous radio, millimetre and X-ray output, no classical radioactive-supernova peak, and a dwarf-galaxy host. The authors argue that these properties support a distinct fast-blue-optical-transient phenomenon, while its progenitor and central engine remain uncertain.
Technology: Zwicky Transient Facility real-time alert stream with a deep-learning real-bogus classifier and a custom contextual transient filter
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: ZTF observations identified AT2020xnd (ZTF20acigmel) at redshift 0.243 as the first unambiguous AT2018cow analogue found and confirmed in real time.
- Still unknown: This is one transient and a small class comparison, not a general population measurement. The AI contribution was alert filtering, not autonomous physical interpretation or confirmation; telescope follow-up was essential. The suggested distinct phenomenon is supported by shared observed properties, while the progenitor/engine interpretation remains unresolved and model-dependent.
- AI role: The paper’s custom search filter required the ZTF alert’s deep-learning real-bogus score to exceed 0.65, along with repeated detections, a high Galactic latitude and no coincident stellar counterpart. This AI-based alert filtering contributed to selecting AT2020xnd in real time; rapid multiband photometry and spectroscopic and multiwavelength human follow-up established its astrophysical nature and unusual properties.
Evidence sources: https://academic.oup.com/mnras/article/508/4/5138/6385772
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 79 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A machine-learning-guided iterative design–test–learn workflow engineered fatty acyl-ACP reductase variants for microbial fatty alcohol production. Across ten rounds, the study reports over twice the production of the starting natural sequences under tested conditions; the top sequence also had enhanced catalytic rate on palmitoyl-ACP. These are laboratory results, not industrial-scale production. The journal article date is used here; the earlier preprint’s exact posting and result-version differences were not checked.
Technology: Machine-learning-guided protein engineering; Gaussian-process optimization
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The paper reports ten design–test–learn rounds, in-vivo microbial fatty-alcohol production and catalytic-rate characterization on palmitoyl-ACP.
- Still unknown: Results are under the study’s microbial test conditions and do not establish industrial production; exact preprint-version results remain unchecked.
- AI role: Machine-learning models iteratively selected reductase sequences for experimental testing and subsequent model updates.
Evidence sources: https://www.nature.com/articles/s41467-021-25831-w
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary Nature Communications indexed full text, abstract, article date, author affiliations; preprint chronology not fully checked..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A Transformer-based model predicts gene expression from 200,000 base pairs of input DNA, over five times more than earlier methods, and is much more accurate at predicting variant effects. Enhancer attribution scores are comparable to methods using experimental data. The post gives no numerical gain and acknowledges that linking enhancers to the genes they regulate remains an open problem.
Technology: Enformer (Transformer)
Family Enformer: profile · models page
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Enformer is compared with prior models on variant-effect prediction and enhancer contribution scores against methods using experimental data, with a rs11644125 case study.
- Still unknown: Linking enhancers to the genes they regulate is described as a major unsolved problem, and many disease variants are spuriously correlated.
- AI role: Transformer model predicted gene expression from 200,000 base pairs of DNA.
Evidence sources: https://deepmind.google/blog/predicting-gene-expression-with-ai/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1038/s41592-021-01252-x&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 1533 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
ECNet integrated evolutionary context with learned sequence representations to prioritize previously untested higher-order TEM-1 variants. The authors constructed and measured 37 selected variants under ampicillin selection, using relative resistance as an enzyme-fitness proxy. The assays do not imply clinical treatment outcomes, and the reported group of 37 should not be read as showing that every variant improved.
Technology: ECNet evolutionary-context-integrated deep-learning framework
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Thirty-seven previously untested higher-order TEM-1 variants selected with ECNet were constructed and experimentally measured under ampicillin selection against wild-type and study controls. The study uses relative resistance as an enzyme-fitness proxy.
- Still unknown: The bounded entry does not imply that all 37 variants improved equally, does not establish clinical outcomes, and makes no claim of independent sequence novelty beyond the authors’ screened literature.
- AI role: ECNet integrated evolutionary context and a learned representation to prioritize higher-order TEM-1 variants for experimental construction and ampicillin-selection measurements.
Evidence sources: https://www.nature.com/articles/s41467-021-25976-8 · https://zhaogroup.web.illinois.edu/publications/HZ370.pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 17 Nov 2026. Review scope: Primary Nature indexed article and author-hosted full text; official bioRxiv API checked and identified the previously associated preprint DOI as a different paper..
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Developed with the UK Met Office, the model forecasts precipitation up to two hours ahead; over 50 expert meteorologists chose it as their first choice in 89% of cases compared with the most widely used methods. The authors cite long-range accuracy and rare, intense events as limitations.
Technology: Deep generative radar model (DGMR)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Over 50 Met Office meteorologists chose the model first in 89% of cases, and it was compared with PySTEPS and UNet on UK and US radar data.
- Still unknown: No method is without limitations; long-range accuracy and rare intense events need improvement.
- AI role: Generative model forecast precipitation up to two hours ahead.
Evidence sources: https://deepmind.google/blog/nowcasting-the-next-hour-of-rain/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1038/s41586-021-03854-z&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 1232 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Evolutionarily informed XGBoost and GENIE3 analyses of conserved nitrogen-response expression patterns prioritized transcription factors associated with nitrogen-use efficiency in Arabidopsis and maize. Loss-of-function tests found higher NUE in Arabidopsis myb33 and tcp2 mutants under both low- and high-nitrogen conditions, and in six other tested TF mutants specifically under low nitrogen; a maize nfya3 mutant also showed higher nitrogen-use efficiency under sufficient nitrogen in field tests.
Technology: Evolutionarily informed XGBoost models and GENIE3 random-forest gene-regulatory-network inference
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Loss-of-function tests found higher NUE in Arabidopsis myb33 and tcp2 mutants under both low- and high-nitrogen conditions, and in six other tested TF mutants specifically under low nitrogen; a maize nfya3 mutant also showed higher nitrogen-use efficiency under sufficient nitrogen in field tests.
- Still unknown: The machine-learning prediction scores are not themselves causal evidence; this paper adds functional evidence from specific mutants. Some tested maize candidate roles were assessed through Arabidopsis homologs, and the maize NFYA3 phenotype described here was under sufficient-N field conditions, not a general yield benefit across conditions.
- AI role: The models ranked conserved nitrogen-responsive genes and transcription factors for contribution or network connectivity to NUE; researchers selected the candidates and tested loss-of-function mutants in Arabidopsis and maize, including field-grown maize.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8463701/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 109 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A variational autoencoder ranked unexplored element combinations for lithium solid electrolytes. Researchers combined those rankings with crystal-structure prediction and synthesis to discover Li₃.₃SnS₃.₃Cl₀.₇, then characterized its structure and lithium-ion transport. Impedance, NMR and lithium-cell measurements supported a new transport pathway and compatibility with lithium metal.
Technology: Unsupervised machine learning for element selection with crystal structure prediction
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Synthesis, diffraction, impedance and NMR characterization of the selected lithium solid electrolyte, with lithium plating/stripping measurements.
- Still unknown: This is a laboratory material study; full-battery performance and independent replication were not assessed.
- AI role: An unsupervised variational autoencoder ranked chemical element combinations; human selection and crystal-structure calculations directed synthesis.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8455628/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A%2210.1038%2Fs41467-021-25343-7%22&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 86 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A first-principles database and neural-network-potential search explored 396,862 Pt–Fe–Cu nanoparticle configurations and mapped candidate compositions. The team synthesized PtFeCu variants and measured oxygen-reduction reaction (ORR) performance. A tested PtFeCu formulation showed about 3.1-fold higher specific activity (776 μA cm⁻² Pt) and 3.2-fold higher mass activity (0.67 A mg⁻¹ Pt) than Pt/C at 0.9 V; the authors attribute activity and improved durability to Cu-dependent surface-strain modulation and reduced Fe segregation, supported by calculations and experimental tests.
Technology: DFT-integrated neural-network potentials and machine-learning configuration search
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A first-principles database and neural-network-potential search explored 396,862 Pt–Fe–Cu nanoparticle configurations and mapped candidate compositions.
- Still unknown: The result is a PtFeCu catalyst-composition/configuration finding, not a claim that the ternary system itself was previously unknown. The paper labels the high-/low-Cu variants inconsistently between its abstract/results and conclusion, so the quoted activity values are not tied here to a disputed variant name. Activity was measured in O2-saturated 0.1 M HClO4 using a rotating-disk setup; durability used a 30,000-cycle accelerated stress test, not a full fuel-cell operating lifetime. The reported 2 g batch capacity is a synthesis-scale result, not commercial manufacturing validation.
- AI role: The authors built neural-network potentials from first-principles data, screened 396,862 PtFeCu nanoparticle configurations, and used the predicted ternary configuration/composition map to guide experimental synthesis and selection of catalyst variants. The model-supported search was used to identify composition-dependent ORR activity and stability relationships; measurements and physical interpretation were performed by the research team.
Evidence sources: https://doi.org/10.1016/j.checat.2021.06.001
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 86 of works of the same type, year and subfield (OpenAlex work metrics, 59 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The EXAM federated model, trained on data from 20 institutes without sharing patient data, achieved an average AUC above 0.92 for predicting oxygen requirements at 24 and 72 hours. At the largest independent test site it reached sensitivity 0.950 and specificity 0.882, with a 16% average AUC gain over single-site models. Caveat: retrospective data from the pandemic period and unharmonized sites.
Technology: EXAM federated learning model (EMR data and chest X-rays)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Data from 20 institutes; average AUC above 0.92 for oxygen-requirement outcomes at 24 and 72 hours, 16% higher average AUC than single-site models; at the largest independent site, sensitivity 0.950 and specificity 0.882 for ventilation or death at 24 hours.
- Still unknown: Effect on patient care when used in practice is not reported in the abstract.
- AI role: EXAM, a model trained by federated learning on vital signs, laboratory data and chest X-rays without exchanging data between sites.
Evidence sources: https://doi.org/10.1038/s41591-021-01506-3
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 964 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 5/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Using machine learning on data from over 300 satellites and 11,100 sensors (over 59 trillion bytes), emissions from oil and gas in major countries were estimated at about twice UNFCCC reports (about 1 billion tonnes more), while rice emissions in India were nearly three times the official 2016 inventory. No peer review; the page gives both September 14 and September 16, 2021.
Technology: Machine learning on satellite and sensor data
Publication: Announcement only · Test context: Test context unspecified in annotation. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Announcement only
- Test type: not reported
- Tested: The page gives no methodology for checking the estimates; it says more than 50 outside organisations reviewed methodology and validated findings, without describing results.
- Still unknown: The page notes granularity is still developing and that estimates are hedged and constantly evolving; no peer review is mentioned.
- AI role: Machine learning on satellite and sensor data estimated global emissions.
Evidence sources: https://climatetrace.org/news/climate-trace-releases-first-comprehensive-independent
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 4/5 · Validation 1/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A high-throughput optical screen and data-science models identified a Co–Ta–Sn composition region whose optical trends indicated phase behavior beyond simple mixtures. Follow-up X-ray diffraction verified a rutile substitutional-alloy oxide, (Sn,Co,Ta)O₂. Composition tuning produced optical transparency and oxygen-evolution electrocatalytic activity with stability in strong-acid electrolyte, as reported by the authors.
Technology: Physics-aware data-science phase-diagram and emergent-property models
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A high-throughput optical screen and data-science models identified a Co–Ta–Sn composition region whose optical trends indicated phase behavior beyond simple mixtures.
- Still unknown: The phase inference initially came from optical data and the authors discuss potential false positives from extrinsic film morphology; the selected Co–Ta–Sn rutile phase was followed up and verified by XRD. The optical screen identifies promising regions, not all possible phases, and may miss phases without emergent optical signatures. Reported oxygen-evolution performance and acid stability are laboratory electrocatalysis results; no commercial device or scale-up is established.
- AI role: Models analyzed high-throughput optical absorption measurements across 376,752 compositions in 108 three-cation oxide systems. They inferred candidate phase diagrams and flagged optical trends inconsistent with lower-order phase mixtures, guiding the Co–Ta–Sn follow-up composition and XRD experiments that verified a rutile alloy phase; this screening also guided catalytic characterization.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8449358/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 88 of works of the same type, year and subfield (OpenAlex work metrics, 38 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
COMPOSER, a deep-learning early sepsis predictor, reached AUCs of 0.925-0.953 in ICU and 0.938-0.945 in ED across six cohorts (515,720 patients) from two US health systems. About 20% of non-septic and 8% of septic prediction windows were marked indeterminate, and the model gave a median early warning of 12.2 hours in ICU and 2.1 hours in ED before the first antibiotics order. The abstract reports no prospective deployment or patient-outcome results.
Technology: COMPOSER deep-learning model with uncertainty-based indeterminate output
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: COMPOSER's AUCs were measured across six cohorts (515,720 patients) from two US health systems in ICU and ED settings, with the share of predictions marked indeterminate and early-warning time before the first antibiotics order.
- Still unknown: The abstract reports no prospective deployment or patient-outcome results; data come from only two US health systems.
- AI role: A deep-learning model predicted early sepsis and marked unfamiliar cases as indeterminate rather than guessing.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41746-021-00504-6&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 147 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Random-forest and k-nearest-neighbors QSAR models trained on known odorant responses prioritized natural-product candidates for two Spodoptera littoralis odorant receptors. The paper reports receptor responses for selected compounds and Y-maze preference for seven strong agonists; all seven were preferred at 10⁻² dilution, while three retained preference at 10⁻³. The percentages of receptor-active candidates apply to selected test sets and are not field trap accuracy. The fly-neuron assay is heterologous, and larval choice is laboratory evidence, not crop-protection efficacy or ecological safety. This extends the same group’s 2020 receptor-ligand study; count the 2021 behavior result as one study, not each molecule or a separate model discovery.
Technology: Random-forest QSAR and k-nearest-neighbors classifier
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Selected ML-prioritized receptor ligands were tested electrophysiologically and in larval Y-maze assays; the paper reports the stated dose-dependent preference outcomes.
- Still unknown: No field efficacy, human health benefit, broad ecological selectivity or global priority is established. The study extends earlier same-group work; its compounds and behavior result are bounded to the reported assays.
- AI role: The models ranked candidate natural-product ligands for SlitOR24/SlitOR25; researchers selected the targets and candidates and performed the receptor and larval behavioral experiments.
Evidence sources: https://link.springer.com/article/10.1007/s00018-021-03919-2
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 16 Nov 2026. Review scope: Primary publisher article, article metadata and author-affiliation block reviewed; summary is limited to reported assay results..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The model outperforms ECMWF’s SEAS5 dynamical system in seasonal forecasts of summer sea ice, especially for extreme events, and is over 2,000 times faster (under ten seconds on a GPU). SEAS5 is better at a one-month lead, and the September comparison covers nine years; published in Nature Communications.
Technology: IceNet (probabilistic deep learning)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: IceNet is compared with the SEAS5 dynamical model in seasonal summer sea-ice forecasts, especially extreme events.
- Still unknown: Not reported in the abstract read.
- AI role: Probabilistic deep-learning model forecast the next six months of sea-ice concentration.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=PMCID:PMC8390499&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Machine-learning property models and phenomenological screening rules narrowed a list of more than 13,000 previously synthesized polymers to candidates for high-temperature dielectric applications. The authors report experimental testing of selected candidates and derive design rules for electric-field and temperature tolerance. Review is limited to the abstract and publication metadata.
Technology: Machine learning and informatics models for polymer dielectric screening
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Property-based screening of over 13,000 known polymers, followed by experimental validation of some selected dielectric candidates.
- Still unknown: Review scope: abstract, online date and affiliations. Candidate-by-candidate property values and the full experimental sample count were not assessed.
- AI role: Machine-learning models predicted screening properties such as band gap and cohesive energy density.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A%2210.1021%2Facsami.1c11885%22&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 84 of works of the same type, year and subfield (OpenAlex work metrics, 41 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The interpretable THESEUS design algorithm produced a three-dimensional six-photon GHZ-state blueprint that suppresses unwanted state terms toward arbitrarily high fidelity, with lower count rates, and a heralded three-dimensional Bell-state blueprint using destructive interference to cancel vacuum contributions. The same graph-based reasoning generalized the constructions to larger photon numbers or dimensions.
Technology: THESEUS
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: The interpretable THESEUS design algorithm produced a three-dimensional six-photon GHZ-state blueprint that suppresses unwanted state terms toward arbitrarily high fidelity, with lower count rates, and a heralded three-dimensional Bell-state blueprint using destructive interference to cancel vacuum contributions.
- Still unknown: These are theoretically calculated experiment blueprints, not experimentally demonstrated states in this paper. For the six-photon GHZ design, unwanted amplitudes can be reduced arbitrarily by adjusting graph weights, at the cost of lower count rates; feasibility is argued for contemporary photonics. The heralded Bell design’s estimated count rate and fidelity are modeled, not measured.
- AI role: The authors’ AI-enabled automated design algorithm used an interpretable weighted, colored-graph representation of photonic experiments, gradient-based optimization, and topology reduction to search open experiment-design problems and expose generalizable physical concepts. The authors identify the work as explainable AI; the contribution is the algorithmically found design/concept, not merely faster benchmarking.
Evidence sources: https://journals.aps.org/prx/abstract/10.1103/PhysRevX.11.031044
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 70 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Hybrid classification and regression models with physically motivated descriptors, trained on about 5,000 metallic-glass compositions, guided exploration of multicomponent alloy compositions. Researchers synthesized 23 selected compositions: 12 predicted glass-formers produced glass in bulk, ribbon or both, while 11 predicted negative comparisons did not form glass under the tested preparation conditions. Six of the positive designs formed bulk glass; six formed glassy ribbons only. These selected experiments are not an unbiased estimate of global predictive accuracy. Some authors disclosed inventorship on a filed patent related to the new bulk compositions; composition-level prior art and independent replication remain open.
Technology: Hybrid classification/regression models including adaptive boosting, SVM, KNN and rational-quadratic Gaussian-process regression
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The study reports synthesis and diffraction/thermal characterization of selected predicted positive and negative compositions.
- Still unknown: Selected validation set, not unbiased global accuracy; patent inventorship disclosed and composition-level novelty/replication remain open.
- AI role: Hybrid models trained on prior metallic-glass data prioritized compositions for synthesis and measurement.
Evidence sources: https://www.nature.com/articles/s41524-021-00607-4 · https://scholars.cityu.edu.hk/ws/portalfiles/portal/86074146/82269007.pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary publisher full indexed article and institutional full-text copy, methods, results, date, affiliation and patent disclosure..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A path-independent machine-learning protocol screens full combinatorial protein libraries in silico, with training-set design that avoids near-zero-fitness variants. On a four-site epistatic fitness landscape the optimized protocol reached the global fitness maximum up to 81-fold more often than single-step greedy optimization. Caveat: validation is on a combinatorial fitness landscape dataset, not a new wet-lab evolution campaign.
Technology: Machine-learning-assisted directed evolution (in silico combinatorial screening)
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: The ML-assisted directed evolution protocol was compared with single-step greedy optimization on a four-site epistatic fitness landscape.
- Still unknown: Not reported in the abstract read.
- AI role: A path-independent machine-learning protocol that screens full combinatorial libraries in silico, with training-set design avoiding near-zero-fitness variants.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1016/j.cels.2021.07.008&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 220 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Models fitted to observations from 70 Scandinavian lakes identified nonmonotonic associations between browning indicators and bacterial community diversity. XGBoost explained up to about 45% of community-composition variation in the analyzed data. The fitted ridges are not demonstrated causal tipping points; translating this spatial gradient into future temporal trajectories requires further validation.
Technology: XGBoost, random forests and feed-forward neural networks
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Models analyzed field-sampled microbial communities with held-out evaluation.
- Still unknown: Covariation, causal mechanisms and long-term temporal predictions remain unresolved.
- AI role: XGBoost, random forests and feed-forward neural networks supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://www.nature.com/articles/s43705-021-00038-8 · https://www.nature.com/articles/s43705-021-00038-8.pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary publisher PDF abstract and selected Methods/Results/limitations; indexed publisher publication metadata. Supplements not reviewed..
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A generator–predictor–optimizer deep-learning workflow trained on quantitative delivery assays was used to design abiotic Mach miniproteins. Twelve selected predicted constructs were synthesized/tested; the strongest library construct improved phosphorodiamidate morpholino oligomer (PMO) delivery nearly 20-fold over unconjugated PMO in the standardized HeLa assay, while the authors describe the best designs as up to 50-fold more effective than prior polypeptide-based variants. PMO–Mach3/4 also produced dose-dependent reporter-protein restoration in skeletal muscle, diaphragm and heart in transgenic mice after a single intravenous dose.
Technology: Deep-learning generator–predictor–optimizer workflow: nested-LSTM sequence generator, CNN activity predictor on residue chemical fingerprints, and evolutionary optimization
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A generator–predictor–optimizer deep-learning workflow trained on quantitative delivery assays was used to design abiotic Mach miniproteins.
- Still unknown: The paper reports improved delivery in a standardized HeLa reporter assay and transgenic mouse reporter model, not therapeutic correction of a disease. Only selected designs were synthesized (12 from hundreds of predicted sequences); mouse experiments used an EGFP reporter transgene and short seven-day follow-up. The article separately states the library's highest construct was nearly 20-fold over PMO alone and characterizes the designs as 50-fold better than previously known polypeptide variants; these denominators are not interchangeable. Safety evidence is limited to reported assays/doses and short follow-up.
- AI role: The model generated seed cell-penetrating sequences, predicted quantitative nuclear-delivery activity from peptide fingerprints, and iteratively optimized sequences for higher predicted activity subject to length, charge, similarity and solubility constraints. The team synthesized and experimentally assayed selected model-designed peptides; this linked the AI design to measured enhanced PMO delivery and animal reporter results.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8819921/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 86 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Insilico Medicine named INS018_073 a preclinical candidate after in vitro tests and testing in a mouse model of renal fibrosis. The company reports improvements in pathology, biomarkers, and histologically observed fibrosis. The candidate was proposed for IND-enabling studies; these are company-reported preclinical results, not clinical evidence or independent confirmation.
Technology: Pharma.AI / Chemistry42
Publication: Announcement only · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Announcement only
- Test type: direct test
- Tested: Company-reported in vitro potency (nanomolar) and a mouse unilateral ureteral obstruction model with histology, plus a 14-day mouse safety study.
- Still unknown: No effect sizes, doses or biomarkers are named, and no independent confirmation or peer review is stated.
- AI role: AI-driven target and compound identification (PandaOmics) produced the candidate.
Evidence sources: https://insilico.com/blog/pcc_kidney
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Predicted structures for the human proteome (about 20,000 proteins) and 20 other organisms were published, over 350,000 models in total, hosted free by EMBL-EBI. DeepMind announced an expansion to over 100 million structures. These are predictions that complement experimental methods. Note: the page header says July 22, 2022, but the text calls CASP14 “last December” and the 2022 post refers to it as a 2021 release; date corrected to 2021.
Technology: AlphaFold 2
Family AlphaFold: profile · models page
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Predictions cover 98.5% of human proteins; 58% of residues have a confident prediction and 36% very high confidence. Case studies illustrate possible hypotheses.
- Still unknown: The structures are predictions; the abstract does not report experimental confirmation of new structures.
- AI role: AlphaFold 2 applied at proteome scale, with confidence metrics built on the model.
Evidence sources: https://doi.org/10.1038/s41586-021-03828-1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 3058 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 5/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A protein language model generated synthetic lysozymes: two of the five characterized in cells degraded bacterial cell walls with activity comparable to egg-white lysozyme. Laboratory tests and crystallography support the result, but do not demonstrate clinical applications. The preprint dates to July 18, 2021; the Nature Biotechnology publication and UCSF announcement are from January 2023.
Technology: ProGen
Family ProGen: profile · models page
Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: direct test
- Tested: Five model-generated lysozyme families were experimentally characterised, with activity and catalytic efficiency compared with natural lysozymes, and crystal structures reported.
- Still unknown: Not reported in the abstract read.
- AI role: Protein language model trained on over 280 million sequences generated artificial lysozymes.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1101/2021.07.18.452833&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A three-track neural network (sequence, residue interactions, and 3D structure) computes a structure in about ten minutes on a single gaming computer. Baker’s group predicted hundreds of new structures, including little-known proteins in the human genome. The web server received over 4,500 requests in the previous month. The page does not state limitations.
Technology: RoseTTAFold
Family RoseTTAFold: profile · models page
Publication: Peer-reviewed paper · Test context: Test context unspecified in annotation. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: not reported
- Tested: The page describes the tool's speed and hundreds of new structures but does not describe how predictions were checked.
- Still unknown: Not reported.
- AI role: Three-track neural network predicted protein structures.
Evidence sources: https://www.ipd.uw.edu/2021/07/rosettafold-accurate-protein-structure-prediction-accessible-to-all/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1126/science.abj8754&resultType=core&format=json
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 5653 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 1/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Neural networks decoded the attempted speech of a man with stroke-related paralysis, displaying words and sentences on a screen. With a 50-word vocabulary, the system reached up to 18 words per minute and a median accuracy of 75%. Proof of principle in one person, using an implant on the brain surface and a limited vocabulary.
Technology: Neural networks for speech and language model
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Decoding was tested in one participant over 48 sessions using a 50-word vocabulary, reaching up to 18 words per minute and a median accuracy of 75%.
- Still unknown: It is a proof of principle in one person with a limited vocabulary, per the press release.
- AI role: Deep-learning algorithms decoded attempted words from cortical activity.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1056/NEJMoa2027540&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 616 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A microbiome metabolomics study used random-forest models to associate bacterial metabolite profiles with taxonomy and found a previously undescribed nitrogen-assimilation pattern in Bacteroides/Bacteroidetes. Follow-up growth experiments tested 60 Bacteroidetes strains with asparagine or glutamine as the sole nitrogen source and supported the predicted phenotype; the study also reports a distinct reduced-sulfur utilization result in B. thetaiotaomicron.
Technology: Random-forest models over metabolomics profiles
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Follow-up growth experiments tested 60 Bacteroidetes strains with asparagine or glutamine as the sole nitrogen source and supported the predicted phenotype; the study also reports a distinct reduced-sulfur utilization result in B. thetaiotaomicron.
- Still unknown: The study's abstract reports machine-learning discovery of a new metabolism and the figure captions document follow-up culture tests; the article's full text is paywalled in this session, so the exact mechanistic pathway is not asserted. Mouse and culture evidence do not establish a human health effect.
- AI role: The models identified metabolite features that distinguished taxa and highlighted a previously undescribed Bacteroides metabolic phenotype; researchers then tested bacterial growth under defined nitrogen sources. Comparative-genomics pathways remained candidate explanations rather than proven pathways.
Evidence sources: https://www.nature.com/articles/s41586-021-03707-9
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 417 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Learning from transcriptomic networks helped prioritize PRKAB1 for experimental follow-up. An agonist improved a barrier-resistance endpoint in about 80% of diseased patient-derived organoids in the tested sample. This is preclinical target-response evidence, not treatment of patients or clinical efficacy. The network direction incorporates sample labels and does not independently establish causal disease progression.
Technology: Boolean Network Explorer learned implication networks
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Patient-derived organoid barriers and preclinical models were tested.
- Still unknown: Clinical safety and benefit, independent replication and causal network direction remain unestablished.
- AI role: Boolean Network Explorer learned implication networks supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8275683/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary article metadata, affiliations, selected network Methods and organoid Results; supplements not reviewed..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A two-stage 1D CNN pipeline applied to continuous three-component seismic waveforms from one L’Aquila station identified 273 previously uncataloged local earthquake events during a one-month 2009 foreshock period. The study reports that 84% were assigned magnitude below 1 and that all 273 new detections were visually confirmed; the expanded catalog contained roughly three times as many new detections as the pre-existing catalog had events for that period.
Technology: Two-stage one-dimensional convolutional neural network (CNN) pipeline
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: A two-stage 1D CNN pipeline applied to continuous three-component seismic waveforms from one L’Aquila station identified 273 previously uncataloged local earthquake events during a one-month 2009 foreshock period.
- Still unknown: The analysis covers one month in February 2009 from one station. The authors report 273 new local detections and six nonlocal events among 369 windows classified as local; all 273 new detections were visually confirmed. The pipeline does not provide exact event locations, and transfer to other regions was not established. Magnitudes are coarse classes, not precise estimates.
- AI role: The detector CNN scanned continuous raw three-component waveform windows for earthquake signals; a second CNN classified distance and magnitude, enabling the researchers to find and characterize uncataloged events from a single station. The CNN pipeline generated the new event detections; authors then visually checked them.
Evidence sources: https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2020JB021566
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 84 of works of the same type, year and subfield (OpenAlex work metrics, 33 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
iTARGEX applied a mixture-regression model to gene-expression profiles from 1,484 single-gene deletion yeast mutants, associating transcriptomic changes with S-phase transcriptional buffering and global protein turnover. Experiments supported ELG1 as a previously unrecognized regulator of transcriptional buffering during S phase; the phenotype was reproduced in a second genetic background and rescued by a PCNA-D150E mutation. Follow-up protein-turnover measurements showed altered turnover in MRN1, UPF3, RAM1 and SSN3 deletion strains.
Technology: iTARGEX, a finite-mixture regression framework fitted by expectation maximization to single-gene-deletion transcriptomic data
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Experiments supported ELG1 as a previously unrecognized regulator of transcriptional buffering during S phase; the phenotype was reproduced in a second genetic background and rescued by a PCNA-D150E mutation.
- Still unknown: The study used budding yeast and pre-existing deletion-mutant transcriptome profiles, followed by experiments on selected candidates. ELG1's role in S-phase transcription buffering was reproduced in a second yeast genetic background and rescued by PCNA-D150E; the protein-turnover effects concern yeast deletion strains. These results do not establish corresponding human functions.
- AI role: iTARGEX associated gene-expression profiles from deletion strains with biological traits without requiring prior gene annotations and nominated candidate regulators. The researchers then performed S-phase transcription and protein-turnover experiments to test the model-prioritized candidates, supporting ELG1's role in transcriptional buffering and altered turnover for four deletion strains.
Evidence sources: https://academic.oup.com/nar/article/49/13/7318/6312755
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 32 of works of the same type, year and subfield (OpenAlex work metrics, 2 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Using Marinopyrrole A as a template, an automated design workflow generated and synthesized new natural-product-inspired molecules; target-prediction software pointed to cyclooxygenases. In biochemical assays, synthetic mimetics 2 and 2a inhibited COX-1 at 0.10 and 0.16 μM, respectively, and compound 2a was crystallographically observed bound to COX-1. Human platelet assays also showed inhibition.
Technology: DOGS rule-based de novo molecule construction and CATS molecular-similarity ranking, coupled with SPiDER self-organizing-map machine-learning target prediction
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: In biochemical assays, synthetic mimetics 2 and 2a inhibited COX-1 at 0.10 and 0.16 μM, respectively, and compound 2a was crystallographically observed bound to COX-1.
- Still unknown: The study tests a small number of designed molecules; automated structure generation was rule-based and similarity-driven rather than a trained generative neural model. The COX-1 effects were biochemical/platelet assays, not clinical effects; the platelet IC50s for 2, 2a, 2b were 9, 13 and 56 nM, but COX-2 inhibition occurred at higher concentrations and selectivity varies by assay. Do not call these approved drugs or imply therapeutic benefit.
- AI role: DOGS algorithmically generated natural-product-inspired structures and suggested synthetic routes; CATS ranked candidates by pharmacophore similarity. SPiDER's cascaded self-organizing-map models predicted molecular target families, including COX. Experimental target assays confirmed the previously unrecognized COX-1 activity of selected synthetic compounds, with crystallographic confirmation for compound 2a.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8373093/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 84 of works of the same type, year and subfield (OpenAlex work metrics, 31 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Deep learning models trained on 11,374 smartphone-tablet images of HIV lateral-flow tests, captured by 60 fieldworkers, classified results with 97.8% sensitivity and 100% specificity in a pilot field study compared with human visual reading. The approach also reduced false positives and false negatives relative to human readers. Caveat: a pilot deployment in one rural setting, so wider field validation is still needed.
Technology: Deep learning image classifier on mobile-captured rapid test images
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: In a pilot field study, deep learning classification of photographed HIV rapid tests reached 97.8% sensitivity and 100% specificity, compared with human visual reading by experienced nurses.
- Still unknown: Not reported; the page describes the study only as a pilot field study.
- AI role: Deep learning models trained on 11,374 smartphone images of lateral-flow tests classified results in a mobile application.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41591-021-01384-9&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 156 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Non-negative matrix factorization (NMF) was applied to stream-chemistry time series from three watersheds to infer solute endmembers and their changing contributions without predefining endmember chemistry. Combined with geological interpretation and independent geochemical evidence, the model separated shallow acid-rain-affected flow from deeper pyrite-weathering contributions. The analysis found that acid rain can reduce a watershed’s long-timescale CO₂-sequestration capacity and that omitting sulfide oxidation/acid-rain reactions overestimates weathering-driven CO₂ drawdown.
Technology: Non-negative matrix factorization (NMF) machine-learning blind-source-separation model applied to stream chemistry
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Non-negative matrix factorization (NMF) was applied to stream-chemistry time series from three watersheds to infer solute endmembers and their changing contributions without predefining endmember chemistry.
- Still unknown: This is an inference from historical stream chemistry and watershed-specific geology, not a direct measurement of global CO₂ sequestration or a causal intervention. The NMF endmembers were interpreted as subsurface flowpaths using geological knowledge and supporting geochemical evidence; the inferred acid-rain sulfate export at Shale Hills includes a 19–31-year lag estimate. The result applies to three studied watersheds and the weathering timescales considered. Endmember counts and interpretations depend on the model setup and watershed reaction-front assumptions.
- AI role: The NMF model simultaneously inferred endmember chemical signatures and per-sample mixing proportions from solute ratios without preset endmember compositions. Researchers interpreted those patterns using watershed geology, sulfur isotopes, weathering profiles and calcite saturation, then estimated mineral-weathering rates and CO₂ sequestration. The ML decomposition enabled source separation where conventional endmember assumptions were uncertain; it did not directly measure a global carbon flux.
Evidence sources: https://hess.copernicus.org/articles/25/3397/2021/index.html
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 35 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A recurrent neural network generated de novo LXR agonist designs, and 25 were synthesized in a microfluidic flow system. In vitro screening found 17 hits (68%), and 12 were confirmed as potent LXR agonists after batch resynthesis. Validation is in vitro only, with no in vivo testing, and the sources disagree on the number of designs retained for synthesis.
Technology: LSTM recurrent neural network generator with transfer learning, coupled to on-chip flow synthesis
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: 25 synthesized designs were screened in reporter gene assays (17 hits); 12 were confirmed as LXR agonists after batch resynthesis, with EC50 0.18 to 4.5 micromolar for LXR-alpha. No in vivo testing was reported.
- Still unknown: Chemical space was limited to one-step reactions, the primary screen used crude mixtures, two compounds were not confirmed, and the authors describe the work as proof-of-concept.
- AI role: A generative LSTM pretrained on 656,070 compounds and fine-tuned on 40 known LXR-alpha agonists, with a virtual reaction filter of 17 reaction schemes.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8195470/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 203 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An interpretable machine-learned descriptor for decomposition enthalpy screened more than 200,000 Chevrel-phase compositions, predicting 48,501 below the study’s statistical synthesizability cutoff. Researchers selected five previously unreported tellurides for synthesis and successfully made all five; experiments also confirmed the predicted preference for intercalant cations to occupy Chevrel-phase channels, a rare motif in this family. The predicted candidate list is much larger than the experimentally attempted and confirmed subset. The date is the journal paper’s online publication; UC Davis announced it on 24 June 2021.
Technology: SIFT descriptor-generation and interpretable machine-learning model Hδ
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: An interpretable machine-learned descriptor for decomposition enthalpy screened more than 200,000 Chevrel-phase compositions, predicting 48,501 below the study’s statistical synthesizability cutoff.
- Still unknown: The original paper abstract reports five successful syntheses among five tellurides attempted and confirms a predicted channel-site occupancy trend. The other thousands of predicted candidates were not demonstrated as synthesized in this study. The result concerns a specific molybdenum-chalcogenide family.
- AI role: The SIFT method generated more than 560,000 candidate descriptors; an interpretable ML model trained against DFT-computed decomposition enthalpies assessed synthesizability and selected Chevrel-phase compositions for experimental follow-up.
Evidence sources: https://chemistry.ucdavis.edu/news/machine-learning-assisted-discovery-chevrel-phase-tellurides
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 87 of works of the same type, year and subfield (OpenAlex work metrics, 43 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A machine-learning feature-selection pipeline integrated public whole-blood (1,885 samples) and synovial-tissue (284 samples) transcriptomic datasets and selected a 13-gene rheumatoid-arthritis score. Across five independent transcriptomic datasets, the score tracked DAS28 disease activity, distinguished rheumatoid arthritis from osteoarthritis, separated polyarticular juvenile idiopathic arthritis from healthy controls, and was associated with treatment effects. In an independent immunoblot cohort, two of six tested proteins, TNFAIP6/TSG-6 and HSP90AB1/HSP90, were confirmed.
Technology: Cross-tissue machine-learning feature-selection pipeline for transcriptomic data
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: In an independent immunoblot cohort, two of six tested proteins, TNFAIP6/TSG-6 and HSP90AB1/HSP90, were confirmed.
- Still unknown: The transcriptomic inputs were previously published datasets and the reported clinical associations are observational; the study does not establish a deployable diagnostic test or causal disease mechanism. The independent protein follow-up confirmed two of six proteins tested, not the entire 13-gene panel, and validation in larger prospective cohorts is needed. Treatment-effect association should not be interpreted as prospective prediction of individual response.
- AI role: The pipeline selected a compact 13-gene signature from public blood and synovial expression datasets; the study evaluated its association with disease activity and diagnostic distinctions across five independent transcriptomic datasets, then tested six selected proteins by immunoblot in a separate patient cohort.
Evidence sources: https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2021.638066/pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 47 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Unsupervised k-means clustering of seven Landsat 8 spectral bands highlighted a small set of priority areas for paleontological field survey in Gorongosa National Park. The 2018 campaign documented four new late Miocene fossil localities; three lay within the model’s target cluster and the fourth was less than 90 m away in the same gully system. Together, the sites expose the first reported estuarine coastal-forest fossil setting in the East African Rift System, filling a regional paleoenvironmental gap.
Technology: Unsupervised k-means clustering of Landsat 8 imagery
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Unsupervised k-means clustering of seven Landsat 8 spectral bands highlighted a small set of priority areas for paleontological field survey in Gorongosa National Park.
- Still unknown: This was a pilot study in a 36 km² area and the model had notable false positives: reported precision was 55.56%, despite 84.6% overall accuracy. Three of four new localities overlapped the selected cluster; the fourth was less than 90 m away and was found by surveying the same gully system, so model localization for that site is indirect. The findings are four new fossil localities, not four new hominin taxa; the reported estuarine coastal-forest interpretation is a paleoenvironmental inference.
- AI role: The authors clustered seven spectral bands without pre-labeled land-cover classes, compared clusters with known fossil localities, and selected the cluster containing most known sites as a predictive target for field prospecting. This decision-support workflow directed the 2018 field survey that documented the new localities; a random forest was separately used to estimate spectral-band importance.
Evidence sources: https://peerj.com/articles/11573/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 71 of works of the same type, year and subfield (OpenAlex work metrics, 14 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Using explainable AI on single-forcing CESM1 large ensembles, the study identified the North Atlantic, Southern Ocean and Southeast Asia as key regional temperature patterns for dating the climate simulations, particularly before the early 21st century. When applied to reanalysis observations, the neural network trained on an ensemble with industrial aerosols fixed at 1920 levels predicted the actual year more closely than networks trained on the all-forcing or greenhouse-gas-fixed ensembles. The authors interpret this as evidence that simulated regional temperature signals are sensitive to aerosol forcing.
Technology: Artificial neural network trained on CESM1 single-forcing and all-forcing large ensembles, interpreted using layer-wise relevance propagation and an uncertainty mask
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Using explainable AI on single-forcing CESM1 large ensembles, the study identified the North Atlantic, Southern Ocean and Southeast Asia as key regional temperature patterns for dating the climate simulations, particularly before the early 21st century.
- Still unknown: This is a model-based attribution analysis from one climate model (CESM1) and historical/RCP8.5 simulations, with reanalysis used for evaluation; it is not a direct experiment or causal attribution of every observed regional trend. The relevance maps identify patterns useful to the trained network and do not by themselves prove a physical mechanism. The authors discuss other forcings, feedbacks and internal variability, and the net influence of aerosols remains uncertain.
- AI role: The ANN learned to predict year from global near-surface-temperature maps in simulations with different combinations of greenhouse-gas and industrial-aerosol forcing. Layer-wise relevance propagation identified regional patterns driving those predictions, and the trained networks were then tested on 20th Century Reanalysis observations. This analysis exposed the model’s aerosol-sensitive regional signal and the higher year-prediction correlation of the network trained with aerosols held at 1920 levels.
Evidence sources: https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021MS002464
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 77 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A sample of about 1 mm³ of human cortex was imaged at 4 nm across about 5,300 sections and automatically reconstructed: 1.4 petabytes, tens of thousands of neurons, 130 million annotated synapses, and 104 manually corrected cells. The sample is about one-millionth of a brain; reconstruction is imperfect and initial findings are preliminary.
Technology: Automated segmentation of electron microscopy images
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: retrospective or benchmark
- Tested: The automated reconstruction was checked by manual proofreading of about 104 cells; the abstract says connections were validated.
- Still unknown: Automated reconstruction is imperfect, the sample is about one-millionth of a brain, and findings are preliminary.
- AI role: Automated machine-learning pipeline reconstructed neurons and synapses from electron microscopy images.
Evidence sources: https://research.google/blog/a-browsable-petascale-reconstruction-of-the-human-cortex/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1101/2021.05.29.446289&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A machine-learning de novo design model was coupled with synthesis route prediction in the COVID Moonshot campaign against the SARS-CoV-2 main protease. The authors report novel chemical scaffolds that are active in biochemical and live-virus assays and were synthesized along model-generated routes. The abstract gives no potency figures, so the strength of the result should be checked in the full text.
Technology: Synthesis-directed de novo design model with synthesis route prediction
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Novel scaffolds designed with machine learning and synthesized along model-generated routes were tested in biochemical and live-virus assays.
- Still unknown: Not reported.
- AI role: Machine-learning de novo design model coupled with synthesis route prediction in the COVID Moonshot campaign.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1039/d1cc00050k&resultType=core&format=json
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 90 of works of the same type, year and subfield (OpenAlex work metrics, 36 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Med-BERT, a transformer pretrained on structured EHR data from 28,490,650 patients, improved AUC by 1.21% to 6.14% across two disease-prediction tasks compared with prior baselines. The gains are reported on retrospective structured-data tasks, and the abstract gives no clinical deployment or outcome results.
Technology: Med-BERT, BERT-style transformer pretrained on structured electronic health records
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Med-BERT, pretrained on structured EHR data from 28,490,650 patients, was fine-tuned on two disease-prediction tasks and compared with baselines trained without pretraining, including small-data settings.
- Still unknown: The abstract states no explicit limitations and no clinical deployment or outcome results.
- AI role: A BERT-style transformer adapted to structured EHR data produced embeddings fine-tuned for prediction.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41746-021-00455-y&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 1048 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An RNN generated peptide sequences and molecular-dynamics-based scoring prioritized Pep-MD for synthesis. In cell assays, the authors report less toxicity than TAT and stronger cell permeability under the tested conditions. The paper proposes a membrane-entry mechanism based partly on simulated structures; these cell results do not establish therapeutic efficacy.
Technology: Recurrent neural network sequence generator with molecular-dynamics-based selection score
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The selected synthesized peptide was tested in cell-viability, confocal-imaging and FACS permeability assays against TAT.
- Still unknown: Cell-based assays and a single comparator; no clinical or therapeutic efficacy evidence; mechanistic interpretation partly depends on modeled structures.
- AI role: An RNN generated candidate peptides; a simulation-derived score prioritized one sequence for synthesis and experimental cell testing.
Evidence sources: https://www.nature.com/articles/s41598-021-90245-z.pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary publisher full PDF, methods/results, publication information and author affiliations..
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A supervised random-forest search of Pan-STARRS1 and WISE photometry identified follow-up targets in the difficult redshift range around z≈5.5, where quasars resemble red and brown dwarfs. Spectroscopic observations of 37 candidates confirmed 20 previously unknown high-redshift quasars (18 at z=4.6–5.5 and two around z≈5.7), including a source outside common color-cut selections.
Technology: Supervised random-forest classification and regression applied to Pan-STARRS1 and WISE data
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A supervised random-forest search of Pan-STARRS1 and WISE photometry identified follow-up targets in the difficult redshift range around z≈5.5, where quasars resemble red and brown dwarfs.
- Still unknown: Only the 20 spectroscopically observed confirmations are counted. The much larger candidate catalog and predicted unobserved quasars are not treated as discoveries; the source reports a survey-restriction-dependent completeness and efficiency.
- AI role: Ranked high-redshift quasar candidates from multiband survey photometry; the resulting sample guided telescope follow-up, and spectroscopy established the 20 reported new quasars.
Evidence sources: https://arxiv.org/abs/2105.09171
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 83 of works of the same type, year and subfield (OpenAlex work metrics, 31 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An ensemble of neural networks trained on 107,823 fetal ultrasound images reached an AUC of 0.99, 95% sensitivity and 96% specificity in an internal test set of 4,108 fetal surveys with 0.9% CHD. Its sensitivity was comparable to that of clinicians and it stayed robust on outside-hospital and lower-quality images. Caveat: retrospective study with a low-prevalence internal test set.
Technology: Ensemble of convolutional neural networks with segmentation models
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Trained on 107,823 images from 1,326 retrospective studies; on 4,108 fetal surveys (0.9% CHD), AUC 0.99, 95% sensitivity, 96% specificity, 100% negative predictive value; comparable to clinicians and robust on outside-hospital images.
- Still unknown: Prospective screening performance is not reported in the abstract.
- AI role: An ensemble of neural networks identifies cardiac views and classifies normal versus complex congenital heart disease.
Evidence sources: https://doi.org/10.1038/s41591-021-01342-5
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 345 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A randomized study across 120 primary-care groups at 45 sites evaluated neural-network alerts on electrocardiograms from 22,641 adults. The intervention produced five additional diagnoses of low ejection fraction per thousand patients, without a global increase in echocardiography use. The result concerns identification of dysfunction, not improved clinical outcomes.
Technology: Convolutional neural network for electrocardiograms
Publication: Peer-reviewed paper · Test context: prospective or independent check. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: prospective or independent check
- Tested: A cluster-randomised trial across 120 primary-care teams (22,641 adults) compared AI-ECG alerts with usual care on new low-EF diagnoses within 90 days.
- Still unknown: Not reported in the abstract read; the trial measured diagnosis rather than clinical outcomes.
- AI role: Neural network analysed electrocardiograms and alerted clinicians to possible low ejection fraction.
Evidence sources: https://newsnetwork.mayoclinic.org/discussion/trial-demonstrates-early-ai-guided-detection-of-heart-disease-in-routine-practice/ · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1038/s41591-021-01335-4&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 467 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 4/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The deep cross-entropy method (reinforcement learning) finds constructions and counterexamples to open conjectures in extremal combinatorics and graph theory, including a Brualdi–Cao question about permanents. The counterexamples are verifiable; source checked was only the arXiv paper, with no institutional announcement.
Technology: Deep cross-entropy (reinforcement learning)
Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: direct test
- Tested: The deep cross-entropy method found explicit constructions and counterexamples, verifiable by checking, including a refutation of a Brualdi and Cao question.
- Still unknown: Not reported in the arXiv abstract read.
- AI role: Reinforcement learning (deep cross-entropy method) searched for constructions and counterexamples.
Evidence sources: https://arxiv.org/abs/2104.14516
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Neural models trained on particle-display affinity-screening data guided sequence mutation and candidate nomination, followed by synthesis and experimental affinity testing. The authors report a 23-nucleotide truncation of candidate G13 with measured dissociation constant 1.5 nM, compared with about 8 nM for the full-length parent under their assay. This is a binding result, not demonstrated diagnostic or therapeutic efficacy. The screening set is not 187,499 independently validated agents; sequence-level prior art remains open.
Technology: Neural-network models trained on particle-display affinity data
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The study reports particle-display screening and measured NGAL binding, including full Kd for truncated and parent G13.
- Still unknown: Binding assay only; no diagnostic/therapeutic outcome; one holdout set used for tuning and sequence novelty requires further review.
- AI role: Trained neural models extrapolated from experimentally measured sequences to nominate and iteratively refine higher-affinity DNA aptamers and truncations.
Evidence sources: https://www.nature.com/articles/s41467-021-22555-9
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary publisher indexed full text, article dates, methods/results, affiliations and disclosed limitations..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Independent analyses of character shapes distinguish two groups across the scroll’s 54 columns, consistent with two scribes alternating around the manuscript’s midpoint. This is statistical evidence from one artifact; the writers’ identities are unknown, and other explanations for the differences are not entirely ruled out.
Technology: Pattern recognition and Kohonen maps
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Independent analyses of character shapes across 54 columns separated two groups, treated as statistical evidence from one artifact.
- Still unknown: Not reported in the abstract read.
- AI role: Pattern recognition and AI techniques analysed handwriting features to identify writers.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1371/journal.pone.0249769&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 63 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A Bayesian optimization workflow using symmetry-constrained crystal relaxation and the MEGNet graph neural network screened 399,960 transition-metal boride and carbide compositions. The study identified MoWC₂ (P6₃/mmc) and ReWB (Pca2₁), then synthesized both by in-situ reactive spark-plasma sintering; the measured hardness was reported to agree with model and DFT predictions. The result is limited to these two synthesized compounds and the authors’ tested synthesis conditions.
Technology: BOWSR (Bayesian Optimization With Symmetry Relaxation) with the MEGNet graph neural network energy model
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A Bayesian optimization workflow using symmetry-constrained crystal relaxation and the MEGNet graph neural network screened 399,960 transition-metal boride and carbide compositions.
- Still unknown: The arXiv abstract states that the two materials were synthesized and describes them as ultra-incompressible hard materials; the institutional project page reports experiments on eight selected candidates and confirmation of two novel hard materials. The result is from a preprint/journal study and the provided abstract does not give numeric hardness values. Do not imply commercial performance or broader synthesis robustness.
- AI role: MEGNet supplied graph-based formation-energy predictions; BOWSR used Bayesian optimization under crystal-symmetry constraints to relax candidate structures without DFT geometry relaxation. This enabled screening of 399,960 boride/carbide compositions, narrowing candidates for experimental synthesis.
Evidence sources: https://arxiv.org/abs/2104.10242
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 153 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Researchers integrated DNA-motif, chromatin-accessibility, TF-binding and expression evidence with supervised learning to build an Arabidopsis gene-regulatory network of 1,491 transcription factors and 1.7 million TF–target interactions. The network predicted candidate reactive-oxygen-species (ROS) regulators; loss- and gain-of-function phenotyping supported 13 regulators not previously linked to ROS or stress responses. Newly tested examples included WRKY55, WRKY47, AT2G33710 and AT5G57150. The paper also reports that 75% of its ROS-predicted TFs had ROS or physiological stress functions supported by either this study or prior evidence.
Technology: Supervised-learning integrated gene-regulatory network (iGRN) built from motif, open-chromatin, transcription-factor-binding and expression-based networks
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Newly tested examples included WRKY55, WRKY47, AT2G33710 and AT5G57150.
- Still unknown: The iGRN integrated existing experimental data and the ROS findings were tested in Arabidopsis stress assays, not crop-yield or field-resilience trials. The 75% figure combines prior literature with new phenotypic tests; it is not a rate of independently replicated new discoveries. The new TF functions are limited to tested oxidative-stress conditions and mutant lines.
- AI role: The supervised integration model inferred TF–target regulatory links across multiple experimental input networks and predicted candidate TF functions, including ROS-response regulators. The investigators tested predicted TF candidates using Arabidopsis loss- or gain-of-function lines and ROS-specific phenotyping; these experiments supported 13 TFs without prior ROS/stress associations.
Evidence sources: https://www.nature.com/articles/s41477-021-00894-1.pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 91 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Across three iterative cycles of experimental testing, machine-learning analysis, prediction and redesign, the authors obtained Cu catalysts selective for CO, formic acid and C₂+ products in electrochemical CO₂ reduction. This summary follows the primary abstract and does not assign disputed sample identifiers or report cell-specific percentages.
Technology: Machine-learning-guided iterative additive screening and redesign
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The primary abstract reports three iterative cycles of experimental testing and model-guided redesign, producing Cu catalysts selective for CO, formic acid and C₂+ products. No disputed sample-level metrics are included.
- Still unknown: Full text and supporting information were not reviewed. The exact sample-to-performance mapping and the third-party rendering’s sample-number discrepancy remain unverified.
- AI role: Machine-learning analysis of experimental additive/catalyst data guided predictions and redesign over three iterative experimental cycles.
Evidence sources: https://pubs.acs.org/doi/abs/10.1021/jacs.1c00339
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 17 Nov 2026. Review scope: Primary ACS abstract, author-affiliation and article-history metadata; full text and supporting information not reviewed..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
The Tails EfficientDet model identified the extended object C/2020 T2 in one Zwicky Transient Facility Twilight Survey image on 2020 October 7. Follow-up orbital work confirmed it as a long-period comet. The study reports this as the first comet discovery assisted by deep learning; it also recovered a previously known comet, which is not counted as a new discovery here.
Technology: Tails, an EfficientDet-based deep-learning comet detector
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The Tails EfficientDet model identified the extended object C/2020 T2 in one Zwicky Transient Facility Twilight Survey image on 2020 October 7.
- Still unknown: The model surfaced the object, while human/standard follow-up established its orbit and comet classification. The entry counts only the newly discovered C/2020 T2, not recovery of P/2016 J3/P/2021 A3 or the detector’s performance metrics.
- AI role: Detected the comet’s extended coma/tail morphology in a single survey image and surfaced C/2020 T2 for discovery/follow-up; this enabled detection without requiring multi-epoch orbit linking at the initial search stage.
Evidence sources: https://arxiv.org/abs/2102.13352
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 77 of works of the same type, year and subfield (OpenAlex work metrics, 16 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A game-tree search using Gaussian-process predictions and first-principles calculations proposed dilute Ir and Pt additions as a counterintuitive way to raise Fe–Co magnetization. Combinatorial sputtering and magnetic measurements experimentally found Fe–Co–Ir and Fe–Co–Pt compositions with magnetization exceeding the conventional Fe₃Co₁ Slater–Pauling limit; the highest-moment points reported in the ternary maps were near Fe₈₁Co₁₅Ir₄ and Fe₈₅Co₁₁Pt₄. The study’s calculations attribute the effect to Ir/Pt-induced increases in local Fe and Co moments.
Technology: Autonomous materials search using a Gaussian-process regression model with game-tree search and an upper-confidence-bound acquisition rule, coupled to KKR-CPA first-principles calculations
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A game-tree search using Gaussian-process predictions and first-principles calculations proposed dilute Ir and Pt additions as a counterintuitive way to raise Fe–Co magnetization.
- Still unknown: The highest-moment composition suggested by the autonomous search (Fe₈₂Co₁₃Ir₄Pt₁) was not itself the maximum in the measured ternary composition spreads; the Fe–Co–Ir and Fe–Co–Pt maps identified different peak compositions. The finding is based on sputtered, annealed thin-film composition spreads and room-temperature MOKE/SQUID measurements, not bulk ingots or device testing. The eight-element search space was narrowed by preliminary calculations. KKR-CPA results assume ideal disordered bulk states at 0 K, unlike the film measurements.
- AI role: The autonomous system iteratively selected compositions in an eight-component disordered-alloy search using ab-initio magnetic-moment estimates and a game-tree Gaussian-process model balancing exploration and exploitation. After about 43 days it proposed Fe₈₂Co₁₃Ir₄Pt₁; that hypothesis directed combinatorial synthesis and testing of Fe–Co–Ir and Fe–Co–Pt spreads. The follow-up measurements found compositions surpassing the prior Fe₃Co₁ benchmark and motivated theoretical analysis of impurity-enhanced Fe/Co local moments.
Evidence sources: https://www.nature.com/articles/s43246-021-00135-0
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 90 of works of the same type, year and subfield (OpenAlex work metrics, 56 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
QSAR virtual screening of a natural-product database prioritized compounds for in-vitro testing against chloroquine-sensitive and multidrug-resistant P. falciparum. The paper reports two sesquiterpene lactones, LDT-597 and LDT-598, with potent and selective activity. ADME/PBPK predictions are not measured pharmacokinetics, and the assays do not establish clinical efficacy.
Technology: QSAR activity models; QSPR ADME and PBPK predictors
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Primary article reports experimental validation of two prioritized compounds against parasite strains and human hepatoma cells.
- Still unknown: Compound-level prior art and animal efficacy remain open; predicted PK is computational, not measured.
- AI role: QSAR screen prioritizes commercial natural products/derivatives for parasite and cytotoxicity assays.
Evidence sources: https://doi.org/10.3390/biom11030459
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 16 Nov 2026. Review scope: publisher primary full text. Material checked for the specific claims stated in the record..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An AI-assisted virtual-screening cascade using shape-based and machine-learning models prioritized potential Plasmodium kinase inhibitors. Eight virtual hits were experimentally evaluated; LabMol-167 inhibited P. berghei ookinete conversion and P. falciparum blood-stage parasites at nanomolar concentrations and showed low cytotoxicity in mammalian cells. A possible additional PK5 target was proposed from computational target fishing and docking, not demonstrated experimentally. This is a preclinical hit result and does not establish therapeutic efficacy. The article appeared online on 2021-03-16.
Technology: AI-assisted virtual screening combining shape-based and machine-learning models
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Eight virtual hits were evaluated; LabMol-167 showed nanomolar activity in P. berghei ookinete conversion and P. falciparum blood-stage assays, with low mammalian-cell cytotoxicity.
- Still unknown: The PK5 dual-target mechanism is proposed from computational target fishing and docking; in-vivo efficacy and clinical benefit are not established.
- AI role: Shape-based and machine-learning virtual screening prioritized candidates for experimental evaluation; the abstract explicitly links the integrated AI-assisted screen to this candidate-identification workflow.
Evidence sources: https://pubmed.ncbi.nlm.nih.gov/33247522/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 17 Nov 2026. Review scope: Primary PubMed abstract, publication metadata, and author-affiliation block; claim limited to the findings explicitly stated in the abstract..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A microkinetic and high-throughput screen of 1,998 bimetallic alloys, combined with machine-learning concepts, shortlisted noble-metal-free catalysts for selective ethane dehydrogenation. The predicted Ni3Mo alloy was synthesized and experimentally shown to outperform Pt in selective ethylene production. The machine-learning role is secondary to the descriptor-based workflow, and the evidence is a single catalyst test.
Technology: Descriptor-based microkinetic modeling with high-throughput DFT and machine learning
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The predicted Ni3Mo alloy was synthesized and experimentally shown to outperform Pt in selective ethylene production from ethane dehydrogenation.
- Still unknown: Not reported.
- AI role: A microkinetic and high-throughput screen of 1,998 bimetallic alloys, based on calculated adsorption energies, shortlisted noble-metal-free catalysts; the abstract describes machine learning concepts as secondary.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1073/pnas.2024666118&resultType=core&format=json
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 70 of works of the same type, year and subfield (OpenAlex work metrics, 25 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Over 48 days, 20 candidates were designed, synthesized, and tested; two showed activity against several pathogens, including multidrug-resistant Klebsiella pneumoniae. In vitro and mouse tests only, with no demonstration of safety or efficacy in humans.
Technology: Generative autoencoder and CLaSS
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: 20 generative-model candidates were synthesised and tested; two were active against several pathogens, with in vitro and mouse tests.
- Still unknown: No demonstration of safety or efficacy in humans, and no human trials are mentioned.
- AI role: Generative models designed candidate antimicrobial peptides.
Evidence sources: https://research.ibm.com/blog/ai-finds-new-peptides · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1038/s41551-021-00689-x&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 508 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Over 6,300 protein structures predicted with deep learning are available in Pfam to explore families without a known structure. These are computational models with estimated quality, not newly experimentally determined structures; this result is distinct from RoseTTAFold and the AlphaFold Database.
Technology: trRosetta
Family trRosetta: profile · models page
Publication: Announcement only · Test context: Test context unspecified in annotation. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Announcement only
- Test type: not reported
- Tested: Pfam models are scored with lDDT (0.6 or higher considered reasonable); the article describes no independent validation.
- Still unknown: The article does not state limitations and says more structures are to follow.
- AI role: Deep-learning trRosetta predicted structures for protein families.
Evidence sources: https://www.ipd.uw.edu/2021/03/trrosetta-reveals-structures-for-every-protein-family/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 4/5 · Validation 1/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
NCATS researchers used biological activity-based modeling (BABM) to infer antiviral activity from compounds’ profiles across multiple assays. Of 311 model-predicted SARS-CoV-2 candidates tested in a live-virus cell-culture assay, 99 were confirmed active (32% hit rate); follow-up assays implicated viral-entry inhibition and/or autophagy modulation among confirmed compounds.
Technology: Biological activity-based modeling (BABM) models trained on multi-assay compound-activity profiles
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: NCATS researchers used biological activity-based modeling (BABM) to infer antiviral activity from compounds’ profiles across multiple assays.
- Still unknown: Evidence is from cell-culture live-virus and mechanistic assays, not clinical treatment. 99/311 were active in the primary assay; further potency/secondary confirmations were available for subsets. Most confirmed compounds were reported to inhibit entry and/or modulate autophagy; these data do not establish safe or effective human therapy.
- AI role: BABM used prior activity signatures across assay panels to predict compounds with potential SARS-CoV-2 activity, including compounds outside conventional similar-structure hit finding. Researchers tested 311 model-predicted compounds in live-virus assays and conducted secondary/mechanistic assays on confirmed actives.
Evidence sources: https://www.nature.com/articles/s41587-021-00839-1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 54 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
A data-driven machine-learning search combined with high-throughput ab initio calculations screened 2,964 two-dimensional bimetal phosphates and identified 60 computationally stable structures with out-of-plane ferroelectric polarization: 16 predicted ferroelectric metals and 44 predicted ferroelectric semiconductors, including seven predicted multiferroics. The calculations analyze how bimetal displacement can support polarization alongside metallicity. These are theoretical candidates and proposed physical explanations, not experimentally synthesized or measured phases.
Technology: Data-driven machine-learning screening with orbital-based descriptors, combined with high-throughput ab initio calculations
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: A data-driven machine-learning search combined with high-throughput ab initio calculations screened 2,964 two-dimensional bimetal phosphates and identified 60 computationally stable structures with out-of-plane ferroelectric polarization: 16 predicted ferroelectric metals and 44 predicted ferroelectric semiconductors, including seven predicted multiferroics.
- Still unknown: The 60 phases and their stability and ferroelectric properties are computational predictions from high-throughput ab initio calculations. The paper does not report experimental synthesis or measurement of these predicted structures; practical stability and device behavior remain unverified.
- AI role: Machine learning with newly developed electronic-orbital descriptors enabled systematic screening of 2,964 candidate 2D bimetal phosphates; first-principles calculations evaluated stability, polarization, and electronic structure for the reported candidate family.
Evidence sources: https://arxiv.org/abs/2004.08527
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 90 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Mirai, trained on over 200,000 exams, was evaluated on hospital data from the United States, Sweden, and Taiwan. In a comparison of high-risk groups at Massachusetts General Hospital, it identified nearly twice as many future diagnoses as Tyrer-Cuzick; it does not demonstrate reduced mortality.
Technology: Deep learning on mammograms
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Mirai was validated on held-out test sets from MGH, Karolinska and Chang Gung, and identified nearly twice as many future diagnoses as Tyrer-Cuzick in high-risk groups.
- Still unknown: It does not use prior imaging and is still being validated in more diverse populations, and it does not show reduced mortality.
- AI role: Deep learning predicted future breast cancer risk from mammograms.
Evidence sources: https://news.mit.edu/2021/robust-artificial-intelligence-tools-predict-future-cancer-0128 · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1126/scitranslmed.aba4373&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 320 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
An image-classification-guided pooled CRISPRi screen mapped factors that affect TFEB movement from nucleus to cytosol during prolonged starvation. The screen identified multiple candidate genes, and follow-up assays independently validated 21 of 64 neural-network-called hits; experiments on CREB5 further linked it to TFEB retention and starvation-associated autophagy/lysosomal protein expression.
Technology: AI-photoswitchable screening (AI-PS), using SVM classifiers and a convolutional neural network
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The screen identified multiple candidate genes, and follow-up assays independently validated 21 of 64 neural-network-called hits; experiments on CREB5 further linked it to TFEB retention and starvation-associated autophagy/lysosomal protein expression.
- Still unknown: Only 21 of 64 neural-network-called TFEB hits were independently validated in secondary assays (about 32%); candidate effectors should not be treated as all confirmed. Results use cultured U2OS cells and prolonged starvation, and do not establish a physiological role in an organism. CREB5 received targeted follow-up but the overall screen has a modest validation rate.
- AI role: SVM and CNN models classified single-cell images by subcellular protein localization; the system photoactivated cells with the target phenotype for FACS isolation and gRNA sequencing in pooled CRISPRi screening. AI enabled the genome-scale genotype-to-subcellular-phenotype screen.
Evidence sources: https://rupress.org/jcb/article/220/2/e202006180/211694/Image-based-pooled-whole-genome-CRISPRi-screening
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 86 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Models trained in part on 26,838 X-rays from 4,914 patients predict deterioration up to 96 hours ahead, outperforming specialists in some retrospective comparisons. This research is for hospital resource planning, not a clinical product or evidence of better patient outcomes.
Technology: MoCo and Transformer
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: retrospective or benchmark
- Tested: Models trained on chest X-rays are compared with specialists in some retrospective comparisons for predicting deterioration.
- Still unknown: Not reported in the arXiv abstract read; the research is for resource planning, not a clinical product.
- AI role: Self-supervised learning (MoCo) predicted COVID-19 deterioration from sequential chest X-rays.
Evidence sources: https://arxiv.org/abs/2101.04909
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Analysis of influenza, HIV, and coronavirus sequences identifies regions of surface proteins less likely to mutate to escape immune responses, including the S2 subunit of spike. These are computational leads for studying possible vaccine targets, not validated vaccines.
Technology: Protein-sequence language model
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Language models trained on about 60,000 HIV, 45,000 influenza and 4,000 coronavirus sequences were checked against earlier findings on influenza and HIV; the SARS-CoV-2 analysis is described as not yet peer-reviewed.
- Still unknown: Flagged SARS-CoV-2 sequences still need investigation, and it is unknown how fast SARS-CoV-2 mutates, so how long current vaccines stay effective is unclear.
- AI role: Adapted language-model methods to viral protein sequences to predict surface regions more or less likely to enable immune escape, as candidate vaccine targets.
Evidence sources: https://news.mit.edu/2021/model-viruses-escape-immune-0114 · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1126/science.abd7331&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 383 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Applied to DR8 data from the DESI Legacy Imaging Surveys, machine learning found 1,210 strong gravitational-lens candidates. The DESI collaboration says this is about twice the number of lenses known at the time; these are candidates, not objects individually confirmed in every case.
Technology: Residual neural network
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: Candidates were selected by applying trained networks to survey images and visually inspecting the top-ranked ones; the sources read describe no spectroscopic confirmation or held-out test.
- Still unknown: Not reported
- AI role: Deep residual neural networks trained on known lenses and non-lenses found 1,210 strong-lens candidates in DESI Legacy Imaging Survey DR8 data.
Evidence sources: https://www.desi.lbl.gov/2021/01/14/desi-legacy-imaging-surveys-doubles-the-number-of-known-gravitational-lenses/ · https://arxiv.org/abs/2005.04730
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: press release. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Eight stage/time-specific Bayesian classifiers trained on historical phenotypic measurements guided prospective selection of predicted active and inactive commercial compounds. In-vitro assays reported 48% and 34% hit fractions for somules and adults, followed by triage of five compounds. The selected-set fractions are not unbiased head-to-head screening rates; no animal cure, clinical mechanism, safety or efficacy is established.
Technology: Bayesian classifiers
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Primary article reports prospective somule/adult screens and prioritized compounds after triage.
- Still unknown: Compound-specific prior evidence and complete supplementary access remain open; no clinical inference.
- AI role: Stage/time-specific Bayesian models guided selection of assay compounds, with human curation and triage.
Evidence sources: https://doi.org/10.1021/acsinfecdis.0c00754
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 16 Nov 2026. Review scope: PMC-indexed primary text; PubMed primary metadata. Material checked for the specific claims stated in the record..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.
Interrogating models trained on genome and resistance data nominated enzyme-substrate relationships for experimental testing. The authors report 22 previously unknown activities validated in their assay system. This is one mechanism study; it does not establish the prevalence or clinical contribution of each relationship in patients. Model performance varied substantially across organism and drug datasets.
Technology: Antibiotic-specific logistic-regression classifiers
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: Predicted relationships received targeted experimental validation.
- Still unknown: Clinical prevalence, generalization and independent replication remain unestablished.
- AI role: Antibiotic-specific logistic-regression classifiers supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8115898/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary article date, affiliations, selected logistic-regression Methods and experimental Results; supplements not reviewed..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.