The preprint abstract reports a variational autoencoder trained on natural AAV sequences to generate capsids. More than 255 designs were synthesized and tested in vitro. Seven transduced human cells at over 50% efficiency; four of those avoided neutralization by every AAV-reactive human serum sample tested, at the reported NT50 threshold below 1:50. This establishes in-vitro capsid properties, not in-vivo delivery or clinical efficacy. Review is limited to the abstract and original-server metadata.
Technology: Variational autoencoder (generative model of AAV capsid sequences)
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: More than 255 AI-generated capsid designs were synthesized and tested in vitro; seven transduced human cells above 50% efficiency and four avoided neutralizing antibodies in all reactive human sera.
- Still unknown: Review limited to the indexed abstract and publication metadata; full-paper methods and additional limitations were not assessed.
- AI role: A variational autoencoder learned AAV sequence constraints from natural sequences and generated functional capsid proteins de novo, with a second design campaign exploring uncertain regions.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A%2210.64898%2F2026.11.06.764881%22&resultType=core&format=json · https://api.biorxiv.org/details/biorxiv/10.64898/2026.11.06.764881
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.
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.
A process combining quantum and classical computing with Chemistry42 selected 15 candidates; two showed activity against mutated KRAS variants in living cells. Published in Nature Biotechnology, this is a proof of principle, with no significant quantum advantage or demonstrated superiority over compounds obtained by classical methods.
Technology: Chemistry42 and hybrid quantum-classical 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: Fifteen candidates from the hybrid process were tested in the lab, and two strongly targeted mutated KRAS variants in living cells.
- Still unknown: The source states it is a proof-of-principle study with no significant quantum advantage and no demonstrated superiority over classically designed molecules.
- AI role: Generative AI (Chemistry42) and a quantum-classical process designed molecules, narrowed to 15 candidates.
Evidence sources: https://www.utoronto.ca/news/ai-quantum-computing-used-target-undruggable-cancer-protein
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, 125 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 closed-loop error-correction learning workflow guided synthesis of PbSe alloyed with SnSb and documented a previously unexplored low-temperature thermoelectric family. At 300 K, the best tested composition, 2 wt% SnSb-doped PbSe, had a measured power factor above 850 µW mK⁻² and more than twice that of PbSe. Density-functional calculations attribute the modeled transport improvement to Sn/Sb interactions that reduce hole effective mass.
Technology: Closed-loop error-correction learning with a neural-network update to a prior materials-property model; composition representations compared included Magpie, Roost and CrabNet
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 closed-loop error-correction learning workflow guided synthesis of PbSe alloyed with SnSb and documented a previously unexplored low-temperature thermoelectric family.
- Still unknown: The result is specific to the tested powder-processing, composition and measurement protocol, including synthesis below 300 °C; it is not evidence of device-level or commercial performance. The reported mechanism for the increased power factor is supported by DFT calculations, not a direct measurement of carrier effective mass. The paper compares the 2 wt% composition with PbSe and reports more than 2× power factor at room temperature.
- AI role: A model trained on published experimental thermoelectric data ranked candidate compositions, and a dense neural-network error-correction model incorporated local experimental comparisons to adapt predictions to the authors’ synthesis and measurement conditions. Iterative model-guided experiments selected the PbSe:SnSb family and 2 wt% SnSb-doped PbSe for characterization. AI supplied composition down-selection and adaptive experiment guidance; the authors synthesized and measured the samples.
Evidence sources: https://advanced.onlinelibrary.wiley.com/doi/10.1002/adma.202302575
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 70 of works of the same type, year and subfield (OpenAlex work metrics, 15 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.
Pharma.AI combined PandaOmics, Chemistry42 and an AlphaFold-predicted structure to identify a hepatocellular-carcinoma target and produce a hit molecule within 30 days of target selection, synthesizing seven compounds. A second round produced a more potent hit; an early Chemical Science study, with no clinical efficacy demonstrated.
Technology: Pharma.AI, PandaOmics, Chemistry42 and AlphaFold
Family AlphaFold: profile · models page
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 compounds were synthesized and tested in biological assays: the first hit bound CDK20 (Kd about 9.2 µM) and a second AI-driven round gave a more potent compound with greater antiproliferative activity in liver cancer cells; the abstract describes no in vivo testing.
- Still unknown: The abstract notes AlphaFold predictions have varying confidence, the first hit came from only 7 synthesized compounds, and potency values vary widely; no clinical efficacy is demonstrated.
- AI role: Pharma.AI platforms (PandaOmics, Chemistry42) used AlphaFold-predicted structures to select a liver-cancer target and generate candidate molecules.
Evidence sources: https://www.utoronto.ca/news/researchers-use-ai-powered-database-design-potential-cancer-drug-30-days · https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1039/D2SC05709C&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, 403 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 BIONIC graph-convolutional network integrated yeast interaction datasets and predicted essential-gene chemical sensitivities to the uncharacterized compound NP329. Experimental screens supported four BIONIC-predicted sensitive genes in the cell-wall biogenesis process; follow-up tests showed related steroidal alkaloid jervine reduced β-1,6-glucan and KRE6/SKN1 mutations conferred resistance, supporting a pathway-level connection for this compound family.
Technology: BIONIC (Biological Network Integration using Convolutions), a graph-convolutional deep-learning network-integration method
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: Experimental screens supported four BIONIC-predicted sensitive genes in the cell-wall biogenesis process; follow-up tests showed related steroidal alkaloid jervine reduced β-1,6-glucan and KRE6/SKN1 mutations conferred resistance, supporting a pathway-level connection for this compound family.
- Still unknown: BIONIC predicted chemical–genetic sensitivity, not direct molecular binding. NP329 is pseudojervine; jervine is a related compound tested in follow-up. The authors report jervine reduced β-1,6-glucan and KRE6/SKN1 mutations conferred resistance, implicating but not biochemically proving target engagement. Yeast-specific findings.
- AI role: BIONIC combined yeast protein-interaction, coexpression and genetic-interaction network features to predict essential-gene chemical sensitivities. For NP329 it predicted four of six experimentally sensitive essential genes in the glycosylation/cell-wall biogenesis process, helping identify this cellular process for follow-up. The later jervine experiments are supportive chemical-family follow-up, not direct proof that BIONIC predicted the jervine interaction.
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11236286/
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, 61 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 fitted energy model and quantum-inspired optimizer selected a mixed-oxide catalyst family for laboratory testing. The study reports a Ru-Cr-Mn-Sb oxide catalyst with higher ruthenium-normalized activity than its RuO2 comparator and sustained operation in the tested setup. This is one bounded materials result, not commercial electrolyzer validation or evidence that the optimizer itself is a learned model. The catalyst result already appears in the May 2022 preprint.
Technology: DFT-trained cluster expansion with quantum-inspired search
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: Selected oxide catalysts received electrochemical activity and stability measurements.
- Still unknown: Scale-up, independent replication and general design success rates were not established.
- AI role: DFT-trained cluster expansion with quantum-inspired search supported the stated study; experimental and interpretive work remained with researchers.
Evidence sources: https://arxiv.org/abs/2205.09007v1 · https://light.northwestern.edu/wp-content/uploads/2023/01/1-s2.0-S2590238522006622-main.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 v1 preprint abstract/history; indexed publisher article and institutional publisher-PDF passages on model fitting and affiliations; 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.
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.
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.
DFT and active machine learning identified Cu–Al catalysts that reduce CO2 to ethylene with over 80% Faradaic efficiency at 400 mA/cm² (about 66% for pure copper) and 55% half-cell energy efficiency at 150 mA/cm². Synthesized and tested in the lab; the abstract does not state how many candidates were screened.
Technology: Active machine learning and DFT
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: Cu-Al catalysts synthesized and tested in the lab: over 80% Faradaic efficiency for ethylene at 400 mA/cm2 versus about 66% for copper, and 55% half-cell energy efficiency at 150 mA/cm2; in situ X-ray absorption examined the copper environment.
- Still unknown: The abstract does not state how many candidates were screened or list explicit limitations; full text not read.
- AI role: DFT calculations combined with active machine learning identified the Cu-Al catalysts.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41586-020-2242-8&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: 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, 1624 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 high-throughput robotic synthesis and characterization workflow used a convolutional neural network to recognize crystal growth and a machine-learning regressor to guide synthesis conditions. The team reported the first synthesis of (3-PLA)₂PbCl₄, a new perovskite-like single crystal with a direct band gap near 4 eV and strong blue emission. The reported growth conditions were restrictive and required a carefully tuned search.
Technology: Convolutional neural network image classifier and machine-learning synthesis-condition regressor
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 robotic synthesis and characterization workflow used a convolutional neural network to recognize crystal growth and a machine-learning regressor to guide synthesis conditions.
- Still unknown: The authors characterize this as a new perovskite-like material and report a laboratory single-crystal synthesis and blue emission. Synthesis conditions were restrictive; the paper does not establish device performance or scale-up.
- AI role: The CNN classified crystal-growth outcomes from images, and the model trained on high-throughput experimental results selected promising conditions for successive synthesis trials. That feedback-guided sequence enabled the first synthesis of (3-PLA)₂PbCl₄.
Evidence sources: https://light.utoronto.ca/wp-content/uploads/2020/09/matter_perovskite_crystallization.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, 152 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.