AI Science Tracker

University of Edinburgh

3 discoveries from 2025 to 2026

Discoveries

Machine learning prioritizes compounds active against heterogeneous glioblastoma stem-cell models

Researchers trained cell-survival predictors on image-based screening data from six patient-derived glioblastoma stem-cell lines and screened more than 12,000 compounds. Experimental follow-up identified three compounds with activity across the GBM phenotype; HSP90 inhibitor XL-888 eliminated all six tested lines at nanomolar IC50 values, with analyses consistent with HSP90 inhibition and downstream client-protein disruption.

Technology: Machine-learning cell-survival predictors trained on high-throughput phenotypic 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: Experimental follow-up identified three compounds with activity across the GBM phenotype; HSP90 inhibitor XL-888 eliminated all six tested lines at nanomolar IC50 values, with analyses consistent with HSP90 inhibition and downstream client-protein disruption.
  • Still unknown: This is an in-vitro lead-discovery study across six patient-derived cell lines, not clinical efficacy. XL-888 is an existing HSP90 inhibitor and its proposed development as a GBM lead needs medicinal-chemistry optimization, including improved blood–brain-barrier penetration; no patient outcomes are reported.
  • AI role: ML models trained on in-house imaging/compound-response data predicted cell survival and prioritized compounds from a >12,000-compound screen; experimental assays across patient-derived GBM stem-cell models validated three leads and tested mechanisms. Researchers performed the wet-lab work and mechanism analyses.

Evidence sources: https://pubmed.ncbi.nlm.nih.gov/42158926/

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 3/5 · Validation 3/5 · Novelty 2/5. 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 forecasts aftershock rates in seconds, comparable to ETAS

Neural networks trained on earthquake catalogues from California, New Zealand, Italy, Japan and Greece forecast the number of aftershocks in the following 24 hours after magnitude 4+ earthquakes. Their quality is reported as comparable to the operational ETAS model, while producing results in seconds rather than hours or days. The abstract reports no numeric skill scores, so the comparison rests on the full paper.

Technology: Deep neural networks for spatiotemporal seismicity rate forecasting, benchmarked against ETAS

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: Deep-learning seismicity forecasts were compared with an epidemic-type aftershock sequence benchmark and a persistence null hypothesis on Southern California and Italy test datasets; they matched ETAS at much lower processing time.
  • Still unknown: The abstract says performance depends on training data that represent the properties of earthquake sequences.
  • AI role: Deep neural networks learned short-term spatiotemporal seismicity rates from high-resolution catalogues.

Evidence sources: https://link.springer.com/article/10.1186/s40623-025-02241-6

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 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.

Deep learning enables multi-site bone marrow adiposity genetics in UK Biobank

Deep learning measured bone marrow fat fraction at four skeletal sites in UK Biobank MRI data; after quality control, 48,608 participants contributed to genome-wide analyses. In the white-participant meta-GWAS, the study reported 67, 147, 134 and 174 independent significant variants for femoral head, total hip, femoral diaphysis and spine, mapping to 54, 90, 43 and 100 genes, respectively. Analyses also identified site- and sex-specific genetic associations and added signals in multi-ancestry analyses.

Technology: Previously validated deep-learning models for MRI segmentation and bone marrow fat-fraction measurement

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: Deep learning measured bone marrow fat fraction at four skeletal sites in UK Biobank MRI data; after quality control, 48,608 participants contributed to genome-wide analyses.
  • Still unknown: The GWAS, transcriptome-wide and colocalization results are statistical associations and candidate gene mappings, not proof of causal mechanisms. Ancestry subgroup sizes differ, and results do not establish clinical utility or disease prevention. The deep-learning measurement method was established in an earlier study; this record concerns the distinct population-scale phenotype and genetic findings. A 2025 author correction fixed a misspelling of AKNA as ANKA; it did not alter the reported analysis or findings.
  • AI role: The study applied deep-learning models to segment four skeletal regions and derive bone marrow fat-fraction phenotypes at UK Biobank scale. Those AI-derived measurements were the phenotypes used in the study's subsequent genetic association analyses; the paper's genetic findings are not themselves outputs of a generative model.

Evidence sources: https://www.nature.com/articles/s41467-024-55422-4

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, 30 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.

Open the interactive profile for the timeline, or browse all organizations and model families.