AI Science Tracker

Active learning repurposes BMS-262084 as a potent TMPRSS2 inhibitor that blocks coronavirus entry

Freie Universität Berlin; Microsoft Research AI for Science, NIH NCATS, German Primate Center and collaborators · 29 Jul 2025 · medicine

Discovery

Active learning repurposes BMS-262084 as a potent TMPRSS2 inhibitor that blocks coronavirus entry

A molecular-dynamics and active-learning workflow prioritized the existing compound BMS-262084 as a nanomolar inhibitor of human TMPRSS2 (IC50 1.82 nM). Cell assays reported inhibition of SARS-CoV-2 variants and other coronavirus entry into Calu-3 lung cells.

Technology: Molecular-dynamics-informed active learning with a target-specific scoring function

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: Cell assays reported inhibition of SARS-CoV-2 variants and other coronavirus entry into Calu-3 lung cells.
  • Still unknown: BMS-262084 is a known small molecule repurposed here for TMPRSS2; the discovery claim is its target/antiviral activity under tested conditions. Evidence is biochemical and cell-based, not clinical efficacy or safety. Assay concentrations, viral variants and cell systems limit generalization.
  • AI role: The active-learning workflow used receptor ensembles and target-specific features to iteratively prioritize compounds for testing; researchers measured purified-enzyme inhibition and viral-entry effects in cell assays. This is AI-assisted repurposing of an existing compound, not de novo molecule design.

Evidence sources: https://www.nature.com/articles/s41467-025-62139-5.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, 10 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 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.

Open in the full catalog for filters, charts and related discoveries.