{"id":"W4412409238","doi":"10.17975/sfj-2025-007","title":"A Needle in a Haystack: Leveraging Machine Learning for Drug-Mechanism of Action Identification across Existing Therapeutics, with Specific Applications for Drug Repurposing for Rare Diseases","year":2025,"lang":"en","type":"article","venue":"STEM Fellowship Journal","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Haystack; Drug repositioning; Identification (biology); Repurposing; Drug; Mechanism (biology); Computational biology; Drug discovery; Mechanism of action; Computer science; Medicine; Bioinformatics; Pharmacology; Biology; Artificial intelligence; Genetics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004471917,0.00164307,0.001674681,0.002547491,0.0006001287,0.001867438,0.001405329,0.001460871,0.001311865],"category_scores_gemma":[0.006983496,0.0006413268,0.002060736,0.001212122,0.0007545656,0.00269607,0.001290521,0.002383975,0.0007954536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008836489,"about_ca_system_score_gemma":0.001771402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006753028,"about_ca_topic_score_gemma":0.01041394,"domain_scores_codex":[0.9989172,0.0003861865,0.00006896384,0.0002913332,0.0002552878,0.00008104495],"domain_scores_gemma":[0.9966772,0.002152546,0.0003051982,0.0004789061,0.0002634538,0.0001227082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007002268,0.0007097582,0.02956456,0.0009274625,0.0009686675,0.0006284806,0.0002301567,0.6010475,0.006710759,0.01018755,0.01159446,0.3367306],"study_design_scores_gemma":[0.00003136894,0.0001927426,0.00100433,0.00005413789,0.00006342262,0.00009043188,0.00002887495,0.9804427,0.001420638,0.01450462,0.002139452,0.00002738094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1815216,0.01502215,0.772819,0.006481288,0.0003273505,0.0004026862,0.002954062,0.01442683,0.006045031],"genre_scores_gemma":[0.6989739,0.003843121,0.2891664,0.001597644,0.0002149099,0.0001971805,0.003554606,0.0003528294,0.00209945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006753028,"threshold_uncertainty_score":0.02364999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07635961584780655,"score_gpt":0.364239173251859,"score_spread":0.2878795574040525,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}