{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001831358,0.0001870476,0.0002878503,0.0003049339,0.0007714209,0.0005150803,0.0005050515,0.00004058207,5.623692e-7],"category_scores_gemma":[0.00007663752,0.0001820143,0.0001797535,0.0005801315,0.00004090021,0.0006386129,0.00007966396,0.0002279473,2.757831e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000250334,"about_ca_system_score_gemma":0.0002459908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009406555,"about_ca_topic_score_gemma":0.00002639544,"domain_scores_codex":[0.9980627,0.0002016601,0.000676473,0.0004466156,0.0002624966,0.0003500981],"domain_scores_gemma":[0.9970515,0.001475695,0.0006289123,0.0002790248,0.0005022671,0.00006257797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001231242,0.0005685321,0.004624755,0.001879303,0.0003335037,0.000004438965,0.01665025,0.2185294,0.02028646,0.1455205,0.0002077615,0.5901639],"study_design_scores_gemma":[0.002589502,0.00009118816,0.001257723,0.0006125277,0.00007577357,0.00003187948,0.006518682,0.8961206,0.01390767,0.07302187,0.005427879,0.0003446974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04364914,0.0009176337,0.952854,0.0005251625,0.0003193031,0.001607639,0.00004329333,0.00005454941,0.00002928121],"genre_scores_gemma":[0.8685424,0.00003121301,0.1300172,0.00005498961,0.0001582799,0.0004999481,0.00003954833,0.00002885682,0.0006275942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8248932,"threshold_uncertainty_score":0.7422329,"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."}}