{"id":"W4407140906","doi":"10.1186/s13321-025-00962-0","title":"Improving drug repositioning with negative data labeling using large language models","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Drug repositioning; Drug; Data mining; Natural language processing; Data science; Medicine; Pharmacology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.001325864,0.0001113462,0.0002131302,0.0001770772,0.0001313784,0.0002868896,0.001017457,0.00002851802,0.00000137183],"category_scores_gemma":[0.0002783719,0.00009025695,0.00004226475,0.0004104422,0.00002107299,0.003264909,0.0006146576,0.0002642249,4.654704e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001113233,"about_ca_system_score_gemma":0.0004834307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034619,"about_ca_topic_score_gemma":0.000001736721,"domain_scores_codex":[0.9986566,0.00002600927,0.0006217649,0.0001056989,0.0004090748,0.000180907],"domain_scores_gemma":[0.998018,0.0003905023,0.0007333148,0.0004699116,0.0003333088,0.00005496788],"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":[0.00005815889,0.0001233996,0.00007680999,0.0004502568,0.0002822975,0.00009173303,0.02706813,0.9137406,0.001998638,0.01646819,0.001185493,0.03845625],"study_design_scores_gemma":[0.0004661363,0.00001316952,0.000007604454,0.0003647425,0.00003700094,0.0001195743,0.001457985,0.9843794,0.01043801,0.002583855,0.00003498066,0.00009750843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0707828,0.0001438429,0.9260804,0.0001290106,0.0001370872,0.00005878156,0.000006123865,0.00001917313,0.002642787],"genre_scores_gemma":[0.2575648,0.000002984204,0.7420886,0.0002306112,0.00004509957,3.624439e-7,0.00000385222,0.000004781439,0.00005902261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.186782,"threshold_uncertainty_score":0.3680572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02494095244085814,"score_gpt":0.320357368948671,"score_spread":0.2954164165078128,"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."}}