{"id":"W2996505894","doi":"10.1371/journal.pcbi.1007541","title":"Overlap matrix completion for predicting drug-associated indications","year":2019,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; Hunan Provincial Science and Technology Department; National Natural Science Foundation of China","keywords":"Drug repositioning; Matrix completion; Adjacency matrix; Drug; Computer science; Similarity (geometry); Artificial intelligence; Data mining; Disease; Rank (graph theory); Machine learning; Computational biology; Medicine; Mathematics; Theoretical computer science; Biology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001739416,0.001261927,0.001136556,0.001901479,0.0004731074,0.0007141553,0.0009622771,0.001279164,0.002183369],"category_scores_gemma":[0.006760706,0.0004919237,0.001009365,0.001163982,0.0007434609,0.001291512,0.001063288,0.001857809,0.0006647314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009154297,"about_ca_system_score_gemma":0.001754128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01159445,"about_ca_topic_score_gemma":0.009575204,"domain_scores_codex":[0.9991178,0.0003100926,0.00005126133,0.000185511,0.000229356,0.0001060001],"domain_scores_gemma":[0.9961885,0.002300951,0.0004116001,0.0002140789,0.0006627358,0.0002222009],"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":[0.0005406167,0.0002072786,0.01015975,0.0003121659,0.0001729689,0.0003460328,0.0001286206,0.8190414,0.00462092,0.00779222,0.0079081,0.1487699],"study_design_scores_gemma":[0.000008782946,0.00001973562,0.0003362903,0.000006791875,0.00001072865,0.00003012524,0.00001023926,0.9957572,0.0005244819,0.002890134,0.0003993952,0.000005973897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1052228,0.001836746,0.8873981,0.0007390615,0.00007792652,0.0001614781,0.001152383,0.001271409,0.002140102],"genre_scores_gemma":[0.7798716,0.001069502,0.2111813,0.0002899219,0.0001685753,0.0002662425,0.003852487,0.0001661492,0.003134329],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01159445,"threshold_uncertainty_score":0.02305394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0250629180630618,"score_gpt":0.3199556017374918,"score_spread":0.29489268367443,"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."}}