{"id":"W3209134778","doi":"10.1186/s12911-021-01648-x","title":"Learning from low-rank multimodal representations for predicting disease-drug associations","year":2021,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Drug repositioning; Computer science; Similarity (geometry); Machine learning; Disease; Novelty; Representation (politics); Drug; Artificial intelligence; Association (psychology); Rank (graph theory); Data mining; Medicine; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001153414,0.000121388,0.000206273,0.0001012679,0.000445143,0.000483064,0.0003536154,0.00006690461,0.00003551027],"category_scores_gemma":[0.009852386,0.0001155497,0.0001145903,0.0003242502,0.00003490457,0.0007145475,0.0005765794,0.0002212263,0.000008878103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004274794,"about_ca_system_score_gemma":0.0005623784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000826728,"about_ca_topic_score_gemma":0.00002780603,"domain_scores_codex":[0.997672,0.0001476061,0.0007150169,0.0002420378,0.0009999018,0.0002234536],"domain_scores_gemma":[0.9832904,0.01564927,0.0002540875,0.0002840317,0.0002634555,0.0002587711],"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":[0.00003505055,0.0001024161,0.02219419,0.0001090388,0.00005317905,0.00001905913,0.004038699,0.3610385,0.00000451509,0.01962986,0.0009314943,0.591844],"study_design_scores_gemma":[0.0006024974,0.000007065746,0.01612877,0.0002637851,0.00001405248,0.000004514795,0.0005534455,0.9422206,0.000007907882,0.03990157,0.0001731325,0.0001227121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1776016,0.0001097215,0.8213622,0.000116718,0.0003511478,0.0001336856,0.00002541943,0.00007920124,0.0002203016],"genre_scores_gemma":[0.2390853,0.00002102359,0.7602825,0.0003808005,0.0001200346,0.00002189564,0.00006341955,0.000007165838,0.00001788276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5917213,"threshold_uncertainty_score":0.9984881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03985766570611984,"score_gpt":0.3654654103053932,"score_spread":0.3256077445992733,"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."}}