{"id":"W6977798216","doi":"10.6084/m9.figshare.c.7050800","title":"Learning self-supervised molecular representations for drug–drug interaction prediction","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Financial Reporting and Valuation Research","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Embedding; Feature (linguistics); Process (computing); Feature learning; Training set; Labeled data; Feature vector","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":[0.001184054,0.0008164038,0.0008785864,0.0007500101,0.0001748668,0.0006226316,0.001162417,0.0009351154,0.001727191],"category_scores_gemma":[0.003064674,0.0003180911,0.0008642322,0.0005767692,0.0006290282,0.001132972,0.000849414,0.00159278,0.0005501639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006802279,"about_ca_system_score_gemma":0.0007433242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001314702,"about_ca_topic_score_gemma":0.001833479,"domain_scores_codex":[0.9994277,0.0002339497,0.00002438254,0.0001442139,0.0001207034,0.00004897445],"domain_scores_gemma":[0.9983941,0.0008262051,0.0002741155,0.0002599777,0.0001821957,0.00006343587],"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":[0.0001744488,0.0002257159,0.001914597,0.0001123761,0.00008099187,0.00005394825,0.00002396121,0.8658291,0.004558032,0.006235298,0.003172025,0.1176196],"study_design_scores_gemma":[0.00000327759,0.00001703625,0.0000576284,0.000001953509,0.000002449979,0.000003976837,0.000001040249,0.9978153,0.000657742,0.001300552,0.0001372468,0.000001842374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1239211,0.001036799,0.8686459,0.0007016896,0.00007614977,0.0001087057,0.0009856088,0.002471345,0.002052619],"genre_scores_gemma":[0.8386948,0.000300974,0.1559845,0.0003555114,0.00008801657,0.0001638774,0.002355988,0.0001204686,0.001935927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001727191,"threshold_uncertainty_score":0.006262004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05235910406846667,"score_gpt":0.3340956302980332,"score_spread":0.2817365262295665,"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."}}