{"id":"W4389888290","doi":"10.1038/s42256-023-00759-6","title":"Multi-modal molecule structure–text model for text-based retrieval and editing","year":2023,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":false,"ca_institutions":"HEC Montréal; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Cheminformatics; Natural language processing; Artificial intelligence; Construct (python library); Generalization; Information retrieval; Chemistry; Programming language","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":[0.0006800881,0.0002622833,0.0002302559,0.0002742807,0.0002127508,0.00019998,0.0009165135,0.0002277594,0.000006364404],"category_scores_gemma":[0.001224072,0.0002437382,0.0001065472,0.0009761048,0.00007690673,0.0003106113,0.0003832532,0.0006717007,0.000009754865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005654581,"about_ca_system_score_gemma":0.0001618693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001106716,"about_ca_topic_score_gemma":0.00001924361,"domain_scores_codex":[0.9979469,0.00009925129,0.0003219039,0.0007388431,0.0004842622,0.0004088347],"domain_scores_gemma":[0.9980726,0.001031115,0.0001258232,0.0004192245,0.000221916,0.0001293206],"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":[0.0000726303,0.00003733532,0.0001114373,0.00007522939,0.00002055912,0.00001443568,0.0004648142,0.9176502,0.004644645,0.02667637,0.000381493,0.04985088],"study_design_scores_gemma":[0.0001914642,0.00004372092,0.0007432131,0.00002501679,0.000007105804,0.000009722297,0.00001067249,0.9468955,0.02163021,0.03008656,0.0001154199,0.0002413386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02137008,0.0004008055,0.9752593,0.001501413,0.0006580924,0.0003571141,0.000118988,0.0002907862,0.00004342544],"genre_scores_gemma":[0.6477014,0.000004316057,0.3514291,0.0006060246,0.0001128612,0.000008620063,0.00003525467,0.00001946925,0.00008290495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6263314,"threshold_uncertainty_score":0.9939353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02499866414802565,"score_gpt":0.3472592376691354,"score_spread":0.3222605735211098,"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."}}