{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009586845,0.0005065717,0.0007041167,0.001534667,0.0004402671,0.001178123,0.001765124,0.001400862,0.005917265],"category_scores_gemma":[0.003205279,0.0002375639,0.001264909,0.001351321,0.0003440397,0.001691436,0.0005902754,0.0009206293,0.003341017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008217416,"about_ca_system_score_gemma":0.0009439277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004785086,"about_ca_topic_score_gemma":0.006443031,"domain_scores_codex":[0.999404,0.0001317669,0.00005982426,0.0001649537,0.0001817343,0.00005778878],"domain_scores_gemma":[0.998551,0.0007519117,0.0001316125,0.0002276603,0.0002816959,0.00005610868],"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":[0.001685931,0.0008903185,0.002496588,0.0009460288,0.0002815283,0.0009912822,0.000393535,0.3138316,0.06832513,0.06026973,0.02928153,0.5206068],"study_design_scores_gemma":[0.00001874005,0.0000639179,0.0002821401,0.000007411273,0.00003119156,0.0001490773,0.00001708679,0.9805968,0.005553737,0.009976845,0.003284769,0.00001820328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02245003,0.0006970683,0.9646364,0.0005895103,0.0001342587,0.0002413064,0.003105337,0.005058333,0.003087654],"genre_scores_gemma":[0.5832809,0.001032638,0.3874051,0.000553251,0.000264542,0.0007642327,0.006821327,0.0005121268,0.01936589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005917265,"threshold_uncertainty_score":0.01979518,"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."}}