{"id":"W4281619372","doi":"10.1038/s41467-022-30839-x","title":"Language models can learn complex molecular distributions","year":2022,"lang":"en","type":"article","venue":"Nature Communications","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Generative grammar; Generative model; Artificial intelligence; Theoretical computer science; Graph; Molecular graph; Representation (politics); Language model; Machine learning; Natural language processing","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":[0.001483103,0.0008190508,0.0006740685,0.0007123061,0.000274254,0.001165227,0.001006987,0.00111936,0.002679219],"category_scores_gemma":[0.006480694,0.0005643435,0.001031724,0.0005713092,0.001020289,0.002958893,0.0009843295,0.002042668,0.0009880164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001155057,"about_ca_system_score_gemma":0.0007427856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003512303,"about_ca_topic_score_gemma":0.005078271,"domain_scores_codex":[0.9995041,0.0002053953,0.00002177884,0.0001281534,0.00008794418,0.00005267312],"domain_scores_gemma":[0.9961999,0.003127087,0.0002023998,0.000257663,0.0001411692,0.00007175686],"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":[0.00006438716,0.00005055011,0.001267013,0.00008029833,0.00004888936,0.00006601226,0.00007359011,0.9280635,0.001888912,0.03960259,0.001431891,0.02736228],"study_design_scores_gemma":[0.000006622871,0.00001165584,0.00008237617,0.000004835771,0.000005081027,0.00001333569,0.000005328305,0.9746916,0.0004001457,0.02430997,0.0004641262,0.000004923695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09753686,0.0007195464,0.8912825,0.001552768,0.00007884292,0.00007912055,0.0006834712,0.00198519,0.006081671],"genre_scores_gemma":[0.8622387,0.000924468,0.1278356,0.0009060798,0.0001069442,0.0002524435,0.001363519,0.0003577573,0.006014461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003512303,"threshold_uncertainty_score":0.008962929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04033398295059509,"score_gpt":0.3508870985748289,"score_spread":0.3105531156242338,"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."}}