{"id":"W3127641366","doi":"10.26434/chemrxiv.13638347.v1","title":"Deep Generative Models Enable Navigation in Sparsely Populated Chemical Space","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Chemical space; Computer science; Generative model; Generative grammar; Artificial intelligence; Benchmark (surveying); Field (mathematics); Machine learning; Space (punctuation); Quality (philosophy); Drug discovery; Mathematics; Geography; Bioinformatics; Biology","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":[0.001018614,0.0009502414,0.0009844904,0.0006310059,0.0005051596,0.001588239,0.001681295,0.001796832,0.003945819],"category_scores_gemma":[0.00469825,0.0009565167,0.001257479,0.0006402889,0.001469863,0.002342374,0.002091092,0.002932889,0.001009633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001492189,"about_ca_system_score_gemma":0.001134803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004284349,"about_ca_topic_score_gemma":0.006962744,"domain_scores_codex":[0.9996206,0.0001330119,0.00001534512,0.00008625479,0.0001077506,0.00003701606],"domain_scores_gemma":[0.9982042,0.001211154,0.0001441989,0.0002402122,0.0001130976,0.0000871799],"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":[0.00003125496,0.00002517997,0.0006629252,0.0000644895,0.00003563779,0.00005279582,0.00003903425,0.9578643,0.002168618,0.02784857,0.001396714,0.009810427],"study_design_scores_gemma":[0.000005723738,0.000009346228,0.00004467498,0.000005600935,0.000003659658,0.00001252564,0.000004122669,0.9838396,0.0006309391,0.01484056,0.0005993837,0.000003880143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06404193,0.0007479673,0.9245974,0.0009147091,0.00007690721,0.0000657614,0.0007832096,0.002465733,0.006306315],"genre_scores_gemma":[0.7470065,0.0009980733,0.2417398,0.0006867888,0.0000993348,0.0002910644,0.00197951,0.000752074,0.00644695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004284349,"threshold_uncertainty_score":0.0132001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04317779125282582,"score_gpt":0.2755820241055644,"score_spread":0.2324042328527386,"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."}}