{"id":"W4200085221","doi":"10.26434/chemrxiv-2021-q5n18","title":"Transferrable Selectivity Profiles Enable Prediction in Synergistic Catalyst Space","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; China Scholarship Council; Compute Canada","keywords":"Catalysis; Enantioselective synthesis; Selectivity; Combinatorial chemistry; Chemical space; Workflow; Space (punctuation); Chemistry; Computer science; Biochemical engineering; Computational chemistry; Organic chemistry; Drug discovery; Database; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001976735,0.0004585449,0.0007248316,0.0001901326,0.000186128,0.0005854976,0.0008337405,0.0004273257,0.002297083],"category_scores_gemma":[0.0007743844,0.0004657439,0.0001184288,0.0004883062,0.0002212844,0.0003296029,0.0005652017,0.0008567799,0.0001824461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003649435,"about_ca_system_score_gemma":0.0006328478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002425592,"about_ca_topic_score_gemma":0.0003414775,"domain_scores_codex":[0.9962029,0.000415717,0.0005891148,0.001472833,0.0005988594,0.0007205555],"domain_scores_gemma":[0.9983356,0.0001363975,0.0002446903,0.0009770278,0.0001612069,0.0001450641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002214771,0.0001378056,0.003816426,0.0008103333,0.000007042638,0.00004510183,0.0006519907,0.03297104,0.9610028,0.00009109969,0.0004136475,0.00003062187],"study_design_scores_gemma":[0.0002480003,0.00003309509,0.005287659,0.0005076464,0.00003652001,0.00001525375,0.0001000358,0.0135669,0.9788932,0.0006381961,0.0001926523,0.0004808327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9870396,0.0002602914,0.004751099,0.0002688097,0.002239678,0.0005596644,0.0000306719,0.0003345161,0.004515633],"genre_scores_gemma":[0.99322,0.00003191855,0.004273559,0.00003126146,0.0003060564,0.0002837864,0.0001487098,0.00005325021,0.001651504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01940414,"threshold_uncertainty_score":0.9997794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499183793462019,"score_gpt":0.2486259842190547,"score_spread":0.2336341462844345,"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."}}