{"id":"W3093525523","doi":"10.1021/acs.jpclett.0c02836","title":"COSMO-RS-Based Descriptors for the Machine Learning-Enabled Screening of Nucleotide Analogue Drugs against SARS-CoV-2","year":2020,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry Letters","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; National Institute for Nanotechnology","funders":"Government of Canada","keywords":"Chemical similarity; Computational biology; Drug; Drug discovery; Nucleotide; Chemistry; Virtual screening; Coronavirus disease 2019 (COVID-19); Molecular descriptor; Machine learning; Artificial intelligence; Computer science; Pharmacology; Biology; Structural similarity; Quantitative structure–activity relationship; Medicine; Biochemistry; Stereochemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0009133912,0.0001948198,0.0003489731,0.00002675069,0.0001758653,0.0000777871,0.00155535,0.00002609864,0.000001714979],"category_scores_gemma":[0.0004203731,0.0001209223,0.0003860001,0.0003986776,0.0001799802,0.0002327161,0.0001734335,0.0005755109,0.000001254133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004685926,"about_ca_system_score_gemma":0.00009626494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001097303,"about_ca_topic_score_gemma":1.964334e-7,"domain_scores_codex":[0.9983138,0.0002573766,0.0004307682,0.0001806819,0.0005729248,0.0002444499],"domain_scores_gemma":[0.9966046,0.002255222,0.0006199663,0.0002663675,0.000172294,0.0000815075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001179792,0.00003751127,0.00002025293,0.00004338348,0.00008565163,0.000003783353,0.0006198701,0.3384692,0.6582718,0.00005183821,0.0008104504,0.001468216],"study_design_scores_gemma":[0.0005245989,0.0000527217,0.00006994911,0.0000366881,0.00005282788,0.000003987521,0.00005326315,0.5850202,0.4134212,0.0001653816,0.000503606,0.00009554181],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4973635,0.00004122005,0.4879863,0.01444747,0.00003427542,0.00008133586,0.000005970858,0.00001625975,0.00002359277],"genre_scores_gemma":[0.9830333,0.000002501941,0.01196209,0.004571994,0.0004024245,0.000002517431,0.000004040547,0.0000186068,0.000002527155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4856698,"threshold_uncertainty_score":0.4931067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03322361551741557,"score_gpt":0.2794819679310508,"score_spread":0.2462583524136353,"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."}}