{"id":"W4321648823","doi":"10.48550/arxiv.2302.10952","title":"Machine learning for the prediction of safe and biologically active organophosphorus molecules","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada","keywords":"Chemical space; Limiting; Drug discovery; Artificial intelligence; Computer science; Fragment (logic); Space (punctuation); Biological activity; Molecule; Combinatorial chemistry; Machine learning; Chemistry; Biological system; Engineering; Biology; Algorithm; Organic chemistry; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204145,0.0008044795,0.0009382326,0.0009303117,0.0002796102,0.0005922017,0.0009689106,0.001106555,0.001467071],"category_scores_gemma":[0.003289049,0.0003057833,0.000508806,0.0007679097,0.0005380095,0.000666204,0.0005861548,0.001185822,0.0003653139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009049536,"about_ca_system_score_gemma":0.0008321401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003787141,"about_ca_topic_score_gemma":0.003043788,"domain_scores_codex":[0.9996626,0.0001302106,0.00001584758,0.00008885925,0.00006824846,0.0000341614],"domain_scores_gemma":[0.9986626,0.0009957713,0.0001060736,0.00006410724,0.0001251194,0.00004634685],"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":[0.0001221846,0.0001050191,0.001711296,0.0001299206,0.00006866501,0.00004189925,0.00001560427,0.9108339,0.001204913,0.005006622,0.002701828,0.07805821],"study_design_scores_gemma":[0.000005553765,0.00001181947,0.0001011976,0.000003962962,0.00000316842,0.000003062404,0.00000148962,0.9966922,0.0001964692,0.00280833,0.0001713167,0.000001501688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2394822,0.01156869,0.7365048,0.002643015,0.0001994593,0.0001510706,0.00136175,0.002898284,0.005190643],"genre_scores_gemma":[0.8874684,0.001706067,0.1054664,0.0002831312,0.0001759825,0.0001922134,0.001683673,0.00008165517,0.002942617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003787141,"threshold_uncertainty_score":0.007530153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09785702069623912,"score_gpt":0.2230339122408197,"score_spread":0.1251768915445806,"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."}}