{"id":"W4400370724","doi":"10.1038/s41467-024-49777-x","title":"A data science roadmap for open science organizations engaged in early-stage drug discovery","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network; Structural Genomics Consortium; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genentech; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; European Commission; Ontario Genomics Institute; European Federation of Pharmaceutical Industries and Associations; Bristol-Myers Squibb; European Molecular Biology Laboratory; Merck KGaA; National Institutes of Health; Ontario Genomics; Genome Canada; National Institute of General Medical Sciences; Diamond Light Source; McGill University; Bayer; Pfizer","keywords":"Drug discovery; Open science; Data science; Computer science; Open data; Bioinformatics; World Wide Web; Biology; Physics","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004119745,0.0001026995,0.00009788569,0.000255092,0.0009956689,0.0009135973,0.01043869,0.0001266967,0.000005216263],"category_scores_gemma":[0.006471375,0.00008879121,0.00002280257,0.001869378,0.001572048,0.0001497698,0.008158405,0.0007936524,0.00001159588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006061594,"about_ca_system_score_gemma":0.002253836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006926914,"about_ca_topic_score_gemma":0.001474596,"domain_scores_codex":[0.9984809,0.00009456751,0.0002508191,0.0004629227,0.000368275,0.0003425331],"domain_scores_gemma":[0.9960754,0.0002007825,0.00004022079,0.00314703,0.0004038826,0.0001326702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008994484,0.0009684077,0.009807747,0.0003337208,0.000112803,0.000003942308,0.005480628,0.00005594473,0.8276263,0.0764024,0.05859648,0.02052167],"study_design_scores_gemma":[0.0007467472,0.000156916,0.01697353,0.000148091,0.00002723699,0.000006618299,0.001992365,0.02627913,0.06478216,0.0005898132,0.8877863,0.0005111228],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8127659,0.04252049,0.03022016,0.05616092,0.003462754,0.009621259,0.009228914,0.0002476344,0.03577198],"genre_scores_gemma":[0.9816458,0.001432716,0.01410371,0.0002602505,0.00006237331,0.00004979422,0.001018965,0.00001420618,0.001412213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8291898,"threshold_uncertainty_score":0.9998634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04926932333380304,"score_gpt":0.3918667521035324,"score_spread":0.3425974287697293,"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."}}