{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.1261314,0.003074503,0.002839738,0.009907905,0.006968648,0.03530502,0.01332721,0.02215394,0.04600726],"category_scores_gemma":[0.1717428,0.002833695,0.004226553,0.01372571,0.008051218,0.08580708,0.0371412,0.02944263,0.02458774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008561824,"about_ca_system_score_gemma":0.05913981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006784808,"about_ca_topic_score_gemma":0.005325849,"domain_scores_codex":[0.9453061,0.02628768,0.006099566,0.004063074,0.01296393,0.005279766],"domain_scores_gemma":[0.6257648,0.1418694,0.01211128,0.05817555,0.0867907,0.07528823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005416067,0.0008355809,0.003377433,0.001807693,0.0001400596,0.0003685882,0.0009568761,0.004317182,0.001719408,0.3501813,0.3658718,0.2698824],"study_design_scores_gemma":[0.0001610314,0.0001560775,0.0006900931,0.001478924,0.000039881,0.0001055301,0.001436905,0.004027774,0.0005573779,0.2770837,0.7141579,0.0001047564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.003298606,0.01307415,0.2030068,0.7231652,0.01057295,0.001493295,0.006929139,0.00676052,0.03169934],"genre_scores_gemma":[0.02744476,0.02234151,0.825549,0.06952982,0.006869851,0.004113069,0.0310216,0.002030147,0.0111003],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9866728,"threshold_uncertainty_score":0.6670543,"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."}}