{"id":"W2097449851","doi":"10.1038/nbt1186","title":"Statistical practice in high-throughput screening data analysis","year":2006,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":726,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"","keywords":"Replicate; Computer science; False discovery rate; Identification (biology); Data mining; Preprocessor; Drug discovery; Throughput; Multiple comparisons problem; Machine learning; Artificial intelligence; Bioinformatics; Statistics; Biology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1226203,0.001394809,0.003248669,0.005371626,0.002100543,0.006155004,0.004325998,0.003290214,0.001869961],"category_scores_gemma":[0.4113575,0.001723412,0.00290894,0.008971157,0.009380043,0.005495106,0.004430216,0.0111047,0.000903572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002468644,"about_ca_system_score_gemma":0.008594919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003888767,"about_ca_topic_score_gemma":0.002845592,"domain_scores_codex":[0.8233674,0.1493118,0.006942499,0.006139391,0.01344724,0.0007918631],"domain_scores_gemma":[0.3386192,0.6190025,0.006079403,0.02718748,0.008080257,0.001031115],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004161643,0.0002929532,0.01493699,0.002218352,0.001917246,0.0004895065,0.001847632,0.1067867,0.001501784,0.4660431,0.01440322,0.3891464],"study_design_scores_gemma":[0.00008565758,0.0001100728,0.001385193,0.0002190457,0.0001237977,0.000259186,0.0001789124,0.242811,0.001226637,0.7458431,0.007709866,0.00004751979],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001140332,0.001145107,0.9960108,0.0009204773,0.00008465043,0.00006043334,0.00006767193,0.0002686647,0.0003018056],"genre_scores_gemma":[0.1207705,0.002684498,0.8714028,0.001234689,0.0009205422,0.001430683,0.0006173721,0.0004064368,0.0005324896],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8773797,"threshold_uncertainty_score":0.648486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01478781202024359,"score_gpt":0.3463605281296443,"score_spread":0.3315727161094007,"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."}}