{"id":"W4383532691","doi":"10.1101/2023.07.06.547938","title":"Reusability Report: Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"","keywords":"Reusability; Machine learning; Computer science; Artificial intelligence; Throughput","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":[0.008799169,0.001857861,0.001305422,0.001414957,0.0005275373,0.002155273,0.002338315,0.002524402,0.005263523],"category_scores_gemma":[0.04210613,0.0007998887,0.0020567,0.0009403788,0.0009608718,0.003160142,0.001962971,0.003122795,0.001977536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001316746,"about_ca_system_score_gemma":0.001597512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008809343,"about_ca_topic_score_gemma":0.005062654,"domain_scores_codex":[0.9960257,0.001124131,0.0002959827,0.001150758,0.001223694,0.0001797057],"domain_scores_gemma":[0.9661903,0.01763354,0.001053845,0.01204274,0.002592482,0.0004870624],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001115378,0.0007525081,0.02093781,0.0007738999,0.001597539,0.0009865159,0.000232739,0.646193,0.03657413,0.01099667,0.0391651,0.2406748],"study_design_scores_gemma":[0.000045729,0.0001053903,0.001553434,0.00001917557,0.00009269441,0.0001517848,0.00001586934,0.967272,0.0217623,0.005953665,0.002986454,0.00004150167],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1308391,0.001350584,0.8262815,0.0019521,0.0008873895,0.000337841,0.007624099,0.02601581,0.004711571],"genre_scores_gemma":[0.7093219,0.0005991558,0.2632023,0.0008339767,0.0003161131,0.0004523748,0.01790913,0.002673104,0.004691904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9912008,"threshold_uncertainty_score":0.04653502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02131894836986205,"score_gpt":0.2553608456229813,"score_spread":0.2340418972531193,"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."}}