{"id":"W4256590393","doi":"10.26434/chemrxiv-2021-rzq4n","title":"CACHE (Critical Assessment of Computational Hit-finding Experiments): A public-private partnership benchmarking initiative to enable the development of computational methods for hit-finding","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Advanced Biosensing Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Ontario Institute for Cancer Research; University of Toronto","funders":"Common Fund; Genentech; Innovative Medicines Initiative; European Commission; University of Cambridge; Ontario Genomics Institute; European Federation of Pharmaceutical Industries and Associations; Merck KGaA; National Institutes of Health; Ontario Genomics; Genome Canada; National Institute of General Medical Sciences; Diamond Light Source; McGill University; Bayer; Engineering and Physical Sciences Research Council; Bristol-Myers Squibb; AstraZeneca; Pfizer","keywords":"Benchmarking; Computer science; Data science; Cache; Computational model; Drug discovery; Drug development; Relevance (law); Management science; Risk analysis (engineering); Machine learning; Artificial intelligence; Bioinformatics; Engineering; Drug; Business; Political science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08894384,0.00320708,0.00254646,0.004582722,0.002198649,0.005592918,0.007834517,0.003203406,0.008612217],"category_scores_gemma":[0.1200003,0.0009749505,0.002203918,0.006449438,0.002920246,0.005486308,0.008971923,0.004732226,0.003584123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003554113,"about_ca_system_score_gemma":0.01551443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008313911,"about_ca_topic_score_gemma":0.006585643,"domain_scores_codex":[0.9383683,0.03716496,0.002385503,0.003080406,0.01605106,0.002949798],"domain_scores_gemma":[0.8750496,0.04677756,0.005005434,0.03605334,0.02792218,0.009191962],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00490927,0.004457458,0.02189424,0.003119186,0.001480308,0.0005367002,0.0009429782,0.2082718,0.01316886,0.07105526,0.3316837,0.3384802],"study_design_scores_gemma":[0.003020648,0.005837555,0.01472418,0.0007000866,0.0004448875,0.0005497032,0.0008781027,0.7316684,0.03114188,0.06747075,0.1431554,0.0004084142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1374473,0.00412347,0.6181084,0.00894927,0.003310083,0.008109506,0.04857548,0.1005366,0.07084002],"genre_scores_gemma":[0.308369,0.00113447,0.5860755,0.001754531,0.0003872878,0.00714502,0.0773845,0.01179445,0.005955183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9110562,"threshold_uncertainty_score":0.4703856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1525183701635116,"score_gpt":0.4685128017208962,"score_spread":0.3159944315573846,"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."}}