{"id":"W4407987025","doi":"10.1101/2025.02.19.639168","title":"gyōza: a Snakemake workflow for modular analysis of deep-mutational scanning data","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Workflow; Modular design; Computer science; Database; Programming language","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01061077,0.0004727304,0.001202983,0.002717962,0.0003249289,0.001051943,0.005492295,0.0002888879,0.0001293815],"category_scores_gemma":[0.007769187,0.0004525858,0.0004792726,0.006389063,0.0001902606,0.000345356,0.005308222,0.000354408,0.00002464356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001524704,"about_ca_system_score_gemma":0.0007128464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005858374,"about_ca_topic_score_gemma":0.00002765274,"domain_scores_codex":[0.992264,0.0002708094,0.001712689,0.003071089,0.002120292,0.000561151],"domain_scores_gemma":[0.986933,0.001578256,0.001283509,0.008044265,0.001945647,0.0002153239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003882383,0.001640517,0.06659745,0.001618268,0.01996624,0.0001279519,0.0002167552,0.7841141,0.01763725,0.02556027,0.07930862,0.002824362],"study_design_scores_gemma":[0.0004241684,0.00001858599,0.08887246,0.0002557763,0.002042274,2.907717e-9,0.00002518308,0.88611,0.001142365,0.0001151757,0.02037793,0.0006160437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1255715,0.001001822,0.8589728,0.0005288147,0.003313043,0.001167043,0.009146522,0.0002297478,0.00006872688],"genre_scores_gemma":[0.9028078,0.00001411332,0.09650405,0.0001802778,0.0002362368,0.0001050533,0.00003266565,0.00003218004,0.00008758199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7772364,"threshold_uncertainty_score":0.999985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0992217264746689,"score_gpt":0.3486132734507842,"score_spread":0.2493915469761153,"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."}}