{"id":"W4414406366","doi":"10.1093/genetics/iyaf199","title":"gyōza: a Snakemake workflow for modular analysis of deep-mutational scanning data","year":2025,"lang":"en","type":"article","venue":"Genetics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; PROTEO","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Key Project for Synthetic Biology; Génome Québec; Genome Canada","keywords":"Workflow; Pipeline (software); Documentation; Modular design; Process (computing); Raw data; Quality (philosophy)","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":[],"consensus_categories":[],"category_scores_codex":[0.003303011,0.00007875085,0.000240295,0.0007924264,0.0001374886,0.00022937,0.001681954,0.00003052921,0.00008507373],"category_scores_gemma":[0.001996204,0.00006730177,0.0001093081,0.003508888,0.00006980565,0.00006974521,0.0009108563,0.00003296819,0.00001057116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001458707,"about_ca_system_score_gemma":0.00006510293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006388883,"about_ca_topic_score_gemma":0.0001356735,"domain_scores_codex":[0.9977357,0.0000558892,0.0005590717,0.0006799233,0.0007950694,0.0001743765],"domain_scores_gemma":[0.9964703,0.0008693658,0.0001740491,0.002099005,0.0003459661,0.00004131342],"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":[0.00001468355,0.0000623181,0.01249054,0.00001154489,0.0006174583,0.000001474059,0.0001739265,0.4707044,0.0001059396,0.003033656,0.05110772,0.4616763],"study_design_scores_gemma":[0.0001481,0.000008695977,0.03423391,0.000007641195,0.0003698315,1.280814e-7,0.0002774699,0.912101,0.0000622368,0.00813143,0.04459526,0.000064277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06650495,0.0003707434,0.9306218,0.0004578246,0.0004776751,0.0001520584,0.0003124008,0.00001475888,0.001087806],"genre_scores_gemma":[0.8473574,0.000004208531,0.1500169,0.0002034378,0.00004434785,0.000006721156,0.000491875,0.000004326806,0.001870813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7808525,"threshold_uncertainty_score":0.3125517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2032187313395684,"score_gpt":0.4477103680318447,"score_spread":0.2444916366922762,"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."}}