{"id":"W7108681698","doi":"10.5376/cmb.2025.15.0015","title":"High-Performance Computing Pipelines for NGS Variant Calling","year":2025,"lang":"","type":"article","venue":"Computational Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Workflow; Orchestration; Benchmark (surveying); Process (computing); Task (project management); Mutation; Pipeline transport; SPARK (programming language); Middleware (distributed applications)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003817487,0.0004906163,0.0005586823,0.0001673173,0.0004645025,0.0000578223,0.0004691851,0.0004492101,0.000005561978],"category_scores_gemma":[0.0001961737,0.0005316774,0.0002623342,0.0002455778,0.0003218592,0.000001403414,0.0004831303,0.0001703033,0.000007551815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004799708,"about_ca_system_score_gemma":0.0004670566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000229512,"about_ca_topic_score_gemma":0.000004217183,"domain_scores_codex":[0.9972581,0.0001469578,0.000806963,0.001030293,0.0001047233,0.0006530135],"domain_scores_gemma":[0.9983705,0.0002011355,0.0002751638,0.0003765036,0.0006819231,0.00009482195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000428966,0.0002535649,0.00300157,0.0004073726,0.001619778,0.000009305753,0.00008063352,0.3816887,0.4284032,0.1376457,0.000825776,0.0456354],"study_design_scores_gemma":[0.01125341,0.003357416,0.01272952,0.0005332936,0.001016333,0.00011381,0.0001878113,0.4377851,0.141278,0.3242489,0.06416737,0.003329094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4271927,0.006235528,0.5636631,0.0008130698,0.001245593,0.0004863587,0.0001217274,0.000007030079,0.0002349696],"genre_scores_gemma":[0.9375694,0.0003064166,0.0588016,0.001922136,0.0004763336,0.00005291438,0.0006525893,0.00004147035,0.0001770964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5103768,"threshold_uncertainty_score":0.9997135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008896724754100378,"score_gpt":0.2745310821449927,"score_spread":0.2656343573908923,"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."}}