{"id":"W3101227640","doi":"10.1101/2020.11.13.380741","title":"precisionFDA Truth Challenge V2: Calling variants from short- and long-reads in difficult-to-map regions","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Genomics","funders":"Agencia Estatal de Investigación; National Institutes of Health; Ministerio de Ciencia e Innovación; National Institute of Standards and Technology; European Commission","keywords":"Benchmarking; Computer science; Nanopore sequencing; Benchmark (surveying); Identification (biology); Data science; Crowdsourcing; Data mining; Computational biology; Artificial intelligence; Genome; Machine learning; Biology; Genetics; Geography; World Wide Web; Cartography; Gene","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002106967,0.0005351039,0.0005588531,0.0001310901,0.00009020596,0.0001696506,0.0005181226,0.0006884265,0.00001171833],"category_scores_gemma":[0.0005670663,0.0006013368,0.0001122969,0.0002153749,0.0000715569,0.000006776012,0.001122129,0.0005227251,0.00001857716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000110021,"about_ca_system_score_gemma":0.000427472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001342898,"about_ca_topic_score_gemma":0.00008804099,"domain_scores_codex":[0.9971812,0.00008088883,0.0005240359,0.001513013,0.0002259828,0.0004748485],"domain_scores_gemma":[0.9979357,0.00009153792,0.0001574522,0.001115418,0.0002243327,0.0004756001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003206342,0.000418425,0.01517382,0.0002919519,0.0003771372,0.0002870983,0.00007236384,0.0008720772,0.9794984,0.0008710656,0.001776836,0.00004021467],"study_design_scores_gemma":[0.003413843,0.0008182817,0.6728697,0.002111341,0.000500883,1.287211e-7,0.00003033203,0.00214184,0.2588201,0.00009677385,0.05447906,0.00471765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838006,0.005961654,0.006480921,0.0008791593,0.001075118,0.0007561805,0.0009781512,0.00005964434,0.000008587906],"genre_scores_gemma":[0.9916824,0.003557303,0.002984141,0.0004365911,0.001030288,0.0001696928,0.00001072354,0.0001263099,0.000002558112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7206782,"threshold_uncertainty_score":0.9996438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01997059577809692,"score_gpt":0.2355286485904228,"score_spread":0.2155580528123258,"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."}}