{"id":"W4380483329","doi":"10.1101/2023.06.12.544612","title":"Performance analysis of conventional and AI-based variant callers using short and long reads","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Canadian Field Crop Research Alliance; Government of Canada; Grain Farmers of Ontario; Génome Québec; Genome Canada","keywords":"Computer science; Nanopore sequencing; 1000 Genomes Project; Set (abstract data type); Genomics; Indel; Data mining; Artificial intelligence; DNA sequencing; Machine learning; Genome; Computational biology; Biology; Genetics","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":[],"consensus_categories":[],"category_scores_codex":[0.01127401,0.00109098,0.0009714082,0.003073929,0.000814783,0.002171295,0.002292177,0.001469147,0.001398929],"category_scores_gemma":[0.03334749,0.0003614873,0.001188416,0.002700571,0.0005600575,0.001810961,0.001262703,0.00139405,0.001358263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001081139,"about_ca_system_score_gemma":0.001153587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006923817,"about_ca_topic_score_gemma":0.005900775,"domain_scores_codex":[0.9908097,0.002533154,0.0008993337,0.002007988,0.003356673,0.0003932298],"domain_scores_gemma":[0.9655726,0.02503841,0.00143575,0.002017424,0.005232133,0.000703709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007166456,0.0007429373,0.1369607,0.0019522,0.003043833,0.0006776545,0.001199618,0.1915676,0.1332062,0.005096368,0.008204525,0.510182],"study_design_scores_gemma":[0.0001099525,0.0006190069,0.02265985,0.00007218227,0.0002729891,0.0005214251,0.0002592409,0.893984,0.07630927,0.001578579,0.003377374,0.0002360411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6889572,0.004610211,0.2764281,0.000413805,0.0004376725,0.0002949273,0.00354309,0.02178282,0.003532139],"genre_scores_gemma":[0.6532845,0.0005803285,0.3339354,0.0002305934,0.00007370355,0.0002420198,0.008752368,0.001073482,0.001827639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01127401,"threshold_uncertainty_score":0.05962336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02165924527205876,"score_gpt":0.2398859223061934,"score_spread":0.2182266770341346,"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."}}