{"id":"W2566346075","doi":"10.1101/gr.211748.116","title":"Using reference-free compressed data structures to analyze sequencing reads from thousands of human genomes","year":2016,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Wellcome Trust; Wellcome","keywords":"1000 Genomes Project; Biology; Population; Genome; Reference genome; Human genome; Indel; Computational biology; Genetics; Sequence assembly; k-mer; Single-nucleotide polymorphism; Genotype; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001560051,0.0007033903,0.0005724934,0.00220453,0.0005929905,0.001406392,0.00121012,0.0007548091,0.002056236],"category_scores_gemma":[0.0105779,0.0004304186,0.0005666175,0.005199086,0.0004982734,0.001813335,0.001166128,0.0009681483,0.001526333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006993885,"about_ca_system_score_gemma":0.0008559941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002148882,"about_ca_topic_score_gemma":0.00236196,"domain_scores_codex":[0.9987292,0.0002480958,0.0001502436,0.0002853461,0.000532116,0.00005507001],"domain_scores_gemma":[0.996194,0.001593948,0.0003743328,0.0009125688,0.0008400213,0.00008508522],"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":[0.002200153,0.0003805442,0.01476021,0.001246836,0.0004285945,0.001130951,0.00159395,0.0656323,0.234116,0.02331165,0.02524666,0.6299521],"study_design_scores_gemma":[0.0004639412,0.001118876,0.02358848,0.0003199709,0.0002749219,0.001765995,0.00103895,0.5331919,0.283821,0.07797005,0.07617245,0.0002734759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2708714,0.002390262,0.6765875,0.001190985,0.0003601915,0.0002900799,0.02325063,0.02097594,0.004082966],"genre_scores_gemma":[0.3086116,0.001155998,0.6347081,0.0003740724,0.0001576472,0.0005315199,0.0510372,0.001319196,0.002104721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00220453,"threshold_uncertainty_score":0.008250415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2766921240708995,"score_gpt":0.4189060771164468,"score_spread":0.1422139530455472,"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."}}