{"id":"W1966966274","doi":"10.1371/journal.pone.0104579","title":"Choice of Reference Sequence and Assembler for Alignment of Listeria monocytogenes Short-Read Sequence Data Greatly Influences Rates of Error in SNP Analyses","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reference genome; Genome; Computational biology; Trimming; Sequence assembly; Sequence (biology); Whole genome sequencing; Quality Score; Software; Single-nucleotide polymorphism; Genetics; Biology; Replicate; Computer science; Data mining; Statistics; Mathematics; Gene; Genotype","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":[0.0001879767,0.000130349,0.000360314,0.00004298011,0.00002144583,0.00000609384,0.000326419,0.00007166327,0.000002309878],"category_scores_gemma":[0.0002027158,0.0001161094,0.00002597276,0.00007023649,0.0001704775,0.00000374293,0.0002541542,0.00002502118,8.036977e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004629908,"about_ca_system_score_gemma":0.00004312739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003962449,"about_ca_topic_score_gemma":0.0003501694,"domain_scores_codex":[0.9989889,0.00004770171,0.0003703074,0.0003353306,0.0001172562,0.0001405097],"domain_scores_gemma":[0.9990439,0.00007797931,0.0001855882,0.0004955268,0.0001640951,0.00003284795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005115087,0.0001119106,0.1467435,0.0002120564,0.0001758204,9.848334e-8,0.00003978988,0.00004726309,0.8521041,0.00002705219,0.000004200074,0.0004830817],"study_design_scores_gemma":[0.0002406747,0.000404955,0.06924453,0.0001178804,0.0001146072,4.314878e-7,0.00005449734,0.0005368431,0.928974,0.00008836584,0.0001026515,0.0001206027],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973465,0.001892473,0.00008176718,0.00002878518,0.00001073883,0.000212236,0.0003446658,9.858626e-7,0.00008181801],"genre_scores_gemma":[0.9923433,0.001372798,0.006084701,0.00002220378,0.00002377694,0.00002683625,0.00009491595,0.000008631213,0.00002284237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07749898,"threshold_uncertainty_score":0.4734803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5744717037731171,"score_gpt":0.4396144708943679,"score_spread":0.1348572328787491,"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."}}