{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006091936,0.0008360255,0.001167453,0.0007210975,0.0007379723,0.001068184,0.0009465317,0.0008001598,0.0008044783],"category_scores_gemma":[0.01548368,0.0005221061,0.0008148348,0.001338413,0.0005726227,0.0007184712,0.0006078997,0.001014819,0.0006484125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004653543,"about_ca_system_score_gemma":0.0005096948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001949887,"about_ca_topic_score_gemma":0.00388724,"domain_scores_codex":[0.9933962,0.002707888,0.001009871,0.001162751,0.001373991,0.0003492723],"domain_scores_gemma":[0.9903961,0.004677287,0.0007803034,0.001937828,0.001950248,0.0002581458],"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":[0.001515815,0.0003745014,0.01872666,0.0008991854,0.0002285714,0.0003857605,0.0005196887,0.02573935,0.9231795,0.0009088629,0.0008084496,0.02671356],"study_design_scores_gemma":[0.00008181872,0.001507341,0.03175697,0.0001523965,0.0002181683,0.0003904891,0.0002514246,0.04056796,0.9184822,0.0007094592,0.005733827,0.0001480231],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9354729,0.001655514,0.05885493,0.0001711993,0.00005950566,0.0002534197,0.00143685,0.00080829,0.001287377],"genre_scores_gemma":[0.8087956,0.001149704,0.1822061,0.0002331741,0.00001238332,0.0005164646,0.005864603,0.0006088447,0.0006131707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006091936,"threshold_uncertainty_score":0.03221762,"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."}}