{"id":"W2900675193","doi":"10.1093/nar/gky1142","title":"Sources of erroneous sequences and artifact chimeric reads in next generation sequencing of genomic DNA from formalin-fixed paraffin-embedded samples","year":2018,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"National Institutes of Health; Canadian Institutes of Health Research; Genome British Columbia; Society for the Study of Amphibians and Reptiles","keywords":"Biology; Computational biology; DNA sequencing; Genome; DNA; Artifact (error); Sequence (biology); Genetics; Gene","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":[0.0005224801,0.0001139191,0.0001912772,0.0001174377,0.0001047245,0.00001895722,0.0002535476,0.0001937139,0.00004433174],"category_scores_gemma":[0.00008591863,0.0001049215,0.00004356966,0.0001665887,0.0006491062,0.000007771411,0.0001877079,0.0001319041,0.000004537425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002472157,"about_ca_system_score_gemma":0.0001254579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001010963,"about_ca_topic_score_gemma":0.0003968642,"domain_scores_codex":[0.9987156,0.0001806455,0.0003201606,0.0003540875,0.0001616959,0.0002677608],"domain_scores_gemma":[0.9992666,0.00003390015,0.0001096643,0.0003783297,0.0001555958,0.00005595805],"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":[0.00004988199,0.00002698609,0.003950229,0.00001105327,0.00002220323,0.000001148022,0.0002642942,0.00001160597,0.9910871,0.0002658306,0.0000752198,0.004234434],"study_design_scores_gemma":[0.000182872,0.0004641679,0.006346816,0.00001646759,0.000006508028,0.000008191982,0.0002753177,0.001406624,0.9899308,0.0006372158,0.0006174932,0.0001075009],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969305,0.0005755548,0.001842548,0.00009120732,0.00001411342,0.0002649844,0.00002933967,0.00000929758,0.0002424193],"genre_scores_gemma":[0.9892434,0.00043095,0.009965668,0.0000379272,0.000115014,0.00003915581,0.0001223998,0.00001584696,0.00002957021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00812312,"threshold_uncertainty_score":0.4278573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09751854611490769,"score_gpt":0.3476191653371176,"score_spread":0.2501006192222099,"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."}}