{"id":"W2517033688","doi":"10.1109/tcbb.2016.2598752","title":"Machine Learned Replacement of N-Labels for Basecalled Sequences in DNA Barcoding","year":2016,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Ontario Ministry of Research, Innovation and Science; Government of Canada; Ontario Genomics Institute; Genome Canada","keywords":"Barcode; Correctness; DNA barcoding; Word error rate; Computer science; Sequence (biology); Sequence database; Sanger sequencing; Biology; Automation; Artificial intelligence; Computational biology; DNA sequencing; Pattern recognition (psychology); DNA; Genetics; Algorithm; Gene; Evolutionary biology; Engineering","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":[0.0001984006,0.0001069328,0.0001455384,0.00007714702,0.0000835605,0.000004497856,0.00009067717,0.00009039186,0.000007683692],"category_scores_gemma":[0.00003660525,0.00007525009,0.00004995407,0.00004885192,0.0001284054,0.000002347583,0.00000828507,0.00003500018,0.000001226396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009703443,"about_ca_system_score_gemma":0.00004320982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004535944,"about_ca_topic_score_gemma":0.00002099813,"domain_scores_codex":[0.9993311,0.00002809101,0.0003153791,0.0001464931,0.00004621091,0.0001327501],"domain_scores_gemma":[0.9995086,0.0001850606,0.00009177781,0.0001157434,0.00006820519,0.00003062766],"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":[0.002443644,0.0005289793,0.01190889,0.0003288279,0.0007797751,9.463217e-7,0.0007956582,0.02334515,0.6812438,0.00396309,0.000297946,0.2743633],"study_design_scores_gemma":[0.03024614,0.01588137,0.0154274,0.0005414847,0.0002779344,0.0001077657,0.001421825,0.08428957,0.72716,0.09445826,0.02772242,0.002465799],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5462489,0.0002104519,0.4514856,0.001102654,0.0001977438,0.0002987137,0.0003691809,0.000003993906,0.00008275671],"genre_scores_gemma":[0.9699588,0.000448037,0.02923718,0.0002065336,0.0000193678,0.00002837372,0.00003679324,0.000004942131,0.00005998327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4237099,"threshold_uncertainty_score":0.306861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02494258416889964,"score_gpt":0.2860665525876618,"score_spread":0.2611239684187621,"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."}}