{"id":"W2160265768","doi":"10.1093/bioinformatics/btr208","title":"Error correction of high-throughput sequencing datasets with non-uniform coverage","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Research Resources; National Institutes of Health","keywords":"Computer science; Error detection and correction; Throughput; Simple (philosophy); Hamming graph; Algorithm; Hamming distance; Hamming code; Data mining; Decoding methods; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008746421,0.0001251333,0.0001357592,0.00003641758,0.00004877072,0.00001265973,0.0001372476,0.00009790095,0.00002172999],"category_scores_gemma":[0.00003501918,0.0001071942,0.00003149331,0.00007139005,0.00006515519,0.00001374904,0.0000854094,0.00006137748,0.00001342253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003236432,"about_ca_system_score_gemma":0.0001635134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003243094,"about_ca_topic_score_gemma":0.000139042,"domain_scores_codex":[0.9993517,0.000004987769,0.0002674958,0.000107636,0.0001022931,0.0001659224],"domain_scores_gemma":[0.9992975,0.0000103061,0.00019433,0.000373403,0.00006526201,0.00005917862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00661101,0.001955601,0.02471381,0.003498377,0.002573905,0.0001283533,0.02780654,0.04146863,0.3091854,0.008419677,0.4039861,0.1696526],"study_design_scores_gemma":[0.00383674,0.004013209,0.00693085,0.0002008695,0.0002237422,0.0001681346,0.002512089,0.02736408,0.9080794,0.0002573931,0.04521823,0.001195294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8953339,0.00005753027,0.08635397,0.000009181289,0.0006763302,0.0003241654,0.00086522,0.00001598599,0.01636374],"genre_scores_gemma":[0.9759442,0.0001712245,0.02249528,0.0001982711,0.00007290966,0.000007662407,0.001021861,0.00001581157,0.0000728445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.598894,"threshold_uncertainty_score":0.4371252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01589431564421076,"score_gpt":0.2275069057263118,"score_spread":0.211612590082101,"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."}}