{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01368027,0.001227068,0.001779946,0.002871827,0.001387092,0.001592368,0.00311431,0.002040406,0.001018742],"category_scores_gemma":[0.06203208,0.0008237428,0.00183216,0.004635116,0.002219509,0.002903223,0.003927385,0.003024753,0.000763201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001301582,"about_ca_system_score_gemma":0.00167552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001902212,"about_ca_topic_score_gemma":0.002838563,"domain_scores_codex":[0.9859484,0.004532113,0.001501233,0.003766836,0.003835179,0.000416247],"domain_scores_gemma":[0.9394234,0.03374427,0.005288516,0.01575376,0.005212532,0.0005774558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001562717,0.000246964,0.07450484,0.002143819,0.001571375,0.001440355,0.001279028,0.3392999,0.09982751,0.02515443,0.01333501,0.439634],"study_design_scores_gemma":[0.0001174474,0.0002117086,0.0178885,0.0001369606,0.0002684743,0.00153563,0.0002671789,0.6983899,0.1824727,0.08807451,0.01048195,0.0001550489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04604357,0.0006094792,0.9477782,0.0003351693,0.0001357581,0.00008386315,0.000906646,0.003784359,0.0003229621],"genre_scores_gemma":[0.2748452,0.0003809651,0.7164823,0.0004884609,0.0001021265,0.0002166545,0.005474114,0.0008866332,0.001123689],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01368027,"threshold_uncertainty_score":0.07234901,"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."}}