{"id":"W2897603144","doi":"10.1109/tcbb.2018.2876855","title":"MEC: Misassembly Error Correction in Contigs based on Distribution of Paired-End Reads and Statistics of GC-contents","year":2018,"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":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Contig; Sequence assembly; Computer science; DNA sequencing; Genome; Computational biology; Data mining; Biology; Genetics; DNA","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001313733,0.0001198746,0.000174133,0.00007715179,0.00008548733,0.000005076106,0.0000603042,0.0001270109,0.000003683566],"category_scores_gemma":[0.00004188519,0.0001086869,0.00003280438,0.0000764627,0.0003089646,0.000002595651,0.000006242577,0.0000643454,8.738335e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001030549,"about_ca_system_score_gemma":0.00004139085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002465253,"about_ca_topic_score_gemma":0.00005708183,"domain_scores_codex":[0.9992926,0.00004319522,0.0003457972,0.0001375237,0.0000698079,0.0001110845],"domain_scores_gemma":[0.9993997,0.0001317185,0.0001436965,0.0001159997,0.0001748185,0.00003413162],"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":[0.006388023,0.002448038,0.0955511,0.0008342294,0.001147225,0.000003288273,0.002510134,0.06192505,0.3303094,0.003280062,0.001682619,0.4939208],"study_design_scores_gemma":[0.006156783,0.01083844,0.3148984,0.0002404901,0.0001698951,0.00003564256,0.0009095837,0.4924721,0.1672449,0.004602038,0.001629653,0.0008020212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6748655,0.00003082135,0.3236915,0.00006828961,0.0002431981,0.0001282495,0.0009249332,0.000002217964,0.00004525558],"genre_scores_gemma":[0.9888852,0.00007879565,0.01048352,0.0001083138,0.00001777859,0.000007168506,0.000397022,0.00000467564,0.00001755262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4931188,"threshold_uncertainty_score":0.4432123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01660439633401863,"score_gpt":0.266012007464778,"score_spread":0.2494076111307593,"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."}}