{"id":"W2607286649","doi":"10.1089/cmb.2017.0021","title":"Zseq: An Approach for Preprocessing Next-Generation Sequencing Data","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preprocessor; Sequence (biology); DNA sequencing; Sequence assembly; Computer science; Computational biology; Genome; Biology; Discriminative model; Genomics; Algorithm; Genetics; Artificial intelligence; DNA; 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":[0.0004377244,0.00007944232,0.000137161,0.00002795036,0.0002870215,0.00007501696,0.0004802916,0.00007342998,8.8893e-7],"category_scores_gemma":[0.0001959856,0.00006767909,0.00004531659,0.000009673025,0.00008153819,0.00000859781,0.0001396019,0.00004597666,1.697312e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001036375,"about_ca_system_score_gemma":0.0001856096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003475833,"about_ca_topic_score_gemma":0.000004005243,"domain_scores_codex":[0.9993445,0.00003705652,0.0002525205,0.0002073042,0.00005439104,0.0001042592],"domain_scores_gemma":[0.9989068,0.00001908113,0.0004362109,0.0003034096,0.000292918,0.00004161437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008736584,0.00005006231,0.004672243,0.0000162516,0.0001447029,6.125277e-7,0.0000777539,0.03011579,0.9482689,0.0004769875,0.0003114759,0.01577787],"study_design_scores_gemma":[0.006679763,0.004795254,0.06429416,0.00005131509,0.0003486506,0.0008508901,0.0008331009,0.7630144,0.08147056,0.04351434,0.03281662,0.001330929],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7640704,0.0007919825,0.2345251,0.000135485,0.0002265663,0.0000755108,0.00003631591,7.778366e-7,0.0001378055],"genre_scores_gemma":[0.8851529,0.00004642932,0.1132214,0.0000960544,0.001119181,0.000002479814,0.0003407367,0.000007438046,0.00001342632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8667983,"threshold_uncertainty_score":0.2759873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2161899380631361,"score_gpt":0.3635272799106088,"score_spread":0.1473373418474727,"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."}}