{"id":"W2218908876","doi":"10.1109/bibm.2015.7359954","title":"ZSeq 2.0: A fully automatic preprocessing method for next generation sequencing data","year":2015,"lang":"en","type":"article","venue":"","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Trimming; Preprocessor; Computer science; Adapter (computing); Outlier; Data mining; Data pre-processing; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003903607,0.002673679,0.001936506,0.005571167,0.002254474,0.002624808,0.003370533,0.001198601,0.02998259],"category_scores_gemma":[0.008487591,0.001765396,0.001988771,0.004177153,0.0006540829,0.001708917,0.002369132,0.002693591,0.01993233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107938,"about_ca_system_score_gemma":0.002913891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003545193,"about_ca_topic_score_gemma":0.006223471,"domain_scores_codex":[0.9973863,0.0003134883,0.0003007373,0.0008414807,0.0009725063,0.0001855797],"domain_scores_gemma":[0.9975771,0.0007218984,0.0002655663,0.0004368092,0.0008960495,0.0001025304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001760186,0.0002139719,0.01465568,0.003712328,0.001000351,0.001041549,0.001818858,0.009258506,0.3515103,0.0118764,0.2350306,0.3681213],"study_design_scores_gemma":[0.0002749171,0.0002561446,0.02567747,0.0002583718,0.0004199415,0.001297508,0.0004069441,0.06170649,0.2874312,0.01962161,0.601932,0.0007174676],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01259824,0.0008451634,0.8001248,0.0002002754,0.0004323476,0.0007714662,0.09932309,0.08017683,0.005527688],"genre_scores_gemma":[0.01764165,0.0004481416,0.8364217,0.0005486846,0.0001212512,0.002473085,0.115974,0.01973653,0.006634974],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02998259,"threshold_uncertainty_score":0.1003018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2482787616255271,"score_gpt":0.3631426912189121,"score_spread":0.114863929593385,"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."}}