{"id":"W2892636970","doi":"10.3390/v10100528","title":"Considerations for Optimization of High-Throughput Sequencing Bioinformatics Pipelines for Virus Detection","year":2018,"lang":"en","type":"article","venue":"Viruses","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sanofi (Canada)","funders":"","keywords":"Computer science; Pipeline (software); Identification (biology); Pipeline transport; Data mining; Throughput; Reliability (semiconductor); Computational biology; Biology; Engineering","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":[0.00007634152,0.0000759446,0.00009594058,0.00003327688,0.0002363138,0.0000327433,0.00004443367,0.00004724573,0.000566382],"category_scores_gemma":[0.0001642121,0.00007117238,0.00004517745,0.00007895079,0.0001160781,0.0004601043,0.00002790228,0.00002375445,0.00003884238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000761436,"about_ca_system_score_gemma":0.0000147157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007998811,"about_ca_topic_score_gemma":0.001291245,"domain_scores_codex":[0.9994659,0.000008707194,0.0002549438,0.0001088024,0.00004509952,0.0001165198],"domain_scores_gemma":[0.9995376,0.0001287993,0.0001386045,0.0001130509,0.00005781469,0.00002406901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003080242,0.00002505582,0.00001143788,0.00001591559,0.00001134453,3.981027e-8,0.000303578,0.01512739,0.9802631,0.0001718406,0.001834935,0.002204553],"study_design_scores_gemma":[0.00028962,0.0002049627,0.0001531686,0.00001387687,0.00003328892,0.000005885222,0.000103713,0.05074465,0.9416446,0.0007039702,0.005997348,0.000104915],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1985475,0.000005686131,0.7998519,0.00007506782,0.0004929905,0.0004808168,0.0002232544,0.00004318853,0.0002796282],"genre_scores_gemma":[0.7966692,0.00001144373,0.2025991,0.0004446732,0.0001353605,0.00005026928,0.00001213956,0.00001181589,0.00006594745],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5981218,"threshold_uncertainty_score":0.6201485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04432254068784137,"score_gpt":0.2855008862064169,"score_spread":0.2411783455185756,"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."}}