{"id":"W2950237782","doi":"10.1186/s12864-019-5571-y","title":"ML-DSP: Machine Learning with Digital Signal Processing for ultrafast, accurate, and scalable genome classification at all taxonomic levels","year":2019,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Software; Genome; Artificial intelligence; Computer science; Pattern recognition (psychology); Digital signal processing; Biology; Benchmark (surveying); Machine learning; Support vector machine; Data mining; Computational biology; Genetics","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":[0.0001207031,0.0002218635,0.0002026688,0.00003544444,0.0001806357,0.0001125999,0.000137537,0.0001050398,0.000008049801],"category_scores_gemma":[0.000013078,0.000200998,0.00005446729,0.00003943172,0.0000707238,0.000005375487,0.0001294196,0.00006966721,0.00001290514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004896508,"about_ca_system_score_gemma":0.0001303482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005777815,"about_ca_topic_score_gemma":0.00005448417,"domain_scores_codex":[0.9988912,0.00001577621,0.0002212895,0.0004961634,0.0000612874,0.0003142742],"domain_scores_gemma":[0.999447,0.00002657656,0.000166722,0.0001865407,0.00009137635,0.00008178131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002727462,0.0000259997,0.04342493,0.00007609544,0.00007335612,1.996105e-7,0.0001101236,0.003901764,0.9494593,0.00001659505,0.00002687675,0.002612054],"study_design_scores_gemma":[0.007569213,0.003040198,0.1654971,0.00004853253,0.0002485626,0.0001539052,0.001481687,0.05838206,0.1732898,0.0001620047,0.5877337,0.00239325],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990482,0.001464312,0.006719526,0.00004309416,0.00003282826,0.0005685004,0.0001659518,0.000007796541,0.0005159286],"genre_scores_gemma":[0.9941047,0.000156491,0.003256204,0.00007423812,0.0001239311,0.00005223209,0.0002928879,0.00005023254,0.001889027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7761695,"threshold_uncertainty_score":0.8196462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03221787137313004,"score_gpt":0.2347313241980173,"score_spread":0.2025134528248873,"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."}}