{"id":"W2887505600","doi":"10.1101/394932","title":"ML-DSP: Machine Learning with Digital Signal Processing for ultrafast, accurate, and scalable genome classification at all taxonomic levels","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Benchmark (surveying); Computer science; Digital signal processing; Software; Identification (biology); Scalability; Pattern recognition (psychology); Artificial intelligence; Machine learning; Computational biology; Biology; Data mining; Genetics; Computer hardware; Gene; Cartography","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":[0.001925395,0.001516772,0.0008278532,0.002466742,0.0005299692,0.001535553,0.002842419,0.001160955,0.006909719],"category_scores_gemma":[0.005052291,0.0006126331,0.001168001,0.001776279,0.0007627801,0.002454101,0.001945467,0.001926288,0.004213301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007561229,"about_ca_system_score_gemma":0.0009442555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001394688,"about_ca_topic_score_gemma":0.001669042,"domain_scores_codex":[0.9985856,0.0002211589,0.0001371376,0.0004468743,0.0005241692,0.00008511463],"domain_scores_gemma":[0.9975086,0.001051231,0.0003091383,0.0004513714,0.0005227472,0.0001568439],"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":[0.0006719253,0.0004160459,0.007535037,0.0007850484,0.0003488848,0.000260455,0.0002807892,0.07590085,0.05749677,0.008201846,0.06049932,0.787603],"study_design_scores_gemma":[0.0001177719,0.0001886306,0.001858501,0.00004432769,0.00003290264,0.0001345449,0.00006179373,0.9090397,0.05689814,0.01352828,0.01802136,0.00007397286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01748953,0.000338875,0.8883048,0.0003700588,0.0001423355,0.0001321683,0.001685623,0.08990353,0.001633086],"genre_scores_gemma":[0.1301859,0.0001753255,0.8596734,0.0004126431,0.0001102828,0.0004965332,0.004274448,0.00237262,0.002298891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006909719,"threshold_uncertainty_score":0.02311534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02509433138171077,"score_gpt":0.2234510845729224,"score_spread":0.1983567531912116,"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."}}