{"id":"W2943381976","doi":"10.1089/cmb.2018.0239","title":"Toward an Alignment-Free Method for Feature Extraction and Accurate Classification of Viral Sequences","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Virus; Subsequence; Computational biology; Genetics; Mathematics","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":[0.0002651295,0.000065058,0.0001454023,0.00003927369,0.00002413796,0.000006590721,0.0001055651,0.00008405052,0.000002108742],"category_scores_gemma":[0.00004571467,0.00005246927,0.00005402097,0.0000202846,0.00004000555,0.000002943696,0.000027719,0.00003997389,1.867031e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006576535,"about_ca_system_score_gemma":0.00005733893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000274823,"about_ca_topic_score_gemma":0.000001745652,"domain_scores_codex":[0.9994879,0.00006560122,0.0002157295,0.0001126516,0.00005049898,0.00006757264],"domain_scores_gemma":[0.9992582,0.00007090579,0.000336288,0.00006951607,0.0002380435,0.0000270356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001858641,0.00002646106,0.004442015,0.00001345036,0.0001016013,1.510079e-7,0.00005847965,0.002774404,0.9853149,0.002388369,0.0001993107,0.004495007],"study_design_scores_gemma":[0.005425564,0.01033986,0.5206914,0.00003358839,0.0001912568,0.000434788,0.001001201,0.01318471,0.2337242,0.1899433,0.02449601,0.0005342096],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415073,0.0007327094,0.05673032,0.000618484,0.0002112435,0.0001021344,0.00005413385,5.112204e-7,0.00004318752],"genre_scores_gemma":[0.922117,0.00009484579,0.07749008,0.00008280027,0.0001410138,0.000002067208,0.00005134132,0.00000405798,0.00001681751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7515907,"threshold_uncertainty_score":0.2139635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03237791519115444,"score_gpt":0.3414660170478026,"score_spread":0.3090881018566481,"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."}}