{"id":"W2747126452","doi":"10.4236/jbise.2017.108030","title":"Combined Use of k-Mer Numerical Features and Position-Specific Categorical Features in Fixed-Length DNA Sequence Classification","year":2017,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Categorical variable; Sequence (biology); Position (finance); DNA sequencing; Feature (linguistics); Algorithm; Pattern recognition (psychology); Mathematics; Computer science; DNA; Artificial intelligence; Computational biology; Biology; Genetics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004688511,0.00007555069,0.0001314557,0.0001144955,0.0001041246,0.00009470941,0.0002214635,0.00008684768,0.000001546394],"category_scores_gemma":[0.0006683882,0.00005690397,0.00002273934,0.0001115036,0.0004153248,0.00004948482,0.00008619652,0.0001956751,1.484626e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002295218,"about_ca_system_score_gemma":0.00006285728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001296986,"about_ca_topic_score_gemma":7.966494e-7,"domain_scores_codex":[0.9992022,0.00001104642,0.0002358898,0.0001058445,0.0003010166,0.0001440031],"domain_scores_gemma":[0.999422,0.0000288068,0.0001759735,0.0001384517,0.00009631683,0.0001384748],"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":[0.00005949624,0.00005146392,0.008635745,0.00004364037,0.00001307438,0.00001364318,0.0001683999,0.0001638747,0.9751031,0.0006871031,0.0008201098,0.01424033],"study_design_scores_gemma":[0.0005996133,0.0005020543,0.9648429,0.00008875529,0.000009928553,0.0004003344,0.00006939144,0.01366573,0.01505045,0.00003661852,0.004568142,0.000166075],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953403,0.0001955052,0.003196036,0.001041681,0.0001496077,0.00004034927,0.000002220215,0.00000243306,0.0000318886],"genre_scores_gemma":[0.9950448,0.0003216288,0.004507801,0.00003667557,0.00007352153,6.203847e-7,0.000002919449,0.000003647832,0.000008380222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9600527,"threshold_uncertainty_score":0.2320477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01495636699701944,"score_gpt":0.2671672753798142,"score_spread":0.2522109083827948,"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."}}