{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001245453,0.0008896349,0.001261403,0.002810004,0.0006136859,0.001045727,0.001438187,0.001069989,0.001704152],"category_scores_gemma":[0.003375813,0.0001999706,0.0007876329,0.002833991,0.000368402,0.001662948,0.0008482683,0.001075823,0.00149543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004421584,"about_ca_system_score_gemma":0.001065692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002652547,"about_ca_topic_score_gemma":0.003913658,"domain_scores_codex":[0.9987464,0.0002143451,0.0001518057,0.0004006169,0.0003633384,0.0001234487],"domain_scores_gemma":[0.9978801,0.0008338565,0.00016477,0.0002705409,0.0007218636,0.0001289535],"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":[0.0006908327,0.0004303341,0.01214251,0.0003261034,0.0001457507,0.0001780532,0.0001068815,0.0223831,0.04054312,0.001558493,0.005417795,0.9160771],"study_design_scores_gemma":[0.0001428869,0.0006183046,0.01617802,0.00009947755,0.0001882519,0.0007625234,0.0002472585,0.9156476,0.04593913,0.008716824,0.01131749,0.0001422205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2438509,0.003598882,0.7361628,0.0005511782,0.0005468947,0.0003583843,0.002431708,0.00814085,0.004358464],"genre_scores_gemma":[0.5484421,0.0005982159,0.4435974,0.0002321046,0.0001290463,0.0002475446,0.003960306,0.0001515956,0.002641743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002810004,"threshold_uncertainty_score":0.006586671,"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."}}