{"id":"W2809728348","doi":"10.4236/jbise.2018.116012","title":"Improving Protein Sequence Classification Performance Using Adjacent and Overlapped Segments on Existing Protein Descriptors","year":2018,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"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":"Subsequence; Sequence (biology); Computer science; Protein sequencing; Pattern recognition (psychology); Segmentation; Feature selection; Feature (linguistics); Feature vector; Artificial intelligence; Peptide sequence; Mathematics; Biology; Genetics; Gene","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":[0.0008915194,0.00008530472,0.00008309237,0.0001095004,0.0001477828,0.00005753363,0.000134082,0.00005462628,0.000001512013],"category_scores_gemma":[0.000552774,0.00006677995,0.00001306918,0.0001866393,0.0002904073,0.00003668941,0.00007710352,0.0001378657,4.142988e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005469512,"about_ca_system_score_gemma":0.0001140475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004267746,"about_ca_topic_score_gemma":1.678806e-7,"domain_scores_codex":[0.9990683,0.000009089251,0.0002355639,0.0001229616,0.0003661416,0.0001979069],"domain_scores_gemma":[0.9994678,0.00000439408,0.000169707,0.00007913675,0.0001273361,0.0001516333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001484137,0.000008781994,0.0004593777,0.00005300382,0.000003569553,8.019424e-7,0.00006317016,0.00004208571,0.9810222,0.00001861654,0.000003297532,0.01831019],"study_design_scores_gemma":[0.000511077,0.001622471,0.008990172,0.0006228869,0.00001065129,0.0001682736,0.0001359266,0.6787947,0.3068239,0.000004732772,0.002077758,0.0002373678],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9891187,0.0000336775,0.01055689,0.00004612033,0.0001089629,0.00009135125,5.850762e-7,0.000004748323,0.00003893801],"genre_scores_gemma":[0.9786319,0.00001085767,0.02111857,0.00002744175,0.0001934603,0.000001387292,6.233759e-7,0.000005391698,0.00001041244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6787527,"threshold_uncertainty_score":0.2723207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02626929420757971,"score_gpt":0.273701352229618,"score_spread":0.2474320580220383,"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."}}