{"id":"W1768968559","doi":"10.3233/ifs-151550","title":"Classifying sequences by the optimized dissimilarity space embedding approach: A case study on the solubility analysis of the E. coli proteome","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Classifier (UML); Embedding; Proteome; Pattern recognition (psychology); Generality; Protein sequencing; Sequence (biology); Representation (politics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001232861,0.0006501959,0.0005878463,0.001617719,0.0004679419,0.0007268944,0.000628394,0.0009863517,0.0008287391],"category_scores_gemma":[0.003152012,0.0001003799,0.0006140396,0.001427666,0.0005022364,0.0009361,0.0007554556,0.0004517449,0.0002218991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004389625,"about_ca_system_score_gemma":0.0003721015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002508073,"about_ca_topic_score_gemma":0.002300212,"domain_scores_codex":[0.9991819,0.0003101687,0.00008133492,0.0001747395,0.0001868548,0.00006497064],"domain_scores_gemma":[0.9982285,0.001020052,0.0001205434,0.0001921002,0.0003256593,0.0001131146],"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":[0.002037684,0.002099673,0.04584063,0.0009587865,0.0003252488,0.001396014,0.0006979562,0.4404291,0.04273142,0.006625947,0.004508702,0.4523488],"study_design_scores_gemma":[0.00005109954,0.0005288484,0.006046944,0.00001954394,0.00003120701,0.0003233288,0.0003721382,0.9687119,0.01812636,0.003772836,0.001991216,0.00002455821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9516224,0.0003832202,0.04603529,0.0002666969,0.00004364321,0.00008016091,0.0004758547,0.0001910911,0.0009018043],"genre_scores_gemma":[0.9100581,0.000155817,0.08778787,0.00003629626,0.00002642601,0.00004304593,0.001147664,0.00002588411,0.0007188126],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.002508073,"threshold_uncertainty_score":0.006520092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0629302058908194,"score_gpt":0.3282464611380764,"score_spread":0.265316255247257,"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."}}