{"id":"W4233999394","doi":"10.32920/ryerson.14657172","title":"Protein structural class prediction using predicted secondary structure and hydropathy profile","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Class (philosophy); Machine learning; Feature (linguistics); Sequence (biology); Pattern recognition (psychology); Protein structure prediction; Data mining; Protein folding; Protein structure; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001181283,0.0004113323,0.0003182333,0.00007289625,0.0001381851,0.0001753366,0.0002290381,0.0008828766,0.0002701312],"category_scores_gemma":[0.0001191296,0.0003760661,0.00009799919,0.00006738442,0.0001108619,0.00001017712,0.001257002,0.0009926327,5.22731e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004029878,"about_ca_system_score_gemma":0.0003869472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004600509,"about_ca_topic_score_gemma":0.00002348216,"domain_scores_codex":[0.9982569,0.000129713,0.0004579538,0.0006147381,0.0002492325,0.0002914413],"domain_scores_gemma":[0.998773,0.000004760978,0.0003039977,0.000630078,0.0001690346,0.0001191226],"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":[0.0001528369,0.0000230655,0.01309095,0.002501394,0.0005063867,0.00001656865,0.0006418749,0.007648197,0.968767,0.00007439358,0.00085023,0.005727145],"study_design_scores_gemma":[0.001516656,0.0004856355,0.02000012,0.000466624,0.0002045356,0.0004826038,0.0003974895,0.6382242,0.3334954,0.0003043298,0.00306043,0.001361894],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931754,0.0004087545,0.002823706,0.00004467317,0.0004519094,0.0008815055,0.0008116171,0.00007484529,0.001327582],"genre_scores_gemma":[0.956843,0.00002213591,0.03562083,0.0001101184,0.0004754455,0.00002741154,0.006325421,0.00005368978,0.0005219532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6352715,"threshold_uncertainty_score":0.9998691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005863915885939899,"score_gpt":0.2344738505864852,"score_spread":0.2286099347005453,"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."}}