{"id":"W4385294814","doi":"10.1515/jib-2022-0055","title":"Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks","year":2023,"lang":"en","type":"article","venue":"Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Transporter; Computer science; Classifier (UML); Artificial intelligence; Deep learning; Encoder; Transmembrane protein; Computational biology; Machine learning; Chemistry; Biochemistry; Biology; Gene","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":[0.0004992611,0.0009596518,0.0006757774,0.001147781,0.0003039,0.0007470641,0.001047362,0.001097993,0.00102167],"category_scores_gemma":[0.0006904198,0.0003016182,0.0006355821,0.000668811,0.000278006,0.001026477,0.001011969,0.0007686528,0.0008020133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008994044,"about_ca_system_score_gemma":0.0008363027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005768806,"about_ca_topic_score_gemma":0.007799225,"domain_scores_codex":[0.9997554,0.00003113949,0.0000110141,0.00006621453,0.00008962106,0.00004660783],"domain_scores_gemma":[0.9997476,0.0000531583,0.00003231559,0.00004072598,0.0001008391,0.00002545698],"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":[0.000565885,0.0003974891,0.007551874,0.0002596369,0.0002526329,0.0006070205,0.00007539339,0.1868857,0.1570718,0.006973766,0.01002742,0.6293314],"study_design_scores_gemma":[0.000007739307,0.00002841824,0.0007535341,0.00000701293,0.00001776111,0.0001147701,0.00001009539,0.9816942,0.01472406,0.001186038,0.001445625,0.00001077823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1430931,0.001221705,0.8422053,0.0005864655,0.0001307773,0.0001001955,0.0009855559,0.00634586,0.005331045],"genre_scores_gemma":[0.6444219,0.0006248756,0.3386457,0.0005184051,0.00005805576,0.00009467762,0.003990974,0.0002590655,0.01138627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005768806,"threshold_uncertainty_score":0.01147044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009999736582629051,"score_gpt":0.2589255661150686,"score_spread":0.2489258295324395,"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."}}