{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002328072,0.0007643758,0.001088345,0.0008143023,0.0002737467,0.0001620095,0.0009212572,0.0003925591,0.00001888013],"category_scores_gemma":[0.0009317479,0.0005669469,0.0003835441,0.001131142,0.0006989957,0.0007031663,0.0003004632,0.0009081983,0.00002225443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006780926,"about_ca_system_score_gemma":0.0004678484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008667153,"about_ca_topic_score_gemma":0.000003491902,"domain_scores_codex":[0.9929961,0.000116431,0.004699211,0.0002141239,0.001218467,0.0007556847],"domain_scores_gemma":[0.9926847,0.0001564285,0.004625952,0.0005854574,0.001573052,0.0003743609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01082163,0.002504213,0.01309597,0.02779103,0.01868354,0.00007686293,0.30045,0.275558,0.09495695,0.01693164,0.03291365,0.2062166],"study_design_scores_gemma":[0.004207243,0.002068687,0.002447597,0.0004897216,0.0003854363,0.0008023232,0.01400434,0.9155663,0.05226315,0.00006444279,0.006596846,0.001103895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3782648,0.00084503,0.6070604,0.0002315611,0.000930711,0.002812675,0.0002981172,0.0001756038,0.009381081],"genre_scores_gemma":[0.9497401,0.0007364285,0.04709371,0.0003987804,0.0002004516,0.0001039678,0.001454648,0.00005754719,0.0002144201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6400083,"threshold_uncertainty_score":0.9996782,"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."}}