{"id":"W4293518025","doi":"10.1109/cibcb55180.2022.9863051","title":"Predicting the specific substrate for transmembrane transport proteins using BERT language model","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"UniProt; Computer science; Classifier (UML); Artificial intelligence; Transmembrane protein; Language model; Machine learning; Chemistry; Biochemistry","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":[0.0005328234,0.0009831458,0.0003177892,0.001291389,0.0002076846,0.0008064159,0.0005068236,0.0007488122,0.001174124],"category_scores_gemma":[0.001686708,0.0001645597,0.0005514475,0.0006832181,0.0001983275,0.0008834701,0.0003443491,0.0005126313,0.001001687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007990981,"about_ca_system_score_gemma":0.0007021015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005079201,"about_ca_topic_score_gemma":0.00562166,"domain_scores_codex":[0.9998065,0.00004589108,0.00001961947,0.00004519426,0.00004731591,0.00003551149],"domain_scores_gemma":[0.9993113,0.0003348699,0.00008356742,0.00004106871,0.0001955776,0.00003365945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001564265,0.0004508712,0.06664903,0.0005892403,0.0001468079,0.002235468,0.0001999373,0.6369049,0.08690451,0.01470208,0.01650207,0.1731509],"study_design_scores_gemma":[0.000009627998,0.00004338167,0.0009936041,0.000007930508,0.0000109433,0.0001461171,0.00002741831,0.9883134,0.007576985,0.001946974,0.0009134204,0.00001005909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7937317,0.001164639,0.1858387,0.0006885535,0.00008298078,0.0001054963,0.008359512,0.003718028,0.006310393],"genre_scores_gemma":[0.9540603,0.0003257123,0.03442191,0.0000841252,0.00001536977,0.00005730738,0.008610975,0.00009286554,0.00233138],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005079201,"threshold_uncertainty_score":0.01009929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587198441246351,"score_gpt":0.2557313749277768,"score_spread":0.2398593905153133,"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."}}