{"id":"W7111352857","doi":"10.1051/bioconf/202516301001/pdf","title":"TooT-SS: Transfer Learning using ProtBERT-BFD Language Model for Predicting Specific Substrates of Transport Proteins","year":2025,"lang":"en","type":"article","venue":"Springer Link (Chiba Institute of Technology)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University; Genome Canada","keywords":"Construct (python library); Language model; Class (philosophy); Artificial neural network; Transfer of learning; Transfer (computing); Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000939562,0.001059321,0.0006777408,0.0009124237,0.000390495,0.000669198,0.001459966,0.001145113,0.002561158],"category_scores_gemma":[0.001941602,0.000303311,0.0010873,0.0006480013,0.000308701,0.001219188,0.0008635412,0.001590905,0.001425597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001024569,"about_ca_system_score_gemma":0.001294323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009632337,"about_ca_topic_score_gemma":0.008309375,"domain_scores_codex":[0.9997358,0.00008206967,0.00001804381,0.00007123614,0.0000553055,0.00003760862],"domain_scores_gemma":[0.9993263,0.0003794499,0.00004216243,0.00006528116,0.0001444133,0.00004239233],"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":[0.0006313352,0.0004087178,0.004407348,0.0001711452,0.000198323,0.0002975098,0.00006565426,0.7766102,0.005855283,0.004344895,0.01246059,0.194549],"study_design_scores_gemma":[0.00001270452,0.00003043209,0.0001052365,0.000004154719,0.000006342384,0.00002153292,0.000005145358,0.9967649,0.001095376,0.001582068,0.0003674457,0.000004694848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2560082,0.001610166,0.7124684,0.001042981,0.0002692848,0.0002820843,0.005264407,0.01706847,0.005985968],"genre_scores_gemma":[0.7960539,0.0004763872,0.1834745,0.0004484437,0.00007056991,0.000447407,0.01127929,0.0005865388,0.007163049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009632337,"threshold_uncertainty_score":0.01915258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01204307215238619,"score_gpt":0.2540567325972173,"score_spread":0.2420136604448311,"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."}}