{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005591433,0.0002656871,0.0005003358,0.0003587268,0.0001268859,0.00001046963,0.0004396373,0.0005059603,0.000004065531],"category_scores_gemma":[0.0003294839,0.000257883,0.0002355332,0.0003355942,0.0003186431,0.00002058699,0.00008831739,0.0004512958,4.795307e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002498485,"about_ca_system_score_gemma":0.0002101778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002193134,"about_ca_topic_score_gemma":0.00004213806,"domain_scores_codex":[0.9982896,0.00001974589,0.0008626691,0.0003572953,0.0001420011,0.0003286704],"domain_scores_gemma":[0.9990439,0.00001339239,0.0002551875,0.0004836747,0.0001685101,0.0000352871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000139208,0.00009747931,0.0246768,0.001051547,0.0002275592,0.000001614419,0.0003776141,0.06327803,0.8955329,0.00591371,0.0000117165,0.008691806],"study_design_scores_gemma":[0.001118768,0.0002744847,0.0006410289,0.0004914031,0.0001174804,0.00000709734,0.000221854,0.1009774,0.8862614,0.0002281252,0.009337833,0.0003231638],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7791328,0.0004405559,0.2180441,0.000164779,0.0001667848,0.00102179,0.00002972391,0.00009505448,0.0009043323],"genre_scores_gemma":[0.900997,0.000070021,0.09829194,0.0000178201,0.00006666071,0.00009499976,0.00006455505,0.00002992406,0.0003671144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1218641,"threshold_uncertainty_score":0.9999874,"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."}}