{"id":"W4286797666","doi":"10.1101/2022.07.23.501263","title":"Predicting the specific substrate for transmembrane transport proteins using BERT language model","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"UniProt; Computer science; Classifier (UML); Transmembrane protein; Artificial intelligence; 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":[0.0007870237,0.001146954,0.0003498141,0.001576834,0.0002141108,0.0009148617,0.0005922802,0.0009046308,0.001208298],"category_scores_gemma":[0.002061618,0.0001734212,0.0005884719,0.0008270922,0.000233265,0.0008924799,0.0003977144,0.000651947,0.001045729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001011872,"about_ca_system_score_gemma":0.0007279529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005826621,"about_ca_topic_score_gemma":0.005727753,"domain_scores_codex":[0.9997137,0.0000836171,0.00002328987,0.00006601014,0.00006672191,0.00004665271],"domain_scores_gemma":[0.9989399,0.0005662891,0.0001196051,0.00006334835,0.0002559323,0.00005495308],"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":[0.001522615,0.0005072956,0.05658974,0.0005284493,0.0001595735,0.001337293,0.0001480341,0.7172457,0.06330226,0.01039053,0.01693925,0.1313293],"study_design_scores_gemma":[0.000008172142,0.00003482359,0.000717451,0.000007141225,0.000008102988,0.00007322377,0.00001837742,0.9914465,0.005703059,0.001385826,0.0005896008,0.000007596874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8153834,0.001330662,0.1623502,0.0008665736,0.00009815244,0.0001078647,0.009954887,0.004348657,0.005559578],"genre_scores_gemma":[0.9546517,0.000277393,0.03291432,0.00009060405,0.00001828198,0.00005164664,0.009723711,0.00009763514,0.002174812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005826621,"threshold_uncertainty_score":0.01158541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0152082455531926,"score_gpt":0.2387239810005427,"score_spread":0.2235157354473502,"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."}}