{"id":"W4410811958","doi":"10.1093/biomethods/bpaf041","title":"KD_MultiSucc: incorporating multi-teacher knowledge distillation and word embeddings for cross-species prediction of protein succinylation sites","year":2025,"lang":"en","type":"article","venue":"Biology Methods and Protocols","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Succinylation; Computer science; Computational biology; Embedding; Artificial intelligence; Biological system; Chemistry; Lysine; Biology; 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":[0.001269569,0.002341924,0.00175871,0.001617871,0.0009147073,0.001228602,0.002903901,0.002590503,0.004228912],"category_scores_gemma":[0.004635956,0.0008494557,0.001565459,0.00129992,0.0009073979,0.002744663,0.002315796,0.003608081,0.002923533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001255374,"about_ca_system_score_gemma":0.001962694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01195094,"about_ca_topic_score_gemma":0.01946379,"domain_scores_codex":[0.9992639,0.0001742887,0.00005302678,0.0003019153,0.0001182895,0.00008858721],"domain_scores_gemma":[0.9980719,0.001108726,0.000133661,0.0001970865,0.0003704533,0.0001181725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001195798,0.0005491554,0.01089155,0.0007974642,0.0005288809,0.0005695444,0.00027242,0.4524681,0.01261813,0.005944605,0.03008076,0.4840837],"study_design_scores_gemma":[0.00002437128,0.00005424793,0.0003106011,0.00001701433,0.00002088663,0.00004114075,0.00001691732,0.9934303,0.001398589,0.003220204,0.00144664,0.00001911235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08080573,0.004716321,0.8852298,0.001338515,0.0005055355,0.0002476249,0.004290238,0.01965418,0.003212051],"genre_scores_gemma":[0.5838352,0.001598518,0.3809,0.001809819,0.0003416007,0.0007328371,0.01921816,0.001252976,0.01031098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01195094,"threshold_uncertainty_score":0.02376276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05279280048849869,"score_gpt":0.4607313964467801,"score_spread":0.4079385959582814,"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."}}