{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001164783,0.0001366925,0.000198583,0.00006828747,0.0001395349,0.00003239309,0.00006573911,0.0002634609,0.000003559683],"category_scores_gemma":[0.001068841,0.0001170195,0.00003917815,0.00007795179,0.0001835954,0.00001070964,0.0001063669,0.00008835276,1.257779e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009289007,"about_ca_system_score_gemma":0.00003676579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000600058,"about_ca_topic_score_gemma":0.000007918194,"domain_scores_codex":[0.9989839,0.0002495145,0.0003732207,0.0002439655,0.00002506674,0.0001243657],"domain_scores_gemma":[0.9993132,0.0001013145,0.0002579893,0.0001447547,0.0001543462,0.00002842003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001838186,0.00003554934,0.3235877,0.0004528856,0.00003551577,1.508252e-8,0.0001327155,0.00001329236,0.6155585,0.001905637,0.00003059399,0.05806376],"study_design_scores_gemma":[0.003867995,0.001324178,0.4792921,0.0003180355,0.00004719602,0.000004556028,0.0001156054,0.08060689,0.3463473,0.002985179,0.08469513,0.0003958124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3752709,0.0003203226,0.6008022,0.00004930142,0.00004974862,0.02290389,0.00006126416,0.00002605125,0.0005162949],"genre_scores_gemma":[0.3487027,0.00001072473,0.6340041,0.00001970032,0.0001053566,0.01566786,0.0002494876,0.00001409531,0.001226022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2692112,"threshold_uncertainty_score":0.4771918,"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."}}