{"id":"W4416205407","doi":"10.1093/bib/bbaf590","title":"M3Site: multiclass multimodal learning for protein active site identification and classification","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Cegep Edouard Montpetit","funders":"Fundamental Research Funds for the Central Universities; Wuhan University; Renmin Hospital of Wuhan University; National Natural Science Foundation of China; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"UniProt; Feature (linguistics); Source code; Multiclass classification; Active learning (machine learning); Graph; Identification (biology); Limiting; Binary classification","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":[0.001306299,0.002314427,0.001177292,0.002047573,0.0005853279,0.001088804,0.002589792,0.002013094,0.006394192],"category_scores_gemma":[0.003166452,0.0004184467,0.001681048,0.001570095,0.0005348124,0.001838075,0.003062673,0.002169091,0.003717883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008484425,"about_ca_system_score_gemma":0.001052074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00431941,"about_ca_topic_score_gemma":0.008016676,"domain_scores_codex":[0.9993724,0.0001614369,0.00002614099,0.0002299243,0.0001395011,0.00007059386],"domain_scores_gemma":[0.9993275,0.0002134899,0.00006523891,0.0001870193,0.00011471,0.00009193934],"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":[0.001093966,0.0009797949,0.007483078,0.0008203167,0.0005319884,0.0002998794,0.000189847,0.1027828,0.03489066,0.009077078,0.1324338,0.7094167],"study_design_scores_gemma":[0.00007316256,0.0001803421,0.001210546,0.00004391283,0.00005539542,0.0001472391,0.00005411652,0.9594045,0.009927553,0.01815685,0.01070102,0.00004535174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06201699,0.002923837,0.8584569,0.001009437,0.0002486328,0.0003517011,0.0142298,0.0559206,0.004842052],"genre_scores_gemma":[0.3553642,0.001163622,0.5816689,0.001188041,0.0002304839,0.001029103,0.04784336,0.002237442,0.009274769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006394192,"threshold_uncertainty_score":0.02139068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819747715008626,"score_gpt":0.3033901452785213,"score_spread":0.285192668128435,"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."}}