{"id":"W4393158691","doi":"10.1609/aaai.v38i1.27765","title":"ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide Sequencing","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Fudan University; National Natural Science Foundation of China","keywords":"Computational biology; DNA sequencing; Peptide; Biology; Computer science; Natural language processing; Artificial intelligence; Genetics; Biochemistry; Gene","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":[0.0004750027,0.0002109738,0.0002020398,0.00006954368,0.0001340069,0.0001932188,0.0005403208,0.0001097042,0.00001430977],"category_scores_gemma":[0.0004248242,0.0001600063,0.0001250291,0.0002805071,0.0001084748,0.00002136481,0.000158994,0.0002994397,0.00003169793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004924663,"about_ca_system_score_gemma":0.0001744881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002355852,"about_ca_topic_score_gemma":0.000004039364,"domain_scores_codex":[0.9986739,0.00001319293,0.0004046966,0.000362049,0.0001958275,0.0003503428],"domain_scores_gemma":[0.9993337,0.0000256146,0.0001196856,0.0001412817,0.0002975765,0.00008215463],"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":[0.0001260534,0.00004826655,0.00007790096,0.0001313685,0.00005562178,2.910492e-7,0.002026935,0.0007947155,0.9137051,0.07165536,0.0001697357,0.01120869],"study_design_scores_gemma":[0.00002132335,0.0003035171,0.00005150282,0.0002824375,0.00002385183,0.00001772941,0.002477597,0.02359003,0.9690367,0.00302055,0.0009483347,0.0002263977],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9187889,0.0002313348,0.04177032,0.0006147508,0.0001831161,0.0005658261,0.00001080125,0.000048672,0.03778631],"genre_scores_gemma":[0.996738,0.00006418563,0.001939039,0.0001898731,0.0001208897,0.0000539067,0.000003691191,0.00002244889,0.0008680001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07794909,"threshold_uncertainty_score":0.6524866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03871356193591151,"score_gpt":0.2895098014544825,"score_spread":0.250796239518571,"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."}}