{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003138739,0.001535283,0.001153191,0.001447271,0.0007764376,0.001632266,0.003275121,0.002523959,0.00268084],"category_scores_gemma":[0.007993347,0.0006425685,0.001061032,0.0008194618,0.001161049,0.00233211,0.002999792,0.002995444,0.001208057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133722,"about_ca_system_score_gemma":0.002065531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003141215,"about_ca_topic_score_gemma":0.006282238,"domain_scores_codex":[0.998836,0.000308514,0.00005327169,0.0003926323,0.00031265,0.00009693336],"domain_scores_gemma":[0.9974611,0.001420686,0.0001704599,0.0003734129,0.0004161941,0.0001581443],"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":[0.00108319,0.0005187047,0.004693408,0.0003641719,0.0002670799,0.0003640158,0.0002572071,0.1783321,0.05035691,0.0266995,0.01587044,0.7211933],"study_design_scores_gemma":[0.00007485689,0.0001859827,0.0003547076,0.00003330306,0.00003836553,0.0001894021,0.00002902037,0.9615173,0.0143022,0.01583813,0.007405458,0.00003120976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03126358,0.001538319,0.9542685,0.0006038689,0.0002950849,0.0001868502,0.0003474257,0.007113483,0.004382891],"genre_scores_gemma":[0.178354,0.0003775585,0.8121623,0.001292754,0.0001455096,0.0001608841,0.001343406,0.00100483,0.00515863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003275121,"threshold_uncertainty_score":0.01659942,"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."}}