{"id":"W4307511629","doi":"10.2196/29404","title":"Prediction of Antibody-Antigen Binding via Machine Learning: Development of Data Sets and Evaluation of Methods","year":2022,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Antigen; Computer science; Antibody; k-nearest neighbors algorithm; Protein sequencing; Artificial intelligence; Computational biology; Machine learning; Biology; Peptide sequence; Immunology; Gene; Genetics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02378397,0.002595253,0.002196535,0.005866985,0.001087076,0.002481331,0.004276785,0.002816655,0.002008686],"category_scores_gemma":[0.05833759,0.0008912745,0.002106377,0.003935873,0.001241201,0.002840187,0.002647931,0.003828609,0.001369675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001744856,"about_ca_system_score_gemma":0.002041547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006620939,"about_ca_topic_score_gemma":0.003299007,"domain_scores_codex":[0.9872912,0.006575315,0.001427779,0.001211646,0.003235357,0.0002587868],"domain_scores_gemma":[0.9444162,0.03897372,0.001883358,0.004551714,0.009464173,0.0007107066],"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":[0.001350808,0.003149054,0.04445975,0.00149784,0.001157851,0.0002455885,0.0002185008,0.4257848,0.003076306,0.00392469,0.01558854,0.4995462],"study_design_scores_gemma":[0.0001329864,0.0004995764,0.005442964,0.0002451825,0.0001243519,0.00009994854,0.0001091193,0.9784485,0.007440314,0.003632717,0.003745118,0.00007923761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2894271,0.008286851,0.662964,0.001913122,0.0007524207,0.004727306,0.01833715,0.008039441,0.005552562],"genre_scores_gemma":[0.325957,0.001842263,0.6428803,0.00033053,0.0001499089,0.007198306,0.02018468,0.0003194177,0.001137662],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02378397,"threshold_uncertainty_score":0.1257831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666600225481614,"score_gpt":0.3500390679752069,"score_spread":0.2833790454270455,"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."}}