{"id":"W4406142138","doi":"10.1021/acs.jproteome.4c00160","title":"MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma","year":2025,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Human plasma; Immunoprecipitation; Computational biology; Computer science; Antibody; Tandem mass spectrometry; DECIPHER; Protein–protein interaction; Mass spectrometry; Chemistry; Bioinformatics; Biology; Cell biology; Chromatography; Immunology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001234639,0.001128811,0.0008110103,0.001860077,0.0003732297,0.0009146716,0.000833274,0.0008263494,0.001146578],"category_scores_gemma":[0.002456282,0.000338054,0.0009228846,0.0009549437,0.0002884175,0.0007917843,0.000922446,0.001021631,0.0006287819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004131559,"about_ca_system_score_gemma":0.0006341415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006868764,"about_ca_topic_score_gemma":0.0009799756,"domain_scores_codex":[0.9995821,0.00009068485,0.00002346738,0.0001704559,0.0001035033,0.00002967393],"domain_scores_gemma":[0.9994255,0.0002957775,0.0001212092,0.00006218014,0.00006467413,0.00003062656],"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":[0.001121492,0.0006772691,0.02772228,0.001119896,0.001096939,0.001020736,0.0002043736,0.1573286,0.1469962,0.008706399,0.01562078,0.6383851],"study_design_scores_gemma":[0.00003451941,0.0001557096,0.004117771,0.00001591324,0.00006992291,0.0004738527,0.0000284876,0.9543506,0.02524837,0.01008414,0.00538217,0.00003859743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0455903,0.00109505,0.9405292,0.0003007747,0.00006738717,0.0001553361,0.001816532,0.00925229,0.001193208],"genre_scores_gemma":[0.357163,0.000850226,0.63572,0.0003777074,0.00008378628,0.0004092797,0.003274255,0.0003424299,0.001779432],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001860077,"threshold_uncertainty_score":0.00652945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05985394758194044,"score_gpt":0.4171936658524401,"score_spread":0.3573397182704997,"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."}}