{"id":"W4408740277","doi":"10.1021/acs.jproteome.4c00967","title":"ProSIMSIt: The Best of Both Worlds in Data-Driven Rescoring and Identification Transfer","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":"IONICS Mass Spectrometry (Canada)","funders":"H2020 Research Infrastructures; European Research Council; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Python (programming language); Pipeline (software); Cluster analysis; Proteome; Data mining; Missing data; Profiling (computer programming); Computational biology; Bioinformatics; Machine learning; Biology; Programming language","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":[0.005968462,0.002951824,0.001759582,0.001873275,0.001408136,0.0029186,0.00383637,0.001657427,0.01088823],"category_scores_gemma":[0.01206389,0.001187506,0.002079361,0.001595077,0.00111205,0.00274453,0.005880614,0.003499996,0.009567827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008191188,"about_ca_system_score_gemma":0.002353472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002596807,"about_ca_topic_score_gemma":0.004338784,"domain_scores_codex":[0.9982502,0.0006011136,0.0001374979,0.0004700977,0.000401057,0.0001401203],"domain_scores_gemma":[0.9972284,0.001259808,0.0002140753,0.0008219189,0.0002913501,0.0001843242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003583456,0.001106194,0.01226786,0.002523399,0.002830999,0.001017021,0.001542139,0.0716574,0.06280641,0.01915961,0.2153559,0.6061496],"study_design_scores_gemma":[0.00045324,0.0005006013,0.005121656,0.0002144135,0.0002754099,0.0006261709,0.0002474998,0.7590144,0.0930579,0.04466943,0.09528219,0.0005370765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03145676,0.001041031,0.6824076,0.001452032,0.0004024931,0.0002806912,0.01010443,0.2686177,0.004237342],"genre_scores_gemma":[0.1490297,0.0008789839,0.7610452,0.001686832,0.0002819629,0.001424939,0.03201865,0.04786607,0.005767651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01088823,"threshold_uncertainty_score":0.0364247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09502943797816282,"score_gpt":0.4294754910656768,"score_spread":0.334446053087514,"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."}}