{"id":"W4395689043","doi":"10.1016/j.xpro.2024.103041","title":"Protocol to identify biomarkers in patients with post-COVID condition using multi-omics and machine learning analysis of human plasma","year":2024,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Metabolomics Innovation Centre; University of Alberta","funders":"Canadian Institutes of Health Research; Northern Alberta Clinical Trials and Research Centre; University of Alberta","keywords":"Feature selection; Preprocessor; Protocol (science); Computer science; Cluster analysis; Omics; Workflow; Biomarker discovery; Data pre-processing; Coronavirus disease 2019 (COVID-19); Machine learning; Data mining; Artificial intelligence; Bioinformatics; Medicine; Proteomics; Biology; Pathology; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002498037,0.0001333613,0.0001856856,0.0002417964,0.00005894673,0.00005943315,0.00008225743,0.00009323134,0.00001361632],"category_scores_gemma":[0.00001727564,0.0001131643,0.00005150318,0.0003160275,0.00004744109,0.00001000385,0.00008772672,0.00009665428,7.99532e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002981083,"about_ca_system_score_gemma":0.00005170536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007167473,"about_ca_topic_score_gemma":0.0002194916,"domain_scores_codex":[0.9991413,0.00004590589,0.0003072718,0.0002397785,0.0001039301,0.0001617773],"domain_scores_gemma":[0.9996002,0.00000687865,0.0001049259,0.0001535487,0.00006921626,0.00006524682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002724465,0.00044431,0.5430515,0.001875105,0.002999534,0.00001037448,0.001346547,0.01053678,0.4268746,0.0001118676,0.00007174187,0.009953128],"study_design_scores_gemma":[0.02106456,0.01122321,0.561237,0.001770672,0.0009916293,0.000008430757,0.0006489991,0.2923267,0.08996832,0.000146395,0.01834196,0.002272173],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7846637,0.000003459029,0.002146348,0.000008540049,0.000006877578,0.2130387,0.0001038718,0.000008184542,0.00002029452],"genre_scores_gemma":[0.7972417,2.446035e-7,0.003244566,0.00004715756,0.00001639035,0.1989195,0.0004852721,0.0000235776,0.00002162028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3369063,"threshold_uncertainty_score":0.4614706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02054970210523239,"score_gpt":0.3394443280753363,"score_spread":0.3188946259701039,"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."}}