{"id":"W4410716781","doi":"10.1101/2025.05.19.654848","title":"upsAI: A high-accuracy machine learning classifier for predicting <i>Plasmodium falciparum var</i> gene upstream groups","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity","funders":"Région Occitanie Pyrénées-Méditerranée; Agence Nationale de la Recherche; Université de Montpellier; Wellcome Trust","keywords":"Plasmodium falciparum; Classifier (UML); Upstream (networking); Artificial intelligence; Computer science; Machine learning; Computational biology; Biology; Malaria; Immunology; Computer network","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001068734,0.00107486,0.000894052,0.000307099,0.000524106,0.0003169928,0.0011434,0.001388469,0.00002678898],"category_scores_gemma":[0.001866424,0.001169492,0.0004444011,0.0003468682,0.0001597952,0.00002612931,0.001677001,0.001621926,0.00002241723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001736751,"about_ca_system_score_gemma":0.0007887048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00010487,"about_ca_topic_score_gemma":0.000009835553,"domain_scores_codex":[0.9955828,0.0002589659,0.00112976,0.001484391,0.0004496302,0.001094487],"domain_scores_gemma":[0.9959449,0.0001816683,0.00110916,0.001804235,0.0006239453,0.0003360789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005717764,0.0004079069,0.05498481,0.002971369,0.001473323,0.00002263077,0.00005832196,0.0128881,0.9222128,0.001052882,0.00330511,0.00005093577],"study_design_scores_gemma":[0.003225933,0.0006961065,0.008928268,0.0008001664,0.00067049,3.210529e-7,0.00001508484,0.05229317,0.7716461,0.00001171834,0.1589332,0.002779523],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9113474,0.00196473,0.07662193,0.0004938415,0.003420728,0.002629158,0.002624396,0.0007194552,0.0001783394],"genre_scores_gemma":[0.9563413,0.0005887549,0.03988298,0.000546513,0.001386152,0.0007013269,0.00007665518,0.0002345159,0.000241839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1556281,"threshold_uncertainty_score":0.9999079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00967620302088911,"score_gpt":0.2321083804290883,"score_spread":0.2224321774081992,"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."}}