{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T13:11:18Z","timestamp":1791983478984,"version":"4.4.0"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":[": 104111\/Z\/14\/Z & A"],"award-info":[{"award-number":[": 104111\/Z\/14\/Z & A"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-21-EXES-0005"],"award-info":[{"award-number":["ANR-21-EXES-0005"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010434","name":"'la Caixa' Foundation","doi-asserted-by":"publisher","award":["HR20-00635"],"award-info":[{"award-number":["HR20-00635"]}],"id":[{"id":"10.13039\/100010434","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002915","name":"Fondation pour la Recherche M\u00c3\u00a9dicale","doi-asserted-by":"publisher","award":["ANR 18\u2010CE15\u20100009\u201001"],"award-info":[{"award-number":["ANR 18\u2010CE15\u20100009\u201001"]}],"id":[{"id":"10.13039\/501100002915","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Service Programme d'Excellence I-Site, MUSE Pre-ERC, MOTIVATOR","award":["EQU202303016290"],"award-info":[{"award-number":["EQU202303016290"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    <jats:italic>Plasmodium falciparum<\/jats:italic>\n                    erythrocyte membrane protein 1 (\n                    <jats:italic>Pf<\/jats:italic>\n                    EMP1), encoded by the hypervariable\n                    <jats:italic>var<\/jats:italic>\n                    gene family, is central to malaria pathogenesis, influencing both disease severity and immune evasion. Classifying\n                    <jats:italic>var<\/jats:italic>\n                    genes into upstream groups (upsA, upsB, upsC, upsE) is important for understanding parasite biology and clinical outcomes, but remains challenging, especially with partial sequences, such as the DBL\u03b1 tag or RNA-Seq assemblies. We developed upsML, a machine-learning-based classifier trained on 2,530 curated\n                    <jats:italic>var<\/jats:italic>\n                    genes, to accurately assign upstream groups based on sequence features from different partial gene regions. We compared seven methods, including support vector machines, random forests, XGBoost, and HMMER models. Several models in upsML achieve accuracies of 83% for DBL\u03b1-tag sequences and 92% for full-length\n                    <jats:italic>Pf<\/jats:italic>\n                    EMP1 sequences, thereby significantly outperforming existing tools. Additionally, we developed a model to distinguish internal from subtelomeric\n                    <jats:italic>var<\/jats:italic>\n                    genes, which we applied to a global collection of\n                    <jats:italic>P. falciparum<\/jats:italic>\n                    genomes, revealing a higher frequency of internal\n                    <jats:italic>var<\/jats:italic>\n                    genes in Asia. upsML is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/sii-scRNA-Seq\/upsML\" xlink:type=\"simple\">https:\/\/github.com\/sii-scRNA-Seq\/upsML<\/jats:ext-link>\n                    , providing a robust and efficient resource for large-scale\n                    <jats:italic>var<\/jats:italic>\n                    gene analysis. It can classify\n                    <jats:italic>var<\/jats:italic>\n                    genes from 20 genomes in under one second.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0344557","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T17:47:27Z","timestamp":1776361647000},"page":"e0344557","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["upsML: A high-accuracy machine learning classifier for predicting Plasmodium falciparum var gene upstream groups"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7434-0139","authenticated-orcid":true,"given":"Elcid Aaron","family":"Pangilinan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Quenu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine","family":"Claessens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-7404","authenticated-orcid":true,"given":"Thomas D.","family":"Otto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"issue":"1","key":"pone.0344557.ref001","doi-asserted-by":"crossref","DOI":"10.1128\/mmbr.00114-23","article-title":"Variable surface antigen expression, virulence, and persistent infection by Plasmodium falciparum malaria parasites","volume":"89","author":"E Hadjimichael","year":"2025","journal-title":"Microbiol Mol Biol Rev"},{"key":"pone.0344557.ref002","doi-asserted-by":"crossref","first-page":"102231","DOI":"10.1016\/j.mib.2022.102231","article-title":"The mystery of persistent, asymptomatic Plasmodium falciparum infections","volume":"70","author":"X Zhang","year":"2022","journal-title":"Curr Opin Microbiol"},{"key":"pone.0344557.ref003","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/1475-2875-2-27","article-title":"Sub-grouping of Plasmodium falciparum 3D7 var genes based on sequence analysis of coding and non-coding regions","volume":"2","author":"T Lavstsen","year":"2003","journal-title":"Malar J"},{"issue":"9","key":"pone.0344557.ref004","article-title":"Plasmodium falciparum erythrocyte membrane protein 1 diversity in seven genomes--divide and conquer","volume":"6","author":"TS Rask","year":"2010","journal-title":"PLoS Comput Biol"},{"issue":"26","key":"pone.0344557.ref005","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.1120455109","article-title":"Plasmodium falciparum erythrocyte membrane protein 1 domain cassettes 8 and 13 are associated with severe malaria in children","volume":"109","author":"T Lavstsen","year":"2012","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"26","key":"pone.0344557.ref006","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.1120461109","article-title":"A subset of group A-like var genes encodes the malaria parasite ligands for binding to human brain endothelial cells","volume":"109","author":"A Claessens","year":"2012","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"3","key":"pone.0344557.ref007","article-title":"The Plasmodium falciparum transcriptome in severe malaria reveals altered expression of genes involved in important processes including surface antigen-encoding var genes","volume":"16","author":"GQ Tonkin-Hill","year":"2018","journal-title":"PLoS Biol"},{"issue":"129","key":"pone.0344557.ref008","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.3003247","article-title":"Prognostic indicators of life-threatening malaria are associated with distinct parasite variant antigen profiles","volume":"4","author":"GM Warimwe","year":"2012","journal-title":"Sci Transl Med"},{"issue":"1","key":"pone.0344557.ref009","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1046\/j.1365-2958.2003.03570.x","article-title":"Selective upregulation of a single distinctly structured var gene in chondroitin sulphate A-adhering Plasmodium falciparum involved in pregnancy-associated malaria","volume":"49","author":"A Salanti","year":"2003","journal-title":"Mol Microbiol"},{"issue":"2","key":"pone.0344557.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgen.1009269","article-title":"Evolutionary analyses of the major variant surface antigen-encoding genes reveal population structure of Plasmodium falciparum within and between continents","volume":"17","author":"G Tonkin-Hill","year":"2021","journal-title":"PLoS Genet"},{"issue":"12","key":"pone.0344557.ref011","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgen.1004812","article-title":"Generation of antigenic diversity in Plasmodium falciparum by structured rearrangement of Var genes during mitosis","volume":"10","author":"A Claessens","year":"2014","journal-title":"PLoS Genet"},{"key":"pone.0344557.ref012","doi-asserted-by":"crossref","first-page":"1006341","DOI":"10.3389\/fpara.2022.1006341","article-title":"Unravelling var complexity: Relationship between DBL\u03b1 types and var genes in Plasmodium falciparum","volume":"1","author":"MH Tan","year":"2022","journal-title":"Front Parasitol"},{"key":"pone.0344557.ref013","article-title":"A paradoxical population structure of var DBLalpha types in Africa","author":"MH Tan","year":"2023","journal-title":"bioRxiv"},{"issue":"2","key":"pone.0344557.ref014","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1009715923555","article-title":"A Tutorial on Support Vector Machines for Pattern Recognition","volume":"2","author":"CJC Burges","year":"1998","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"1","key":"pone.0344557.ref015","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"pone.0344557.ref016","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System","author":"T Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA"},{"key":"pone.0344557.ref017","article-title":"De novo assembly of complete Plasmodium falciparum isolate genomes using PacBio HiFi sequencing technology","author":"PB Nyarko","year":"2025","journal-title":"bioRxiv"},{"key":"pone.0344557.ref018","doi-asserted-by":"crossref","first-page":"325","DOI":"10.12688\/wellcomeopenres.24031.1","article-title":"Pf8: an open dataset of Plasmodium falciparum genome variation in 33,325 worldwide samples","volume":"10","author":"MM Abdel Hamid","year":"2025","journal-title":"Wellcome Open Res"},{"key":"pone.0344557.ref019","article-title":"Elife","volume":"12","author":"C Andradi-Brown","year":"2024","journal-title":"Elife"},{"issue":"193","key":"pone.0344557.ref020","article-title":"Evolutionary analysis of the most polymorphic gene family in falciparum malaria","volume":"4","author":"TD Otto","year":"2019","journal-title":"Wellcome Open Res"},{"issue":"4","key":"pone.0344557.ref021","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1093\/nar\/gkt1174","article-title":"DNA secondary structures are associated with recombination in major Plasmodium falciparum variable surface antigen gene families","volume":"42","author":"AF Sander","year":"2014","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"pone.0344557.ref022","article-title":"Mitotic evolution of Plasmodium falciparum shows a stable core genome but recombination in antigen families","volume":"9","author":"SER Bopp","year":"2013","journal-title":"PLoS Genet"},{"issue":"6","key":"pone.0344557.ref023","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1111\/j.1365-2958.2008.06248.x","article-title":"Plasmodium falciparum antigenic variation. Mapping mosaic var gene sequences onto a network of shared, highly polymorphic sequence blocks","volume":"68","author":"PC Bull","year":"2008","journal-title":"Mol Microbiol"},{"key":"pone.0344557.ref024","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1186\/1471-2148-13-110","article-title":"Hypervariable antigen genes in malaria have ancient roots","volume":"13","author":"MM Zilversmit","year":"2013","journal-title":"BMC Evol Biol"},{"key":"pone.0344557.ref025","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.01074","article-title":"The antigenic switching network of Plasmodium falciparum and its implications for the immuno-epidemiology of malaria","volume":"2","author":"R Noble","year":"2013","journal-title":"Elife"},{"issue":"4","key":"pone.0344557.ref026","volume":"24","author":"JL Ruiz","year":"2023","journal-title":"Briefings in bioinformatics"},{"key":"pone.0344557.ref027","doi-asserted-by":"crossref","first-page":"52","DOI":"10.12688\/wellcomeopenres.14571.1","article-title":"Long read assemblies of geographically dispersed Plasmodium falciparum isolates reveal highly structured subtelomeres","volume":"3","author":"TD Otto","year":"2018","journal-title":"Wellcome Open Res"},{"issue":"1","key":"pone.0344557.ref028","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s13073-019-0708-9","article-title":"Strains used in whole organism Plasmodium falciparum vaccine trials differ in genome structure, sequence, and immunogenic potential","volume":"12","author":"KA Moser","year":"2020","journal-title":"Genome Med"},{"key":"pone.0344557.ref029","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkl200","article-title":"AUGUSTUS: ab initio prediction of alternative transcripts","volume":"34","author":"M Stanke","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"pone.0344557.ref030","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkae378","article-title":"Annotation and visualization of parasite, fungi and arthropod genomes with Companion","volume":"52","author":"W Haese-Hill","year":"2024","journal-title":"Nucleic Acids Res"},{"issue":"16","key":"pone.0344557.ref031","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The Sequence Alignment\/Map format and SAMtools","volume":"25","author":"H Li","year":"2009","journal-title":"Bioinformatics"},{"key":"pone.0344557.ref032","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1186\/1471-2105-10-421","article-title":"BLAST+: architecture and applications","volume":"10","author":"C Camacho","year":"2009","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"pone.0344557.ref033","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT multiple sequence alignment software version 7: improvements in performance and usability","volume":"30","author":"K Katoh","year":"2013","journal-title":"Mol Biol Evol"},{"issue":"3","key":"pone.0344557.ref034","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0009490","article-title":"FastTree 2--approximately maximum-likelihood trees for large alignments","volume":"5","author":"MN Price","year":"2010","journal-title":"PLoS One"},{"issue":"23","key":"pone.0344557.ref035","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"L Fu","year":"2012","journal-title":"Bioinformatics"},{"issue":"1","key":"pone.0344557.ref036","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/S0166-6851(99)00159-0","article-title":"A study of var gene transcription in vitro using universal var gene primers","volume":"105","author":"HM Taylor","year":"2000","journal-title":"Mol Biochem Parasitol"},{"key":"pone.0344557.ref037","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pone.0344557.ref038","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An introduction to support vector machines and other kernel-based learning methods","author":"N Cristianini","year":"2000"},{"key":"pone.0344557.ref039","doi-asserted-by":"crossref","first-page":"58","DOI":"10.12688\/wellcomeopenres.15194.1","article-title":"Progression of the canonical reference malaria parasite genome from 2002-2019","volume":"4","author":"U B\u00f6hme","year":"2019","journal-title":"Wellcome Open Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0344557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T17:47:36Z","timestamp":1776361656000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0344557"}},"subtitle":[],"editor":[{"given":"Kokouvi","family":"Kassegne","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":39,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0344557","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]}}}