{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:13:00Z","timestamp":1791353580024,"version":"4.3.1"},"posted":{"date-parts":[[2025,12,12]]},"group-title":"Bioinformatics","reference-count":40,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health usa","doi-asserted-by":"crossref","award":["K24AI144048"],"award-info":[{"award-number":["K24AI144048"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health usa","doi-asserted-by":"crossref","award":["U01AI184646"],"award-info":[{"award-number":["U01AI184646"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health usa","doi-asserted-by":"crossref","award":["R01AI156267"],"award-info":[{"award-number":["R01AI156267"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health usa","doi-asserted-by":"crossref","award":["K23AI166009"],"award-info":[{"award-number":["K23AI166009"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"award":["INV-081860"],"award-info":[{"award-number":["INV-081860"]}],"id":[{"id":"https:\/\/ror.org\/0456r8d26","id-type":"ROR","asserted-by":"publisher"}]},{"award":["INV-009416"],"award-info":[{"award-number":["INV-009416"]}],"id":[{"id":"https:\/\/ror.org\/0456r8d26","id-type":"ROR","asserted-by":"publisher"}]},{"award":["INV-043618"],"award-info":[{"award-number":["INV-043618"]}],"id":[{"id":"https:\/\/ror.org\/0456r8d26","id-type":"ROR","asserted-by":"publisher"}]},{"award":["INV-067310"],"award-info":[{"award-number":["INV-067310"]}],"id":[{"id":"https:\/\/ror.org\/0456r8d26","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,6]]},"abstract":"<jats:sec>\n                  <jats:title>Structured Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The rapid increase in the generation of targeted sequencing data offers immense potential for research, medicine, and public health, however the lack of an established standard for these data has led to disparate solutions for data storage. A widely accepted standard is essential for data sharing, reuse, and the coordinated development of interoperable analysis tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      We propose the Portable Microhaplotype Object (PMO), a standardized format for efficiently and losslessly storing phased targeted sequencing data (microhaplotypes). The PMO format is JSON-based, allowing efficient, relational storage of genetic data together with relevant metadata to minimize orphaned data. The format includes required fields and a curated set of optional fields leveraging established ontologies. To facilitate ease of use, we developed pmotools-python, an open-source package for creating, manipulating, and exporting PMO data into common formats. Additionally, we provide a simple web-based app to quickly create PMO files from tabular inputs, making the format accessible to a wide variety of users. Example datasets from\n                      <jats:italic>Plasmodium, Anopheles, Escherichia coli<\/jats:italic>\n                      , and\n                      <jats:italic>Staphylococcus aureus<\/jats:italic>\n                      demonstrate the broad applicability of the approach. PMO will streamline data sharing, foster interoperability, and accelerate the development of harmonized analysis tools.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>\n                      The Portable Microhaplotype Object (PMO) project, including the ontology specification, software tools, example datasets, and tutorials, is freely available at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/plasmogenepi.github.io\/PMO_Docs\/\">https:\/\/plasmogenepi.github.io\/PMO_Docs\/<\/jats:ext-link>\n                      . Key software components and datasets have archived releases with DOIs to ensure permanence, detailed in the Supplementary Text 1-5.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Contact<\/jats:title>\n                    <jats:p>\n                      <jats:email>kathrynmmurie@gmail.com<\/jats:email>\n                      or\n                      <jats:email>nickjhathaway@gmail.com<\/jats:email>\n                    <\/jats:p>\n                  <\/jats:sec>\n                <\/jats:sec>","DOI":"10.64898\/2025.12.10.693568","type":"posted-content","created":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T07:10:23Z","timestamp":1765609823000},"source":"Crossref","is-referenced-by-count":1,"title":["The Portable Microhaplotype Object and Tools"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-2894","authenticated-orcid":false,"given":"Nicholas J.","family":"Hathaway","sequence":"first","affiliation":[{"name":"EPPIcenter program, Division of HIV, ID, and Global Medicine, University of California, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9612-2016","authenticated-orcid":false,"given":"Kathryn","family":"Murie","sequence":"additional","affiliation":[{"name":"EPPIcenter program, Division of HIV, ID, and Global Medicine, University of California, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0332-4388","authenticated-orcid":false,"given":"Maxwell","family":"Murphy","sequence":"additional","affiliation":[{"name":"EPPIcenter program, Division of HIV, ID, and Global Medicine, University of California, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9408-0053","authenticated-orcid":false,"given":"Alfred","family":"Simkin","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Brown University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge","family":"Amaya-Romero","sequence":"additional","affiliation":[{"name":"Department of Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health, Harvard University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4917-7272","authenticated-orcid":false,"given":"Alfred","family":"Hubbard","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8078-3898","authenticated-orcid":false,"given":"Jessica","family":"Briggs","sequence":"additional","affiliation":[{"name":"EPPIcenter program, Division of HIV, ID, and Global Medicine, University of California, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0566-4901","authenticated-orcid":false,"given":"Andr\u00e9s","family":"Aranda-D\u00edaz","sequence":"additional","affiliation":[{"name":"EPPIcenter program, Division of HIV, ID, and Global Medicine, University of California, San Francisco, USA"},{"name":"ISGlobal, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3169-2324","authenticated-orcid":false,"given":"Angela M.","family":"Early","sequence":"additional","affiliation":[{"name":"Infectious Disease and Microbiome Program, Broad Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6320-3575","authenticated-orcid":false,"given":"Amy","family":"Wesolowski","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1665-9323","authenticated-orcid":false,"given":"Daniel E.","family":"Neafsey","sequence":"additional","affiliation":[{"name":"Department of Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health, Harvard University, USA"},{"name":"Infectious Disease and Microbiome Program, Broad Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6899-8204","authenticated-orcid":false,"given":"Jeffrey A.","family":"Bailey","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Brown University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0287-9111","authenticated-orcid":false,"given":"Bryan","family":"Greenhouse","sequence":"additional","affiliation":[{"name":"EPPIcenter program, Division of HIV, ID, and Global Medicine, University of California, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026070906251719000_2025.12.10.693568v2.1","doi-asserted-by":"publisher","DOI":"10.4269\/ajtmh.25-0110"},{"key":"2026070906251719000_2025.12.10.693568v2.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-94716-5"},{"key":"2026070906251719000_2025.12.10.693568v2.3","doi-asserted-by":"publisher","DOI":"10.1111\/1755-0998.12737"},{"key":"2026070906251719000_2025.12.10.693568v2.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2019.10.004"},{"key":"2026070906251719000_2025.12.10.693568v2.5","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-025-01008-0"},{"key":"2026070906251719000_2025.12.10.693568v2.6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3002151"},{"key":"2026070906251719000_2025.12.10.693568v2.7","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr330"},{"key":"2026070906251719000_2025.12.10.693568v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.pt.2024.10.005"},{"key":"2026070906251719000_2025.12.10.693568v2.9","doi-asserted-by":"publisher","DOI":"10.1101\/2025.01.09.25320247"},{"key":"2026070906251719000_2025.12.10.693568v2.10","doi-asserted-by":"publisher","DOI":"10.1099\/mgen.0.001427"},{"key":"2026070906251719000_2025.12.10.693568v2.11","doi-asserted-by":"publisher","DOI":"10.1093\/genetics\/iyac126"},{"key":"2026070906251719000_2025.12.10.693568v2.12","doi-asserted-by":"publisher","DOI":"10.1186\/s12936-019-2944-2"},{"key":"2026070906251719000_2025.12.10.693568v2.13","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1201"},{"key":"2026070906251719000_2025.12.10.693568v2.14","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(17)32130-x"},{"key":"2026070906251719000_2025.12.10.693568v2.15","doi-asserted-by":"publisher","DOI":"10.1186\/s12896-023-00804-7"},{"key":"2026070906251719000_2025.12.10.693568v2.16","doi-asserted-by":"publisher","DOI":"10.1111\/eva.13613"},{"key":"2026070906251719000_2025.12.10.693568v2.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05049-6"},{"key":"2026070906251719000_2025.12.10.693568v2.18","doi-asserted-by":"publisher","DOI":"10.1186\/s12936-025-05441-3"},{"key":"2026070906251719000_2025.12.10.693568v2.19","doi-asserted-by":"publisher","DOI":"10.1186\/s12936-025-05441-3"},{"key":"2026070906251719000_2025.12.10.693568v2.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62357-x"},{"key":"2026070906251719000_2025.12.10.693568v2.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsigen.2024.103096"},{"key":"2026070906251719000_2025.12.10.693568v2.22","doi-asserted-by":"publisher","DOI":"10.1111\/1755-0998.13622"},{"key":"2026070906251719000_2025.12.10.693568v2.23","unstructured":"linkml\/linkml: Linked Open Data Modeling Language. n.d. https:\/\/github.com\/linkml\/linkml (4 Sept. 2025, date last accessed)."},{"key":"2026070906251719000_2025.12.10.693568v2.24","doi-asserted-by":"publisher","DOI":"10.1111\/1755-0998.13436"},{"key":"2026070906251719000_2025.12.10.693568v2.25","doi-asserted-by":"publisher","DOI":"10.1186\/2047-217X-1-7"},{"key":"2026070906251719000_2025.12.10.693568v2.26","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae619"},{"key":"2026070906251719000_2025.12.10.693568v2.27","doi-asserted-by":"publisher","DOI":"10.1101\/2025.07.30.25332463"},{"key":"2026070906251719000_2025.12.10.693568v2.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsigen.2018.09.009"},{"key":"2026070906251719000_2025.12.10.693568v2.29","doi-asserted-by":"publisher","DOI":"10.1038\/ejhg.2012.69"},{"key":"2026070906251719000_2025.12.10.693568v2.30","doi-asserted-by":"publisher","DOI":"10.1128\/mSystems.00190-20"},{"key":"2026070906251719000_2025.12.10.693568v2.31","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.71273"},{"key":"2026070906251719000_2025.12.10.693568v2.32","unstructured":"PlasmoGenEpi\/PGEcore: Core set of scripts to perform common downstream analysis functionalities for Plasmodium. Includes wrappers of tools and bespoke code to perform common tasks. n.d. https:\/\/github.com\/PlasmoGenEpi\/PGEcore (21 Nov. 2025, date last accessed)."},{"key":"2026070906251719000_2025.12.10.693568v2.33","doi-asserted-by":"publisher","DOI":"10.1101\/2025.03.31.25324948"},{"key":"2026070906251719000_2025.12.10.693568v2.34","doi-asserted-by":"publisher","DOI":"10.1101\/2025.04.01.25325032"},{"key":"2026070906251719000_2025.12.10.693568v2.35","doi-asserted-by":"publisher","DOI":"10.1093\/infdis\/jiaa527"},{"key":"2026070906251719000_2025.12.10.693568v2.36","doi-asserted-by":"publisher","DOI":"10.1093\/g3journal\/jkae280"},{"key":"2026070906251719000_2025.12.10.693568v2.37","doi-asserted-by":"publisher","DOI":"10.15485\/1734840"},{"key":"2026070906251719000_2025.12.10.693568v2.38","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18"},{"key":"2026070906251719000_2025.12.10.693568v2.39","doi-asserted-by":"publisher","DOI":"10.1128\/spectrum.04139-23"},{"key":"2026070906251719000_2025.12.10.693568v2.40","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.1823"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2025.12.10.693568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:25:27Z","timestamp":1783603527000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2025.12.10.693568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":40,"URL":"https:\/\/doi.org\/10.64898\/2025.12.10.693568","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"subtype":"preprint"}}