{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:19:25Z","timestamp":1785421165328,"version":"3.56.0"},"posted":{"date-parts":[[2026,7,22]]},"group-title":"Bioinformatics","reference-count":23,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"award":["R35GM128625"],"award-info":[{"award-number":["R35GM128625"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Mapping protein regions to genomic coordinates underpins the study of exon architecture and the interpretation of clinical variants in their exon context. Existing tools resolve individual queries accurately but scale poorly to proteome-wide analyses. We present fastCDS, a C++ toolkit with command line and Python interfaces for rapid protein-to-genome coordinate mapping from GTF annotations. It matches the accuracy of existing methods while running at least two to three orders of magnitude faster. Mapping all human Pfam domains in seconds, we used the resulting atlas to examine how exonic architecture varies with domain function.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>\n                    fastCDS is freely available under the MIT license at {{\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/SotoLF\/fastCDS\">https:\/\/github.com\/SotoLF\/fastCDS<\/jats:ext-link>\n                    }} and can be installed with pip install fastCDS or mamba install -c bioconda fastCDS. Pre-built GTF genome indices are archived at Zenodo, DOI:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/zenodo.org\/records\/21436146\">https:\/\/zenodo.org\/records\/21436146<\/jats:ext-link>\n                    .\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Contact<\/jats:title>\n                  <jats:p>\n                    <jats:email>lsoto@rockefeller.edu<\/jats:email>\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Supplementary Information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.07.18.739381","type":"posted-content","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T04:40:12Z","timestamp":1784781612000},"source":"Crossref","is-referenced-by-count":0,"title":["fastCDS: proteome-scale mapping of protein domains to genomic coordinates"],"prefix":"10.64898","author":[{"given":"G.","family":"Mu\u00f1oz-Esquivel","sequence":"first","affiliation":[{"name":"Escuela Profesional de Gen\u00e9tica y Biotecnolog\u00eda, Facultad de Ciencias Biol\u00f3gicas, Universidad Nacional Mayor de San Marcos, Lima 15081, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. I.","family":"Fuxman Bass","sequence":"additional","affiliation":[{"name":"Boston University, Biology Department, Boston, MA, 02215, USA"},{"name":"Bioinformatics Program, Boston University, Boston, MA 02215, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L. F.","family":"Soto-Ugaldi","sequence":"additional","affiliation":[{"name":"Robin Chemers Neustein Laboratory of Mammalian Cell Biology and Development, Howard Hughes Medical Institute, The Rockefeller University, New York, NY 10065, USA"},{"name":"Tri-institutional Program, Computational Biology and Medicine, New York, NY 10065, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026072706212096000_2026.07.18.739381v1.1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1071"},{"key":"2026072706212096000_2026.07.18.739381v1.2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr367"},{"key":"2026072706212096000_2026.07.18.739381v1.3","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1038"},{"key":"2026072706212096000_2026.07.18.739381v1.4","doi-asserted-by":"publisher","DOI":"10.1101\/2022.11.08.513416"},{"key":"2026072706212096000_2026.07.18.739381v1.5","doi-asserted-by":"publisher","DOI":"10.1101\/gr.229102. Article published online before print in May 2002"},{"key":"2026072706212096000_2026.07.18.739381v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1153"},{"key":"2026072706212096000_2026.07.18.739381v1.7","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkt1113"},{"key":"2026072706212096000_2026.07.18.739381v1.8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003118"},{"key":"2026072706212096000_2026.07.18.739381v1.9","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg668"},{"key":"2026072706212096000_2026.07.18.739381v1.10","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gki858"},{"key":"2026072706212096000_2026.07.18.739381v1.11","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa913"},{"key":"2026072706212096000_2026.07.18.739381v1.12","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1078"},{"key":"2026072706212096000_2026.07.18.739381v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-1119(99)00228-0"},{"key":"2026072706212096000_2026.07.18.739381v1.14","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac993"},{"key":"2026072706212096000_2026.07.18.739381v1.15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq033"},{"key":"2026072706212096000_2026.07.18.739381v1.16","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz031"},{"key":"2026072706212096000_2026.07.18.739381v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.1754"},{"key":"2026072706212096000_2026.07.18.739381v1.18","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1015"},{"key":"2026072706212096000_2026.07.18.739381v1.19","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1010"},{"key":"2026072706212096000_2026.07.18.739381v1.20","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab1061"},{"key":"2026072706212096000_2026.07.18.739381v1.21","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-022-08713-3"},{"key":"2026072706212096000_2026.07.18.739381v1.22","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu613"},{"key":"2026072706212096000_2026.07.18.739381v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3622"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.07.18.739381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T13:21:35Z","timestamp":1785158495000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.07.18.739381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.64898\/2026.07.18.739381","relation":{},"subject":[],"published":{"date-parts":[[2026,7,22]]},"subtype":"preprint"}}