{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:29Z","timestamp":1772138069079,"version":"3.50.1"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,6,15]],"date-time":"2024-06-15T00:00:00Z","timestamp":1718409600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UCLA-Caltech Medical Scientist Training Program","award":["T32 GM008042"],"award-info":[{"award-number":["T32 GM008042"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U19MH114830"],"award-info":[{"award-number":["U19MH114830"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5UM1HG012077-02"],"award-info":[{"award-number":["5UM1HG012077-02"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Next-generation sequencing libraries are constructed with numerous synthetic constructs such as sequencing adapters, barcodes, and unique molecular identifiers. Such sequences can be essential for interpreting results of sequencing assays, and when they contain information pertinent to an experiment, they must be processed and analyzed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present a tool called splitcode, that enables flexible and efficient parsing, interpreting, and editing of sequencing reads. This versatile tool facilitates simple, reproducible preprocessing of reads from libraries constructed for a large array of single-cell and bulk sequencing assays.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The splitcode program is available at http:\/\/github.com\/pachterlab\/splitcode.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae331","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T03:40:35Z","timestamp":1718250035000},"source":"Crossref","is-referenced-by-count":6,"title":["Flexible parsing, interpretation, and editing of technical sequences with\n                    <i>splitcode<\/i>"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8359-6705","authenticated-orcid":false,"given":"Delaney K","family":"Sullivan","sequence":"first","affiliation":[{"name":"UCLA-Caltech Medical Scientist Training Program, David Geffen School of Medicine, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Division of Biology and Biological Engineering, California Institute of Technology , Pasadena, CA 91125, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9164-6231","authenticated-orcid":false,"given":"Lior","family":"Pachter","sequence":"additional","affiliation":[{"name":"Division of Biology and Biological Engineering, California Institute of Technology , Pasadena, CA 91125, United States"},{"name":"Department of Computing and Mathematical Sciences, California Institute of Technology , Pasadena, CA 91125, United States"}]}],"member":"286","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"key":"2024062208565203100_btae331-B1","doi-asserted-by":"crossref","first-page":"6847","DOI":"10.1038\/s41467-022-34681-z","article-title":"A flexible cross-platform single-cell data processing pipeline","volume":"13","author":"Battenberg","year":"2022","journal-title":"Nat Commun"},{"key":"2024062208565203100_btae331-B2","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","article-title":"Trimmomatic: a flexible trimmer for Illumina sequence data","volume":"30","author":"Bolger","year":"2014","journal-title":"Bioinformatics"},{"key":"2024062208565203100_btae331-B3","doi-asserted-by":"crossref","first-page":"btae168","DOI":"10.1093\/bioinformatics\/btae168","article-title":"A machine-readable specification for genomics assays","volume":"40","author":"Booeshaghi","year":"2024","journal-title":"Bioinformatics"},{"key":"2024062208565203100_btae331-B4","doi-asserted-by":"crossref","first-page":"e0185056","DOI":"10.1371\/journal.pone.0185056","article-title":"BBMerge\u2014accurate paired shotgun read merging via overlap","volume":"12","author":"Bushnell","year":"2017","journal-title":"PLoS One"},{"key":"2024062208565203100_btae331-B5","doi-asserted-by":"crossref","first-page":"i884","DOI":"10.1093\/bioinformatics\/bty560","article-title":"fastp: an ultra-fast all-in-one FASTQ preprocessor","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2024062208565203100_btae331-B6","doi-asserted-by":"crossref","first-page":"btae102","DOI":"10.1093\/bioinformatics\/btae102","article-title":"Flexiplex: a versatile demultiplexer and search tool for omics data","volume":"40","author":"Cheng","year":"2024","journal-title":"Bioinformatics"},{"key":"2024062208565203100_btae331-B7","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1038\/s41587-020-0497-0","article-title":"Single-cell RNA counting at allele and isoform resolution using Smart-seq3","volume":"38","author":"Hagemann-Jensen","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2024062208565203100_btae331-B8","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00239-022-10083-z","article-title":"Best practices in designing, sequencing, and identifying random DNA barcodes","volume":"91","author":"Johnson","year":"2023","journal-title":"J Mol Evol"},{"key":"2024062208565203100_btae331-B9","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1038\/s41592-018-0185-x","article-title":"Cellular barcoding: lineage tracing, screening and beyond","volume":"15","author":"Kebschull","year":"2018","journal-title":"Nat Methods"},{"key":"2024062208565203100_btae331-B10","doi-asserted-by":"crossref","first-page":"eadd2793","DOI":"10.1126\/sciadv.add2793","article-title":"A universal sequencing read interpreter","volume":"9","author":"Kijima","year":"2023","journal-title":"Sci Adv"},{"key":"2024062208565203100_btae331-B11","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/nmeth.1778","article-title":"Counting absolute numbers of molecules using unique molecular identifiers","volume":"9","author":"Kivioja","year":"2011","journal-title":"Nat Methods"},{"key":"2024062208565203100_btae331-B12","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.ygeno.2011.05.009","article-title":"Btrim: a fast, lightweight adapter and quality trimming program for next-generation sequencing technologies","volume":"98","author":"Kong","year":"2011","journal-title":"Genomics"},{"key":"2024062208565203100_btae331-B13","doi-asserted-by":"crossref","first-page":"e7170","DOI":"10.7717\/peerj.7170","article-title":"Fuzzysplit: demultiplexing and trimming sequenced DNA with a declarative language","volume":"7","author":"Liu","year":"2019","journal-title":"PeerJ"},{"key":"2024062208565203100_btae331-B14","doi-asserted-by":"crossref","first-page":"10","DOI":"10.14806\/ej.17.1.200","article-title":"Cutadapt removes adapter sequences from high-throughput sequencing reads","volume":"17","author":"Martin","year":"2011","journal-title":"EMBnet J"},{"key":"2024062208565203100_btae331-B15","doi-asserted-by":"crossref","first-page":"4472","DOI":"10.1093\/bioinformatics\/btz279","article-title":"The barcode, UMI, set format and BUStools","volume":"35","author":"Melsted","year":"2019","journal-title":"Bioinformatics"},{"key":"2024062208565203100_btae331-B16","doi-asserted-by":"crossref","first-page":"giy059","DOI":"10.1093\/gigascience\/giy059","article-title":"zUMIs\u2014a fast and flexible pipeline to process RNA sequencing data with UMIs","volume":"7","author":"Parekh","year":"2018","journal-title":"Gigascience"},{"key":"2024062208565203100_btae331-B17","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1038\/s41596-021-00633-y","article-title":"SPRITE: a genome-wide method for mapping higher-order 3D interactions in the nucleus using combinatorial split-and-pool barcoding","volume":"17","author":"Quinodoz","year":"2022","journal-title":"Nat Protoc"},{"key":"2024062208565203100_btae331-B18","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.cell.2018.05.024","article-title":"Higher-order inter-chromosomal hubs shape 3D genome organization in the nucleus","volume":"174","author":"Quinodoz","year":"2018","journal-title":"Cell"},{"key":"2024062208565203100_btae331-B19","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1186\/s13059-021-02505-w","article-title":"Mapping and modeling the genomic basis of differential RNA isoform expression at single-cell resolution with LR-Split-seq","volume":"22","author":"Rebboah","year":"2021","journal-title":"Genome Biol"},{"key":"2024062208565203100_btae331-B20","doi-asserted-by":"crossref","first-page":"2941","DOI":"10.1093\/bioinformatics\/btx330","article-title":"Flexbar 3.0 \u2013 SIMD and multicore parallelization","volume":"33","author":"Roehr","year":"2017","journal-title":"Bioinformatics"},{"key":"2024062208565203100_btae331-B21","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1126\/science.aam8999","article-title":"Single-cell profiling of the developing mouse brain and spinal cord with split-Pool barcoding","volume":"360","author":"Rosenberg","year":"2018","journal-title":"Science"},{"key":"2024062208565203100_btae331-B22","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1101\/gr.209601.116","article-title":"UMI-tools: modeling sequencing errors in unique molecular identifiers to improve quantification accuracy","volume":"27","author":"Smith","year":"2017","journal-title":"Genome Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae331\/58238094\/btae331.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/6\/btae331\/58304662\/btae331.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/6\/btae331\/58304662\/btae331.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T04:57:12Z","timestamp":1719032232000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae331\/7693695"}},"subtitle":[],"editor":[{"given":"Can","family":"Alkan","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":22,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae331","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.03.20.533521","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,6]]},"published":{"date-parts":[[2024,6]]},"article-number":"btae331"}}