{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T01:45:17Z","timestamp":1789695917273,"version":"4.0.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1205000"],"award-info":[{"award-number":["2023YFF1205000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42107148"],"award-info":[{"award-number":["42107148"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572442"],"award-info":[{"award-number":["62572442"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate reconstruction and quantification of full-length RNA isoforms remain challenging in long-read RNA sequencing due to sequencing artifacts, complex splicing, and incomplete annotations. Although Pacific Biosciences circular consensus sequencing (PacBio CCS) provides high-fidelity long reads, scalable and annotation-flexible analysis frameworks remain limited. Here, we present ISAtools, an efficient framework specifically designed for PacBio CCS data. ISAtools introduces a splice site chain representation that unifies read alignments and transcript annotations into a compact format for scalable isoform reconstruction. It further integrates unsupervised density-based clustering for transcription start and end site detection and a truncation-aware quantification strategy. Benchmarking on simulated, SIRV spike-in controls, and biological datasets shows that ISAtools accurately reconstructs both annotated and novel isoforms with reliable splice structures and transcript boundaries while maintaining high computational efficiency. ISAtools processes up to 80 million reads in ~21\u00a0min using ~6\u00a0GB memory and scales to nearly 1 billion reads in under 4\u00a0h with ~8\u00a0GB memory, supporting large-scale PacBio Iso-Seq studies.<\/jats:p>","DOI":"10.1093\/bib\/bbag403","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:53:26Z","timestamp":1783684406000},"source":"Crossref","is-referenced-by-count":1,"title":["Efficient reconstruction of full-length RNA isoforms using ISAtools and large-scale PacBio circular consensus sequencing data"],"prefix":"10.1093","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0540-7036","authenticated-orcid":false,"given":"Hu","family":"Chen","sequence":"first","affiliation":[{"name":"College of Life Science and Medicine, Zhejiang Sci-Tech University , Second Street 928, Qiantang District, Hangzhou 310018 ,","place":["China"]},{"name":"State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases , No. 7 Jinsui Road, Tianhe District, Guangzhou 510060 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Life Science and Medicine, Zhejiang Sci-Tech University , Second Street 928, Qiantang District, Hangzhou 310018 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dai","sequence":"additional","affiliation":[{"name":"College of Life Science and Medicine, Zhejiang Sci-Tech University , Second Street 928, Qiantang District, Hangzhou 310018 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo-Xing","family":"Shi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases , No. 7 Jinsui Road, Tianhe District, Guangzhou 510060 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"2026080408220625100_ref1","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1038\/s41592-024-02298-3","article-title":"Systematic assessment of long-read RNA-seq methods for transcript identification and quantification","volume":"21","author":"Pardo-Palacios","year":"2024","journal-title":"Nat Methods"},{"key":"2026080408220625100_ref2","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1038\/nbt.2705","article-title":"A single-molecule long-read survey of the human transcriptome","volume":"31","author":"Sharon","year":"2013","journal-title":"Nat Biotechnol"},{"key":"2026080408220625100_ref3","doi-asserted-by":"publisher","first-page":"9869","DOI":"10.1073\/pnas.1400447111","article-title":"Defining a personal, allele-specific, and single-molecule long-read transcriptome","volume":"111","author":"Tilgner","year":"2014","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2026080408220625100_ref4","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1186\/s13059-019-1910-1","article-title":"Transcriptome assembly from long-read RNA-seq alignments with StringTie2","volume":"20","author":"Kovaka","year":"2019","journal-title":"Genome Biol"},{"key":"2026080408220625100_ref5","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1038\/s41467-020-15171-6","article-title":"Full-length transcript characterization of SF3B1 mutation in chronic lymphocytic leukemia reveals downregulation of retained introns","volume":"11","author":"Tang","year":"2020","journal-title":"Nat Commun"},{"key":"2026080408220625100_ref6","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s13059-020-1935-5","article-title":"Opportunities and challenges in long-read sequencing data analysis","volume":"21","author":"Amarasinghe","year":"2020","journal-title":"Genome Biol"},{"key":"2026080408220625100_ref7","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1038\/nrg.2018.5","article-title":"Genomics: next regeneration sequencing for reference genomes","volume":"19","author":"Burgess","year":"2018","journal-title":"Nat Rev Genet"},{"key":"2026080408220625100_ref8","doi-asserted-by":"publisher","first-page":"R234","DOI":"10.1093\/hmg\/ddy177","article-title":"Long reads: their purpose and place","volume":"27","author":"Pollard","year":"2018","journal-title":"Hum Mol Genet"},{"key":"2026080408220625100_ref9","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1101\/gr.222976.117","article-title":"SQANTI: extensive characterization of long-read transcript sequences for quality control in full-length transcriptome identification and quantification","volume":"28","author":"Tardaguila","year":"2018","journal-title":"Genome Res"},{"key":"2026080408220625100_ref10","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1101\/gr.10.4.483","article-title":"Genome annotation assessment in Drosophila melanogaster","volume":"10","author":"Reese","year":"2000","journal-title":"Genome Res"},{"key":"2026080408220625100_ref11","doi-asserted-by":"publisher","first-page":"S2.1","DOI":"10.1186\/gb-2006-7-s1-s2","article-title":"EGASP: the human ENCODE genome annotation assessment project","volume":"7 Suppl 1","author":"Guigo","year":"2006","journal-title":"Genome Biol"},{"key":"2026080408220625100_ref12","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1038\/nmeth.2722","article-title":"Systematic evaluation of spliced alignment programs for RNA-seq data","volume":"10","author":"Engstrom","year":"2013","journal-title":"Nat Methods"},{"key":"2026080408220625100_ref13","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1038\/nmeth.2714","article-title":"Assessment of transcript reconstruction methods for RNA-seq","volume":"10","author":"Steijger","year":"2013","journal-title":"Nat Methods"},{"key":"2026080408220625100_ref14","doi-asserted-by":"publisher","first-page":"100","DOI":"10.12688\/f1000research.10571.2","article-title":"Comprehensive comparison of Pacific Biosciences and Oxford Nanopore Technologies and their applications to transcriptome analysis","volume":"6","author":"Weirather","year":"2017","journal-title":"F1000Res"},{"key":"2026080408220625100_ref15","doi-asserted-by":"publisher","first-page":"3359","DOI":"10.1038\/s41467-019-11272-z","article-title":"A comprehensive examination of nanopore native RNA sequencing for characterization of complex transcriptomes","volume":"10","author":"Soneson","year":"2019","journal-title":"Nat Commun"},{"key":"2026080408220625100_ref16","doi-asserted-by":"publisher","DOI":"10.1101\/2023.06.06.543940","article-title":"High coverage highly accurate long-read sequencing of a mouse neuronal cell line using the PacBio Revio sequencer","author":"Manuel","year":"2023"},{"key":"2026080408220625100_ref17","author":"Pacific Biosciences"},{"key":"2026080408220625100_ref18","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1038\/s41587-022-01565-y","article-title":"Accurate isoform discovery with IsoQuant using long reads","volume":"41","author":"Prjibelski","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2026080408220625100_ref19","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1038\/s41592-023-01908-w","article-title":"Context-aware transcript quantification from long-read RNA-seq data with Bambu","volume":"20","author":"Chen","year":"2023","journal-title":"Nat Methods"},{"key":"2026080408220625100_ref20","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1186\/s13059-023-02999-6","article-title":"Identifying and quantifying isoforms from accurate full-length transcriptome sequencing reads with Mandalorion","volume":"24","author":"Volden","year":"2023","journal-title":"Genome Biol"},{"key":"2026080408220625100_ref21","doi-asserted-by":"publisher","first-page":"2438","DOI":"10.1016\/j.cell.2023.04.012","article-title":"Sites of transcription initiation drive mRNA isoform selection","volume":"186","author":"Alfonso-Gonzalez","year":"2023","journal-title":"Cell"},{"key":"2026080408220625100_ref22","doi-asserted-by":"publisher","first-page":"304","DOI":"10.12688\/f1000research.23297.2","article-title":"GFF utilities: GffRead and GffCompare","volume":"9","author":"Pertea","year":"2020","journal-title":"F1000Res"},{"key":"2026080408220625100_ref23","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2026080408220625100_ref24","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1038\/s41592-024-02229-2","article-title":"SQANTI3: curation of long-read transcriptomes for accurate identification of known and novel isoforms","volume":"21","author":"Pardo-Palacios","year":"2024","journal-title":"Nat Methods"},{"key":"2026080408220625100_ref25","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1038\/nbt.3122","article-title":"StringTie enables improved reconstruction of a transcriptome from RNA-seq reads","volume":"33","author":"Pertea","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2026080408220625100_ref26","doi-asserted-by":"publisher","first-page":"i304","DOI":"10.1093\/bioinformatics\/btaf240","article-title":"Oarfish: enhanced probabilistic modeling leads to improved accuracy in long read transcriptome quantification","volume":"41","author":"Zare Jousheghani","year":"2025","journal-title":"Bioinformatics"},{"key":"2026080408220625100_ref27","doi-asserted-by":"publisher","first-page":"2407","DOI":"10.1016\/j.jmb.2019.04.045","article-title":"refTSS: a reference data set for human and mouse transcription start sites","volume":"431","author":"Abugessaisa","year":"2019","journal-title":"J Mol Biol"},{"key":"2026080408220625100_ref28","doi-asserted-by":"publisher","first-page":"D174","DOI":"10.1093\/nar\/gkz918","article-title":"PolyASite 2.0: a consolidated atlas of polyadenylation sites from 3\u2032 end sequencing","volume":"48","author":"Herrmann","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2026080408220625100_ref29","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/s41592-025-02623-4","article-title":"A systematic benchmark of nanopore long-read RNA sequencing for transcript-level analysis in human cell lines","volume":"22","author":"Chen","year":"2025","journal-title":"Nat Methods"},{"key":"2026080408220625100_ref30","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/nmeth.3317","article-title":"HISAT: a fast spliced aligner with low memory requirements","volume":"12","author":"Kim","year":"2015","journal-title":"Nat Methods"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/4\/bbag403\/70389679\/bbag403.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/4\/bbag403\/70389679\/bbag403.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T12:22:13Z","timestamp":1785846133000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag403\/8747559"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag403","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7]]},"article-number":"bbag403"}}