@prefix this: . @prefix sub: . @prefix np: . @prefix dct: . @prefix pav: . @prefix rdf: . @prefix owl: . @prefix rdfg: . @prefix dce: . @prefix xsd: . @prefix rdfs: . @prefix prov: . @prefix npx: . sub:Head { this: a np:Nanopublication; np:hasAssertion sub:assertion; np:hasProvenance sub:provenance; np:hasPublicationInfo sub:pubinfo . } sub:assertion { a ; ; "Reames B" . a ; ; "Yang X" . a ; "Accessions (data not in GigaDB)"; "BioProject: PRJNA675370" . a ; "Additional information"; . a ; "Additional information"; . a ; "Additional information"; . a ; "Additional information"; . a ; "Additional information"; . a ; "Additional information"; . a ; "Additional information"; . a ; "Additional information"; . a ; "Award ID"; "GNT1195743" . a ; "Awardee"; "L Coin" . a ; "Dataset type"; "Epigenomic, Bioinformatics, Software, Transcriptomic" . a ; "Github links"; . a ; "Github links"; . a ; "Github links"; . a ; "Github links"; . a ; "History"; "Date: July 29, 2025, Action: Dataset publish" . a ; "Extra Information"; "Data Type: Readme, File Attributes: MD5 checksum: 450ef019cf8ba58beb644ef18d1411d0" . a ; "This dataset contains too many files that are not individually described"; "other files" . a ; "Extra Information"; "Data Type: Tabular data, File Attributes: MD5 checksum: 97ee210d263c783e4ddfe20352831d60 Figure in MS: 3" . a ; "Extra Information"; "Data Type: GitHub archive, File Attributes: MD5 checksum: 4b4d2ce7259e5045d89b731b7bfcf730 SWH: swh:1:snp:ee789638699e0e33ca3b1d09da5bb1f485ea7c70 license: MPL 2.0" . a . a ; "The person who associated a work with this deed has dedicated the work to the public domain by waiving all of his or her rights to the work worldwide under copyright law, including all related and neighboring rights, to the extent allowed by law. You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information below."; "Creative Commons Zero v1.0 Universal" . a , ; dct:conformsTo . a ; ; ; "doi:10.5524/102736" . a ; "database@gigasciencejournal.com"; "GigaDB is a data repository supporting scientific publications in the Life/Biomedical Sciences domain. GigaDB organises and curates data from individually publishable units into datasets, which are provided openly and in as FAIR manner as possible for the global research community."; "GigaScience DataBase" . a , . a ; "Archival copy of the GitHub repository https://github.com/haotianteng/BoostNano downloaded 18-July-2025. BoostNano, a tool for preprocessing ONT-Nanopore RNA sequencing reads.This project is licensed under the MPL 2.0 license. Please refer to the GitHub repo for most recent updates."; ; "#zipExtra"; "BoostNano-master"; "2025-07-23" . a ; "oxford nanopore technologies" . a ; ; "Chang JJ" . a ; ; "Coin LJM" . a ; ; "Teng H" . a ; ; "Corbin V" . a ; "The University of Melbourne" . a ; "Carnegie Mellon University" . a ; "contact of the publisher"; "database@gigasciencejournal.com"; "database@gigasciencejournal.com" . a ; "Funding Body"; "#awardId", "#awardee"; ; "National Health and Medical Research Council" . a ; "application/zip", . a , ; ; "https://s3.ap-northeast-1.wasabisys.com/gigadb-datasets/live/pub/10.5524/102001_103000/102736/boostnano_no_dorado_R1_tails.csv"; ; "2025-08-28 04:09:14.859328+00:00"; "2025-08-28 04:09:16.525835+00:00"; "PolyA tail lengths as found by Boostnano for R1 sequins which were filtered out by Dorado but kept by Boostnano; underlying data for figure 3"; "text/csv"; "#twoExtra"; ; "boostnano_no_dorado_R1_tails.csv"; "2025-08-28 04:09:14.859328+00:00" . a , ; ; "https://s3.ap-northeast-1.wasabisys.com/gigadb-datasets/live/pub/10.5524/102001_103000/102736/readme_102736.txt"; ; "2025-08-28 04:09:14.858721+00:00"; "2025-08-28 04:09:15.483716+00:00"; "text/txt"; "#oneExtra"; ; "readme_102736.txt"; "2025-08-28 04:09:14.858721+00:00" . a , , ; pav:importedBy ; , , , , , ; ; "8266"^^xsd:integer; "https://api.rohub.org/api/ros/3543b082-9077-492e-a4c7-a3b7c8bb39e8/crate/download/"; ; "2025-07-29 00:00:00"; "2025-10-16 11:11:58.719757+00:00"; "2025-07-29 00:00:00"; "Polyadenylation is a dynamic process which is important in cellular physiology. Oxford Nanopore Technologies direct RNA-sequencing provides a strategy for sequencing the full-length RNA molecule and analysis of the transcriptome and epi-transcriptome. There are currently several tools available for poly(A) tail-length estimation, including well-established tools such as tailfindr and nanopolish, as well as two more recent deep learning models: Dorado and BoostNano. However, there has been limited benchmarking of the accuracy of these tools against gold-standard datasets. In this paper we evaluate four poly(A) estimation tools using synthetic RNA standards (Sequins), which have known poly(A) tail-lengths and provide a valuable approach to measuring the accuracy of poly(A) tail-length estimation. All four tools generate mean tail-length estimates which lie within 12% of the correct value. Overall, Dorado is recommended as the preferred approach due to its relatively fast run times, low coefficient of variation and ease of use with integration with base-calling."; "application/ld+json"; "#accessions", "#additionalInfo1", "#additionalInfo2", "#additionalInfo3", "#additionalInfo4", "#additionalInfo5", "#additionalInfo6", "#additionalInfo7", "#additionalInfo8", "#datasetTypes", "#githubLink1", "#githubLink2", "#githubLink3", "#githubLink4", "#history"; ; , ; "https://w3id.org/ro-id/3543b082-9077-492e-a4c7-a3b7c8bb39e8"; "oxford nanopore technologies, poly(a) tail, estimation, segmentation, direct rna sequencing"; ; "Supporting data for \"Using synthetic RNA to benchmark poly(A) length inference from direct RNA sequencing.\""; ; ; ; , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ; ; "Chang JJ, Coin LJM, Teng H, Corbin V, Yang X, and Reames B. \"Supporting data for \"Using synthetic RNA to benchmark poly(A) length inference from direct RNA sequencing.\".\" ROHub. Jul 29 ,2025. https://w3id.org/ro-id/3543b082-9077-492e-a4c7-a3b7c8bb39e8." . a ; dct:conformsTo ; . a ; "polyester"; "10.658307210031346"; "10.2" . a ; "oceanography"; "100.0"; "0.4704064726829529" . a ; "strategy"; "5.120167189132707"; "4.9" . a ; "molecule"; "9.621993127147766"; "5.6" . a ; "estimate"; "8.986415882967608"; "8.6" . a ; "life sciences (general)"; "100.0"; "0.8512763977050781" . a ; "estimation"; "12.199312714776632"; "7.1" . a ; "Oxford Nanopore Technologies direct RNA-sequencing provides a strategy for sequencing the full-length RNA molecule and analysis of the transcriptome and epi-transcriptome."; "34.26966292134831"; "24.4" . a ; "RNA standard"; "22.157996146435455"; "11.5" . a ; "dataset"; "4.075235109717868"; "3.9" . a ; "gold standard"; "3.3437826541274815"; "3.2" . a ; "Textile and clothing"; "Economy, business and finance/Economic sector/Process industry/Textile and clothing" . a ; "RNA sequencing"; "21.965317919075144"; "11.4" . a ; "ribonucleic acid"; "17.763845350052247"; "17.0" . a ; "transcriptome"; "11.285266457680251"; "10.8" . a ; "RNA"; "24.570446735395187"; "14.3" . a ; "length"; "3.3437826541274815"; "3.2" . a ; "In this paper we evaluate four poly(A) estimation tools using synthetic RNA standards (Sequins), which have known poly(A) tail-lengths and provide a valuable approach to measuring the accuracy of poly(A) tail-length estimation."; "17.696629213483146"; "12.6" . a ; "estimation tool"; "17.919075144508675"; "9.3" . a ; "genetics"; "100.0"; "8.1" . a ; "transcriptome"; "15.29209621993127"; "8.9" . a ; "Genetics"; "Science and technology/Natural science/Biology/Genetics" . a ; "Supporting data for \"Using synthetic RNA to benchmark poly(A) length inference from direct RNA sequencing."; "48.033707865168545"; "34.2" . a ; "earth sciences"; "100.0"; "0.4704064726829529" . a ; "sequencing"; "12.027491408934708"; "7.0" . a ; "Dorado"; "8.045977011494253"; "7.7" . a ; "tail-length estimation"; "11.946050096339114"; "6.2" . a ; "Dorado"; "11.512027491408935"; "6.7" . a ; "molecule"; "7.105538140020898"; "6.8" . a ; "RNA molecule"; "26.01156069364162"; "13.5" . a ; "life sciences"; "100.0"; "0.8512763977050781" . a ; "sequencing"; "8.359456635318704"; "8.0" . a ; "accuracy"; "5.015673981191222"; "4.8" . a ; "poly"; "14.776632302405497"; "8.6" . a ; "coefficient of variation"; "3.657262277951933"; "3.5" . a ; "tool"; "3.239289446185998"; "3.1" . a ; "alex tsang" . } sub:provenance { sub:assertion prov:wasDerivedFrom . } sub:pubinfo { this: a npx:RoCrateNanopub; dct:created "2025-11-10T14:04:57.311+01:00"^^xsd:dateTime; npx:introduces ; rdfs:label "Supporting data for \"Using synthetic RNA to benchmark poly(A) length inference from direct RNA sequencing.\"" . sub:sig npx:hasAlgorithm "RSA"; npx:hasPublicKey "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA4pPaESKwmC6l37P86K6TNLq6yeQtc7m9CvcqauLs/1FC0viHvQnFBgxj0a+loPDv/Egwe6OqFpa0iW9Ypnyz9YPoh+pxbRXonbuMOb+8Ry9hXZ+TEKfWjhjVDGEaClwfRwglh2HI/xfV4CD9AgvDOEoZQiyta8a90PYwJ3G6e70oCHTn61+OWTkI9KRYHOYgg3btdy2Z7q/30PTFawb2ZT5aIfIJYobUYv2a7yhtcqWCHZeKv0bxGnRjTFNx1rscBMlLJSzvRtpQc1cCRVEPFZHo1adaXCI9tGvn4cxeNQ96y8dxkN1XhpaJairde+23MDzf42Oe97KG2HYzKiyVnQIDAQAB"; npx:hasSignature "zzCJEuZxvJ1/k+xzFPuJFYGTqPPvTVzLA4iQR4IxWXuCjOkR5GVV/LXrTjzK5nUHYqs17JYOviNWXNp1fJ8/Tc2wn99lOv4LeyzsOf5yBVghvC3KR+lYFJ+WSnwY1i/iRO2hyR1gd+TEVEeemW5tsw9PDzhWND+jOkWzFTD3V94BSPlIOTrZdZuVhVqHyTvlbY5HX6vq+5pGn0vg4i2XfvkETBrYiBXB9xTL9zhEleDUhmh8bVJk1iw3sPE8cqSdQmzq8cg7pQcXT5fLTn55pP8GdiAAc617rTcz+pVVCmKVSbb/8BGh1+JbK4Urc7xtZwEuELInBwfnsesm+0YwGQ=="; npx:hasSignatureTarget this:; npx:signedBy . }