{"data":[{"id":"10.5281/zenodo.20651865","type":"dois","attributes":{"doi":"10.5281/zenodo.20651865","identifiers":[],"creators":[{"name":"Fu, Laiyi","nameType":"Personal","givenName":"Laiyi","familyName":"Fu","affiliation":["Xi'an Jiaotong University"],"nameIdentifiers":[{"nameIdentifier":"0000-0001-9086-3982","nameIdentifierScheme":"ORCID"}]},{"name":"Li, Jiachun","nameType":"Personal","givenName":"Jiachun","familyName":"Li","nameIdentifiers":[],"affiliation":[]},{"name":"Wang, Ruiqi","nameType":"Personal","givenName":"Ruiqi","familyName":"Wang","nameIdentifiers":[],"affiliation":[]},{"name":"Sun, Hequan","nameType":"Personal","givenName":"Hequan","familyName":"Sun","affiliation":["Xi'an Jiaotong University"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-2046-2109","nameIdentifierScheme":"ORCID"}]},{"name":"Wu, Danyang","nameType":"Personal","givenName":"Danyang","familyName":"Wu","nameIdentifiers":[{"nameIdentifier":"0000-0002-0309-1409","nameIdentifierScheme":"ORCID"}],"affiliation":[]}],"titles":[{"title":"Supplementary file of UFold-X: An Enhanced Dual \u0026 Dynamic U-Mamba Model for Long-Range RNA Secondary Structure Prediction"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651865","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"1","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651865","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":2,"versionOfCount":1,"created":"2026-06-12T00:52:52Z","registered":"2026-06-12T00:52:52Z","published":null,"updated":"2026-06-12T00:52:52Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20650681","type":"dois","attributes":{"doi":"10.5281/zenodo.20650681","identifiers":[{"identifier":"oai:zenodo.org:20650681","identifierType":"oai"}],"creators":[{"name":"Akash Gupta","nameType":"Personal","familyName":"Akash Gupta","affiliation":["Clemson University"],"nameIdentifiers":[]},{"name":"Ethan Kung","nameType":"Personal","familyName":"Ethan Kung","affiliation":["Clemson University"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-2532-2458","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Automatic Generation of Lumped Parameter Cardiovascular Physiology Model"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"lumped parameter model"},{"subject":"cardiovascular physiology"},{"subject":"automatic parameter identification"},{"subject":"closed-loop"},{"subject":"deep learning"}],"contributors":[],"dates":[{"date":"2026-06-11","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.6653063","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v2","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This software will construct and run a realistic closed-loop lumped-parameter model of cardiovascular physiology.  The software automatically tunes the model parameters to achieve a set of desired hemodynamic outputs specified by the user, including:\n\nSystolic aortic pressure, diastolic aortic pressure, heart rate, systolic left ventricular volume, diastolic left ventricular volume, systolic right ventricular volume, diastolic right ventricular volume\n\nThe software will set model parameters such that all other hemodynamic outputs not specified by the user will fall within realistic clinical ranges.  \n\n \n\nRelated conference presentations:\n\nAutomated Tuning of a Lumped Parameter Model for Simulating Resting Cardiovascular Physiology.\n\n1) Summer Biomechanics, Bioengineering and Biotransport Conference, Cambridge, MD, June 20-23, 2022.\n\n2) 9th World Congress of Biomechanics, Taipei, Taiwan, July 10-14, 2022.\n\n \n\nCardiovascular Modeling \u0026 Experimentation Research Laboratory, Clemson University  http://www.cmerl.com\n\n ","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[{"awardTitle":"CAREER: Hybrid Experimental-Computational Modeling Framework for Transformative Research and Multidisciplinary Education in Cardiovascular Biomechanics","funderName":"U.S. National Science Foundation","awardNumber":"1749017","funderIdentifier":"10.13039/100000001","funderIdentifierType":"Crossref Funder ID"}],"url":"https://zenodo.org/doi/10.5281/zenodo.20650681","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:52:32Z","registered":"2026-06-12T00:52:32Z","published":null,"updated":"2026-06-12T00:52:32Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.6653063","type":"dois","attributes":{"doi":"10.5281/zenodo.6653063","identifiers":[{"identifier":"https://zenodo.org/record/6653064","identifierType":"URL"}],"creators":[{"name":"Akash Gupta","nameType":"Personal","familyName":"Akash Gupta","affiliation":["Clemson University"],"nameIdentifiers":[]},{"name":"Ethan Kung","nameType":"Personal","familyName":"Ethan Kung","affiliation":["Clemson University"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-2532-2458","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Automatic Generation of Lumped Parameter Cardiovascular Physiology Model"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"lumped parameter model"},{"subject":"cardiovascular physiology"},{"subject":"automatic parameter identification"},{"subject":"closed-loop"},{"subject":"deep learning"}],"contributors":[],"dates":[{"date":"2026-06-11","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.6653063","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v2","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This software will construct and run a realistic closed-loop lumped-parameter model of cardiovascular physiology.  The software automatically tunes the model parameters to achieve a set of desired hemodynamic outputs specified by the user, including:\n\nSystolic aortic pressure, diastolic aortic pressure, heart rate, systolic left ventricular volume, diastolic left ventricular volume, systolic right ventricular volume, diastolic right ventricular volume\n\nThe software will set model parameters such that all other hemodynamic outputs not specified by the user will fall within realistic clinical ranges.  \n\n \n\nRelated conference presentations:\n\nAutomated Tuning of a Lumped Parameter Model for Simulating Resting Cardiovascular Physiology.\n\n1) Summer Biomechanics, Bioengineering and Biotransport Conference, Cambridge, MD, June 20-23, 2022.\n\n2) 9th World Congress of Biomechanics, Taipei, Taiwan, July 10-14, 2022.\n\n \n\nCardiovascular Modeling \u0026 Experimentation Research Laboratory, Clemson University  http://www.cmerl.com\n\n ","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[{"awardTitle":"CAREER: Hybrid Experimental-Computational Modeling Framework for Transformative Research and Multidisciplinary Education in Cardiovascular Biomechanics","funderName":"U.S. National Science Foundation","awardNumber":"1749017","funderIdentifier":"10.13039/100000001","funderIdentifierType":"Crossref Funder ID"}],"url":"https://zenodo.org/doi/10.5281/zenodo.6653063","contentUrl":null,"metadataVersion":3,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":2,"versionOfCount":1,"created":"2022-06-16T15:11:54Z","registered":"2022-06-16T15:11:55Z","published":null,"updated":"2026-06-12T00:52:32Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651856","type":"dois","attributes":{"doi":"10.5281/zenodo.20651856","identifiers":[],"creators":[{"name":"Choudhary, Abhishek","nameType":"Personal","givenName":"Abhishek","familyName":"Choudhary","affiliation":["AyeAI"],"nameIdentifiers":[]}],"titles":[{"title":"Romenagri / ILM — Reversible Multiscript Substrate and Hindawi Programming System (2004)"}],"publisher":"Zenodo","container":{},"publicationYear":2004,"subjects":[{"subject":"transliteration"},{"subject":"Indic scripts"},{"subject":"systems programming"},{"subject":"linguistic equity"},{"subject":"Romenagri"},{"subject":"Hindawi"},{"subject":"ILM"},{"subject":"reversible"},{"subject":"multilingual"},{"subject":"Brahmi"},{"subject":"Perso-Arabic"},{"subject":"NW-Semitic"},{"subject":"AGI"}],"contributors":[],"dates":[{"date":"2004-08-15","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/project-ilm/romenagri","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"https://sourceforge.net/projects/hindawi","relatedIdentifierType":"URL"},{"relationType":"IsSupplementTo","relatedIdentifier":"https://savannah.nongnu.org/projects/hindawi","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651856","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rights":"GNU General Public License v3.0 only","rightsUri":"https://www.gnu.org/licenses/gpl-3.0-standalone.html","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"gpl-3.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"Romenagri (GPL 2003): reversible, ASCII-7, diacritic-free, C-identifier-legal transliteration kernel unifying Brahmi, Perso-Arabic, and NW-Semitic script families. First realised in the Hindawi Programming System (HPS, public release 15 August 2004): the first complete non-English systems-programming stack — C, C++, Assembly, Lex, Yacc, BASIC, JVM-target — in Indic languages through an unmodified GCC toolchain. 68-language keyword registry (201 constructs spanning hardware RTL through AGI), 45 Brahmi-derived script projection tables, C/JS/Java/WASM bindings. Measured reversibility: 98.68% reversible-or-canonical on exhaustive [a-z]^1..4 (2003-04 kernel). Copyright (C) 1993-2026 Abhishek Choudhary.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651856","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":2,"versionOfCount":1,"created":"2026-06-12T00:51:37Z","registered":"2026-06-12T00:51:37Z","published":null,"updated":"2026-06-12T00:51:37Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651857","type":"dois","attributes":{"doi":"10.5281/zenodo.20651857","identifiers":[{"identifier":"oai:zenodo.org:20651857","identifierType":"oai"}],"creators":[{"name":"Choudhary, Abhishek","nameType":"Personal","givenName":"Abhishek","familyName":"Choudhary","affiliation":["AyeAI"],"nameIdentifiers":[]}],"titles":[{"title":"Romenagri / ILM — Reversible Multiscript Substrate and Hindawi Programming System (2004)"}],"publisher":"Zenodo","container":{},"publicationYear":2004,"subjects":[{"subject":"transliteration"},{"subject":"Indic scripts"},{"subject":"systems programming"},{"subject":"linguistic equity"},{"subject":"Romenagri"},{"subject":"Hindawi"},{"subject":"ILM"},{"subject":"reversible"},{"subject":"multilingual"},{"subject":"Brahmi"},{"subject":"Perso-Arabic"},{"subject":"NW-Semitic"},{"subject":"AGI"}],"contributors":[],"dates":[{"date":"2004-08-15","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/project-ilm/romenagri","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"https://sourceforge.net/projects/hindawi","relatedIdentifierType":"URL"},{"relationType":"IsSupplementTo","relatedIdentifier":"https://savannah.nongnu.org/projects/hindawi","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651856","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rights":"GNU General Public License v3.0 only","rightsUri":"https://www.gnu.org/licenses/gpl-3.0-standalone.html","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"gpl-3.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"Romenagri (GPL 2003): reversible, ASCII-7, diacritic-free, C-identifier-legal transliteration kernel unifying Brahmi, Perso-Arabic, and NW-Semitic script families. First realised in the Hindawi Programming System (HPS, public release 15 August 2004): the first complete non-English systems-programming stack — C, C++, Assembly, Lex, Yacc, BASIC, JVM-target — in Indic languages through an unmodified GCC toolchain. 68-language keyword registry (201 constructs spanning hardware RTL through AGI), 45 Brahmi-derived script projection tables, C/JS/Java/WASM bindings. Measured reversibility: 98.68% reversible-or-canonical on exhaustive [a-z]^1..4 (2003-04 kernel). Copyright (C) 1993-2026 Abhishek Choudhary.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651857","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-06-12T00:51:37Z","registered":"2026-06-12T00:51:37Z","published":null,"updated":"2026-06-12T00:51:37Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651915","type":"dois","attributes":{"doi":"10.5281/zenodo.20651915","identifiers":[{"identifier":"oai:zenodo.org:20651915","identifierType":"oai"}],"creators":[{"name":"Zhang, Zijin","nameType":"Personal","givenName":"Zijin","familyName":"Zhang","nameIdentifiers":[{"nameIdentifier":"0000-0002-9968-067X","nameIdentifierScheme":"ORCID"}],"affiliation":[]}],"titles":[{"title":"CDAWeb.jl: Julia interface to NASA's CDAWeb services"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"Julia"},{"subject":"Space physics"},{"subject":"CDAWeb"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/JuliaSpacePhysics/CDAWeb.jl/tree/v0.2.5","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.17519096","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v0.2.5","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"CDAWeb v0.2.5\n\nDiff since v0.2.4\n\nMerged pull requests:\n\n\n\nfeat: support HTTP.jl 2.x (compat \"1, 2\") (#30) (@Beforerr)\n\nbuild(deps): bump codecov/codecov-action from 6 to 7 (#31) (@dependabot[bot])","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651915","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:47:22Z","registered":"2026-06-12T00:47:23Z","published":null,"updated":"2026-06-12T00:47:23Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.17519096","type":"dois","attributes":{"doi":"10.5281/zenodo.17519096","identifiers":[],"creators":[{"name":"Zhang, Zijin","nameType":"Personal","givenName":"Zijin","familyName":"Zhang","nameIdentifiers":[{"nameIdentifier":"0000-0002-9968-067X","nameIdentifierScheme":"ORCID"}],"affiliation":[]}],"titles":[{"title":"CDAWeb.jl: Julia interface to NASA's CDAWeb services"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"Julia"},{"subject":"Space physics"},{"subject":"CDAWeb"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/JuliaSpacePhysics/CDAWeb.jl/tree/v0.2.5","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.17519096","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v0.2.5","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"CDAWeb v0.2.5\n\nDiff since v0.2.4\n\nMerged pull requests:\n\n\n\nfeat: support HTTP.jl 2.x (compat \"1, 2\") (#30) (@Beforerr)\n\nbuild(deps): bump codecov/codecov-action from 6 to 7 (#31) (@dependabot[bot])","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.17519096","contentUrl":null,"metadataVersion":8,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":9,"versionOfCount":1,"created":"2025-11-04T04:38:59Z","registered":"2025-11-04T04:38:59Z","published":null,"updated":"2026-06-12T00:47:22Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.15061627","type":"dois","attributes":{"doi":"10.5281/zenodo.15061627","identifiers":[],"creators":[{"name":"Ash O'Farrell","nameType":"Personal","familyName":"Ash O'Farrell","affiliation":["University of California Santa Cruz"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4896-1858","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"github.com/aofarrel/myco/myco_simple"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/aliases/workflow-versions/10.5281-zenodo.20651894","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/workflows/github.com/aofarrel/myco/myco_simple:7.1.0","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/api/ga4gh/trs/v2/tools/%23workflow%2Fgithub.com%2Faofarrel%2Fmyco%2Fmyco_simple/versions/7.1.0/PLAIN-WDL/descriptor/myco_simple.wdl","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.15061627","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"7.1.0","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"myco_simple\n\nmyco_simple is the version of myco to use if you already have a bunch of fastqs, divided on a per-sample basis. It assumes you do not want to decontaminate your fastqs at all -- perhaps they are non-tuberculosis mycobacteria or already decontaminated -- but it does offer the option of cleaning with fastp.\n\nEach sample's read direction must be an individual gzipped file, e.g. SRR1173122_1.fq.gz and SRR1173122_2.fq.gz representing sample SRR1173122. Something like SRR1173122.gz which contains two fastqs would not work. Unlike more flexible versions of myco, the inputs to myco_simple strictly must be individually gzipped due to limitations of the variant caller.\n\nNotable inputs\n\nAll non-fastq inputs are documented here: inputs.md\n\nFASTQs\n\nYou need your FASTQs as a nested array, where each inner array represents one sample. For example, let's say you the following samples in a google bucket located at gs://my-cool-bucket/fqs/\n\n\n\nSAMN02599053, consisting of SAMN02599053_SRR1173122_1.fq.gz, SAMN02599053_SRR1173122_2.fq.gz, SAMN02599053_SRR1173191_1.fq.gz, and SAMN02599053_SRR1173191_2.fq.gz\n\nSAMN13813990, consisting of SAMN13813990_SRR10869128_1.fq.gz and SAMN13813990_SRR10869128_2.fq.gz\n\n\nYou would input the following for paired_fastq_sets:\n\n[[\"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_2.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_2.fq.gz\"], [\"gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_1.fq.gz\", gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_2.fq.gz\"]]\n\n\nThe first array represents sample SAMN02599053. The second array represents sample SAMN13813990. You will note that SAMN02599053 has two pairs of fastqs, while SAMN13813990 only has one pair of fastqs -- this is fine!\n\nFull workflow process\n\n[1] clockwork variant_call_single\n\nBased on clockwork variant_call_single, which itself combines samtools, cortex, and minos. For each sample, the output is a single VCF file and a BAM file.\n\n[2] (optional) Run FastQC on slow samples\n\nIf a sample times out in the variant calling step, it is usually due to an issue with the inputs. FastQC examines all inputs that timed out so you can see what might be going on.\n\n[3] VCF2diff -- Mask the outputs and optionally create diff files\n\nWhen feeding outputs into UShER, we want to make use of diff files. But first, we perform a little bit of data processing -- it common for some regions of the TB genome to be masked. We want to avoid those problematic regions in our final output, as well as any regions without much coverage. This task cleans up our outputs and optionally creates a diff file, one per sample, which can be used to make some happy little phylogenetic trees using Tree Nine.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.15061627","contentUrl":null,"metadataVersion":8,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":9,"versionOfCount":1,"created":"2025-03-20T22:05:26Z","registered":"2025-03-20T22:05:27Z","published":null,"updated":"2026-06-12T00:45:41Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651894","type":"dois","attributes":{"doi":"10.5281/zenodo.20651894","identifiers":[{"identifier":"oai:zenodo.org:20651894","identifierType":"oai"}],"creators":[{"name":"Ash O'Farrell","nameType":"Personal","familyName":"Ash O'Farrell","affiliation":["University of California Santa Cruz"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4896-1858","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"github.com/aofarrel/myco/myco_simple"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/aliases/workflow-versions/10.5281-zenodo.20651894","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/workflows/github.com/aofarrel/myco/myco_simple:7.1.0","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/api/ga4gh/trs/v2/tools/%23workflow%2Fgithub.com%2Faofarrel%2Fmyco%2Fmyco_simple/versions/7.1.0/PLAIN-WDL/descriptor/myco_simple.wdl","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.15061627","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"7.1.0","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"myco_simple\n\nmyco_simple is the version of myco to use if you already have a bunch of fastqs, divided on a per-sample basis. It assumes you do not want to decontaminate your fastqs at all -- perhaps they are non-tuberculosis mycobacteria or already decontaminated -- but it does offer the option of cleaning with fastp.\n\nEach sample's read direction must be an individual gzipped file, e.g. SRR1173122_1.fq.gz and SRR1173122_2.fq.gz representing sample SRR1173122. Something like SRR1173122.gz which contains two fastqs would not work. Unlike more flexible versions of myco, the inputs to myco_simple strictly must be individually gzipped due to limitations of the variant caller.\n\nNotable inputs\n\nAll non-fastq inputs are documented here: inputs.md\n\nFASTQs\n\nYou need your FASTQs as a nested array, where each inner array represents one sample. For example, let's say you the following samples in a google bucket located at gs://my-cool-bucket/fqs/\n\n\n\nSAMN02599053, consisting of SAMN02599053_SRR1173122_1.fq.gz, SAMN02599053_SRR1173122_2.fq.gz, SAMN02599053_SRR1173191_1.fq.gz, and SAMN02599053_SRR1173191_2.fq.gz\n\nSAMN13813990, consisting of SAMN13813990_SRR10869128_1.fq.gz and SAMN13813990_SRR10869128_2.fq.gz\n\n\nYou would input the following for paired_fastq_sets:\n\n[[\"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_2.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_2.fq.gz\"], [\"gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_1.fq.gz\", gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_2.fq.gz\"]]\n\n\nThe first array represents sample SAMN02599053. The second array represents sample SAMN13813990. You will note that SAMN02599053 has two pairs of fastqs, while SAMN13813990 only has one pair of fastqs -- this is fine!\n\nFull workflow process\n\n[1] clockwork variant_call_single\n\nBased on clockwork variant_call_single, which itself combines samtools, cortex, and minos. For each sample, the output is a single VCF file and a BAM file.\n\n[2] (optional) Run FastQC on slow samples\n\nIf a sample times out in the variant calling step, it is usually due to an issue with the inputs. FastQC examines all inputs that timed out so you can see what might be going on.\n\n[3] VCF2diff -- Mask the outputs and optionally create diff files\n\nWhen feeding outputs into UShER, we want to make use of diff files. But first, we perform a little bit of data processing -- it common for some regions of the TB genome to be masked. We want to avoid those problematic regions in our final output, as well as any regions without much coverage. This task cleans up our outputs and optionally creates a diff file, one per sample, which can be used to make some happy little phylogenetic trees using Tree Nine.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651894","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-06-12T00:45:41Z","registered":"2026-06-12T00:45:41Z","published":null,"updated":"2026-06-12T00:45:41Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.15080116","type":"dois","attributes":{"doi":"10.5281/zenodo.15080116","identifiers":[],"creators":[{"name":"Ash O'Farrell","nameType":"Personal","familyName":"Ash O'Farrell","affiliation":["University of California Santa Cruz"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4896-1858","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"github.com/aofarrel/myco/myco_sra"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"bacteria"},{"subject":"mycobacterium-tuberculosis"},{"subject":"phylogenetics"},{"subject":"sra"},{"subject":"tuberculosis"},{"subject":"usher"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/aliases/workflow-versions/10.5281-zenodo.20651893","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/workflows/github.com/aofarrel/myco/myco_sra:7.1.0","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/api/ga4gh/trs/v2/tools/%23workflow%2Fgithub.com%2Faofarrel%2Fmyco%2Fmyco_sra/versions/7.1.0/PLAIN-WDL/descriptor/myco_sra.wdl","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.15080116","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"7.1.0","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"myco_sra\n\nmyco_sra is the SRA version of myco. Use this version of myco if you want to analysze fastqs from SRA. This is powered by SRANWRP, most notably the pull-FASTQs-from-biosample workflow. (For the sake of simplicity this readme calls the part of myco_sra that downloads from SRA \"SRANWRP\", even thought SRANWRP contains a few additional utility functions and workflows.)\n\nNotable inputs\n\nbiosample_accessions -- a single text File which contains BioSample accessions, one BioSample accession per line, ex:\n\nSAMEA10030079\nSAMEA10030285\nSAMEA10030321\nSAMEA10030646\nSAMEA104390589\nSAMEA110024138\nSAMEA111556114\n\n\nSAME, SAMN, SRS, ERS, and numeric BioSample accessions are all supported, as well as any combination of these formats. Run accessions (SRR, ERR, DRR) are not supported, but you can use this workflow to convert your run accessions to BioSample accessions.\n\nAll other inputs are documented here: inputs.md\n\nHow does the fastq downloading part differ from similar workflows?\n\nThere are several existing workflows which can pull from SRA, such as SRA Fetch and DownloadFromSRA. If you need your reads downloaded with no processing, need PacBio reads downloaded, or need your fastqs saved to a specific GCS directory, these workflows might be better suited to your needs than SRANWRP. SRANWRP assumes you only want paired-end Illumina data while also making no assumptions that the BioSamples you are giving it actually have any paired-end Illumina data.\n\nHow does myco_sra handle \"weird\" data?/What checks does it perform?\n\nThe \"ideal\" scenario is that each BioSample has some number of run accessions, and each run accession returns one pair of Illumina-created fastq files. But sometimes life isn't so simple, so SRANWRP handles:\n\n\n\nBioSamples which contain run accessions created with different sequencing technologies (ex: SAMN03257097 has two Illumina run accessions and two PacBio run accessions)\n\nRun accessions that return three fastq files\n\nRun accessions that return one fastq file\n\nRun accessions that return more than one pair of fastqs\n\nRun accessions that return large fastqs -- by default, fastqs larger than 450 megabytes will be randomly subsampled down to 1,000,000 random reads\n\nBioSamples with any combination of the above exist -- ex: A single BioSample with one run accession returning one pair of fastqs, one run accession returning three fastqs, one run accession actually being a PacBio run, and one run accession returning two pairs of 2 GB fastqs\n\n\nFor example, let's say this task got SAMN08436121. This has only one run associated with it: SRR6650260. Pulling that yields three files: SRR6650260_1.fastq, SRR6650260_2.fastq, and SRR6650260.fastq. Only SRR6650260_1.fastq and SRR6650260_2.fastq will be passed to the decontamination and variant calling steps.\n\nAre there any SRA accessions known to break SRANWRP?\n\nAccessions belonging to \"sample groups\" are not supported, as it isn't very clear which run accessions correlate to which sample accessions. Known \"sample group\" accessions can be found in SRANWRP's denylists. Non-TB accessions are also not supported.\n\nSamples with a very large number of run accessions could be problematic on a GCP backend. GCP backends require you request a certain amount of disk size before runtime, which can get dicey when what you want to do at runtime is download an unknown number of files of unknown size. As such, SRANWRP requests more disk size than you probably need, but there could come a time that guess doesn't prove to be enough.\n\nThe only other accessions known to fail SRANWRP are ones which break prefetch or fasterq-dump. Usually this means the fastqs themselves are invalid (ex: SAMEA1877221, SAMEA2609926, SAMEA2609935) or were not fully processed by NCBI (ex: ERR760606, although SAMEA3231653 has two other run accessions which do work fine).\n\nWhat if an SRA accession passes SRANWRP, but isn't good enough for the rest of the pipeline?\n\nWe can't always tell that data isn't up to our standards until later down the pipeline. myco (including myco_sra) will filter out samples which:\n\n\n\nare too heavily contaminated to complete decontamination in a timely manner†\n\ntake too long in the variant caller†\n\nhave low overall coverage\n\n\n†This sort of filtering can be disabled by setting the timeout optional variables to 0 -- but be aware that GCP will kill any VM that is still alive after about a week, so if you're on Terra, your samples need to process faster than that!\n\nThere is a small number of BioSamples known to return fastqs which, after decontamination, will cause a runtime error in the variant caller. As of version 3.0.1 of myco, this runtime error is handled by throwing out the sample rather than stopping the entire pipeline (unless you set crash_on_error to true). Throwing out samples like this was decided as the default behavior as a quick analysis indicates the runtime error only happens when clockwork's variant calling removes \u003e95% of the fastq during a Trimmomatic run (ie, the sample probably shouldn't be used anyway). The list of these samples can be found in SRANWRP's denylists.\n\nProcess in detail\n\n[1] Extract BioSample accessions from input file\n\nThe user is expected to input a text containing BioSample accessions. This task grabs all unique lines in that file and outputs an Array[String] of BioSample accessions.\n\n[2] Pull fastqs for the BioSample accession\n\nThis task pulls all fastqs for a given BioSample accession using SRANWRP, which itself uses sra-tools. One BioSample might have multiple run accessions; all of them are pulled. Once pulled, my script attempts to remove everything that is not a set of paired fastqs.\n\nThere are some samples that return no valid fastqs. There is an additional task that keeps track of every sample's run accessions, and the result of trying to pull fastqs from each run accession. The \"pull report\" is a workflow-level output.\n\n[3] Run fastp and decontaminate\n\nThis task is based on clockwork's decontamination process, which runs clockwork map_reads and clockwork remove_contam in a single WDL task. In recent updates, it has also been merged with fastp as a preliminary cleaning and QC step. On default settings, this is the order of events:\n\n\n\nCleaning of the reads via fastp\n\nclockwork map_reads to map reads to the decontamination reference\n\nclockwork remove_contam to generate cleaned fastqs\n\nA second run of fastp, but instead of cleaning the reads again, we focus on the QC metrics and determine if these samples are good enough\n\n\nPart three of this process will merge FASTQs if a single sample has more than one pair of FASTQs. For example, SAMN02599053 has four fastqs associated with it:\n\n\n\nSAMN02599053_SRR1173122_1.fq.gz\n\nSAMN02599053_SRR1173122_2.fq.gz\n\nSAMN02599053_SRR1173191_1.fq.gz\n\nSAMN02599053_SRR1173191_2.fq.gz\n\n\nThe decontamination step will output a single pair: SAMN02599053_1.fastq and SAMN02599053_2.fastq\n\n[4] (optional) Run TBProfiler\n\nIf TBProf_on_bams_not_fastqs is false, TBProfiler will be run on the fastqs here. This form of TBProfiler is a fork by Thiagen Genomics that features some improvements to its database and generates special outputs for LHJs. Because myco_sra's use case is different from that of myco_raw, this step is optional in order to save money.\n\n[5] Call variants\n\nBased on clockwork variant_call_single, which itself combines samtools, cortex, and minos. For each sample, the output is a single VCF file and a BAM file.\n\n[6] (optional) Run covstats\n\nCovstats checks how much of a sample ends up unmapped, and the average coverage. This takes some time to calculate, so it's optional, but it also gives us two additional QC metrics.\n\n[7] Mask the outputs create diff files\n\nWhen feeding outputs into UShER, we want to make use of diff files. But first, we perform a little bit of data processing -- it common for some regions of the TB genome to be masked. We want to avoid those problematic regions in our final output, as well as any regions without much coverage. This task cleans up our outputs and optionally creates a diff file, one per sample, which can be used to make some happy little trees.\n\n[8] Collate QC information\n\nThis pipeline generates a large amount of metadata and intermediate files. This task summarizes QC information into a single file for easy reference.\n\n[9] (optional) Generate UShER, Taxonium, newick, and NextStrain trees\n\nIf decorate_trees = true, and an input tree is passed in, each sample will be placed on the tree by UShER. The resulting tree will then be converted to Taxonium format, allowing it to be viewed in taxonium. NextStrain subtree JSONs will also be generated.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.15080116","contentUrl":null,"metadataVersion":11,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":12,"versionOfCount":1,"created":"2025-03-24T22:51:39Z","registered":"2025-03-24T22:51:39Z","published":null,"updated":"2026-06-12T00:45:36Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651893","type":"dois","attributes":{"doi":"10.5281/zenodo.20651893","identifiers":[{"identifier":"oai:zenodo.org:20651893","identifierType":"oai"}],"creators":[{"name":"Ash O'Farrell","nameType":"Personal","familyName":"Ash O'Farrell","affiliation":["University of California Santa Cruz"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4896-1858","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"github.com/aofarrel/myco/myco_sra"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"bacteria"},{"subject":"mycobacterium-tuberculosis"},{"subject":"phylogenetics"},{"subject":"sra"},{"subject":"tuberculosis"},{"subject":"usher"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/aliases/workflow-versions/10.5281-zenodo.20651893","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/workflows/github.com/aofarrel/myco/myco_sra:7.1.0","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/api/ga4gh/trs/v2/tools/%23workflow%2Fgithub.com%2Faofarrel%2Fmyco%2Fmyco_sra/versions/7.1.0/PLAIN-WDL/descriptor/myco_sra.wdl","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.15080116","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"7.1.0","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"myco_sra\n\nmyco_sra is the SRA version of myco. Use this version of myco if you want to analysze fastqs from SRA. This is powered by SRANWRP, most notably the pull-FASTQs-from-biosample workflow. (For the sake of simplicity this readme calls the part of myco_sra that downloads from SRA \"SRANWRP\", even thought SRANWRP contains a few additional utility functions and workflows.)\n\nNotable inputs\n\nbiosample_accessions -- a single text File which contains BioSample accessions, one BioSample accession per line, ex:\n\nSAMEA10030079\nSAMEA10030285\nSAMEA10030321\nSAMEA10030646\nSAMEA104390589\nSAMEA110024138\nSAMEA111556114\n\n\nSAME, SAMN, SRS, ERS, and numeric BioSample accessions are all supported, as well as any combination of these formats. Run accessions (SRR, ERR, DRR) are not supported, but you can use this workflow to convert your run accessions to BioSample accessions.\n\nAll other inputs are documented here: inputs.md\n\nHow does the fastq downloading part differ from similar workflows?\n\nThere are several existing workflows which can pull from SRA, such as SRA Fetch and DownloadFromSRA. If you need your reads downloaded with no processing, need PacBio reads downloaded, or need your fastqs saved to a specific GCS directory, these workflows might be better suited to your needs than SRANWRP. SRANWRP assumes you only want paired-end Illumina data while also making no assumptions that the BioSamples you are giving it actually have any paired-end Illumina data.\n\nHow does myco_sra handle \"weird\" data?/What checks does it perform?\n\nThe \"ideal\" scenario is that each BioSample has some number of run accessions, and each run accession returns one pair of Illumina-created fastq files. But sometimes life isn't so simple, so SRANWRP handles:\n\n\n\nBioSamples which contain run accessions created with different sequencing technologies (ex: SAMN03257097 has two Illumina run accessions and two PacBio run accessions)\n\nRun accessions that return three fastq files\n\nRun accessions that return one fastq file\n\nRun accessions that return more than one pair of fastqs\n\nRun accessions that return large fastqs -- by default, fastqs larger than 450 megabytes will be randomly subsampled down to 1,000,000 random reads\n\nBioSamples with any combination of the above exist -- ex: A single BioSample with one run accession returning one pair of fastqs, one run accession returning three fastqs, one run accession actually being a PacBio run, and one run accession returning two pairs of 2 GB fastqs\n\n\nFor example, let's say this task got SAMN08436121. This has only one run associated with it: SRR6650260. Pulling that yields three files: SRR6650260_1.fastq, SRR6650260_2.fastq, and SRR6650260.fastq. Only SRR6650260_1.fastq and SRR6650260_2.fastq will be passed to the decontamination and variant calling steps.\n\nAre there any SRA accessions known to break SRANWRP?\n\nAccessions belonging to \"sample groups\" are not supported, as it isn't very clear which run accessions correlate to which sample accessions. Known \"sample group\" accessions can be found in SRANWRP's denylists. Non-TB accessions are also not supported.\n\nSamples with a very large number of run accessions could be problematic on a GCP backend. GCP backends require you request a certain amount of disk size before runtime, which can get dicey when what you want to do at runtime is download an unknown number of files of unknown size. As such, SRANWRP requests more disk size than you probably need, but there could come a time that guess doesn't prove to be enough.\n\nThe only other accessions known to fail SRANWRP are ones which break prefetch or fasterq-dump. Usually this means the fastqs themselves are invalid (ex: SAMEA1877221, SAMEA2609926, SAMEA2609935) or were not fully processed by NCBI (ex: ERR760606, although SAMEA3231653 has two other run accessions which do work fine).\n\nWhat if an SRA accession passes SRANWRP, but isn't good enough for the rest of the pipeline?\n\nWe can't always tell that data isn't up to our standards until later down the pipeline. myco (including myco_sra) will filter out samples which:\n\n\n\nare too heavily contaminated to complete decontamination in a timely manner†\n\ntake too long in the variant caller†\n\nhave low overall coverage\n\n\n†This sort of filtering can be disabled by setting the timeout optional variables to 0 -- but be aware that GCP will kill any VM that is still alive after about a week, so if you're on Terra, your samples need to process faster than that!\n\nThere is a small number of BioSamples known to return fastqs which, after decontamination, will cause a runtime error in the variant caller. As of version 3.0.1 of myco, this runtime error is handled by throwing out the sample rather than stopping the entire pipeline (unless you set crash_on_error to true). Throwing out samples like this was decided as the default behavior as a quick analysis indicates the runtime error only happens when clockwork's variant calling removes \u003e95% of the fastq during a Trimmomatic run (ie, the sample probably shouldn't be used anyway). The list of these samples can be found in SRANWRP's denylists.\n\nProcess in detail\n\n[1] Extract BioSample accessions from input file\n\nThe user is expected to input a text containing BioSample accessions. This task grabs all unique lines in that file and outputs an Array[String] of BioSample accessions.\n\n[2] Pull fastqs for the BioSample accession\n\nThis task pulls all fastqs for a given BioSample accession using SRANWRP, which itself uses sra-tools. One BioSample might have multiple run accessions; all of them are pulled. Once pulled, my script attempts to remove everything that is not a set of paired fastqs.\n\nThere are some samples that return no valid fastqs. There is an additional task that keeps track of every sample's run accessions, and the result of trying to pull fastqs from each run accession. The \"pull report\" is a workflow-level output.\n\n[3] Run fastp and decontaminate\n\nThis task is based on clockwork's decontamination process, which runs clockwork map_reads and clockwork remove_contam in a single WDL task. In recent updates, it has also been merged with fastp as a preliminary cleaning and QC step. On default settings, this is the order of events:\n\n\n\nCleaning of the reads via fastp\n\nclockwork map_reads to map reads to the decontamination reference\n\nclockwork remove_contam to generate cleaned fastqs\n\nA second run of fastp, but instead of cleaning the reads again, we focus on the QC metrics and determine if these samples are good enough\n\n\nPart three of this process will merge FASTQs if a single sample has more than one pair of FASTQs. For example, SAMN02599053 has four fastqs associated with it:\n\n\n\nSAMN02599053_SRR1173122_1.fq.gz\n\nSAMN02599053_SRR1173122_2.fq.gz\n\nSAMN02599053_SRR1173191_1.fq.gz\n\nSAMN02599053_SRR1173191_2.fq.gz\n\n\nThe decontamination step will output a single pair: SAMN02599053_1.fastq and SAMN02599053_2.fastq\n\n[4] (optional) Run TBProfiler\n\nIf TBProf_on_bams_not_fastqs is false, TBProfiler will be run on the fastqs here. This form of TBProfiler is a fork by Thiagen Genomics that features some improvements to its database and generates special outputs for LHJs. Because myco_sra's use case is different from that of myco_raw, this step is optional in order to save money.\n\n[5] Call variants\n\nBased on clockwork variant_call_single, which itself combines samtools, cortex, and minos. For each sample, the output is a single VCF file and a BAM file.\n\n[6] (optional) Run covstats\n\nCovstats checks how much of a sample ends up unmapped, and the average coverage. This takes some time to calculate, so it's optional, but it also gives us two additional QC metrics.\n\n[7] Mask the outputs create diff files\n\nWhen feeding outputs into UShER, we want to make use of diff files. But first, we perform a little bit of data processing -- it common for some regions of the TB genome to be masked. We want to avoid those problematic regions in our final output, as well as any regions without much coverage. This task cleans up our outputs and optionally creates a diff file, one per sample, which can be used to make some happy little trees.\n\n[8] Collate QC information\n\nThis pipeline generates a large amount of metadata and intermediate files. This task summarizes QC information into a single file for easy reference.\n\n[9] (optional) Generate UShER, Taxonium, newick, and NextStrain trees\n\nIf decorate_trees = true, and an input tree is passed in, each sample will be placed on the tree by UShER. The resulting tree will then be converted to Taxonium format, allowing it to be viewed in taxonium. NextStrain subtree JSONs will also be generated.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651893","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:45:36Z","registered":"2026-06-12T00:45:36Z","published":null,"updated":"2026-06-12T00:45:36Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651892","type":"dois","attributes":{"doi":"10.5281/zenodo.20651892","identifiers":[{"identifier":"oai:zenodo.org:20651892","identifierType":"oai"}],"creators":[{"name":"Thomsen, Lars","nameType":"Personal","givenName":"Lars","familyName":"Thomsen","affiliation":["GNACODE Inc., Medicine Hat, AB, Canada"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-1557-5646","nameIdentifierScheme":"ORCID"}]},{"name":"Makovetskyi, Sergii","nameType":"Personal","givenName":"Sergii","familyName":"Makovetskyi","affiliation":["Kharkiv National University of Radio Electronics, Ukraine"],"nameIdentifiers":[]}],"titles":[{"title":"Wildlife–Vehicle Collision Monte Carlo Simulator"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/Gnacode/WILDLIFE-VEHICLE-COLLISION-MONTECARLO/tree/v2.0.0","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20313718","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v2.0.0","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"he release notes from before (major model revision, FID-draw, 40.3% headline, traffic envelope, magnetometer ablation, 13-sweep battery, unified wvc.py toolchain).","descriptionType":"Abstract"},{"description":"If you use this software or data, please cite the paper.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651892","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-06-12T00:45:34Z","registered":"2026-06-12T00:45:34Z","published":null,"updated":"2026-06-12T00:45:34Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20313718","type":"dois","attributes":{"doi":"10.5281/zenodo.20313718","identifiers":[],"creators":[{"name":"Thomsen, Lars","nameType":"Personal","givenName":"Lars","familyName":"Thomsen","affiliation":["GNACODE Inc., Medicine Hat, AB, Canada"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-1557-5646","nameIdentifierScheme":"ORCID"}]},{"name":"Makovetskyi, Sergii","nameType":"Personal","givenName":"Sergii","familyName":"Makovetskyi","affiliation":["Kharkiv National University of Radio Electronics, Ukraine"],"nameIdentifiers":[]}],"titles":[{"title":"Wildlife–Vehicle Collision Monte Carlo Simulator"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/Gnacode/WILDLIFE-VEHICLE-COLLISION-MONTECARLO/tree/v2.0.0","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20313718","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v2.0.0","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"he release notes from before (major model revision, FID-draw, 40.3% headline, traffic envelope, magnetometer ablation, 13-sweep battery, unified wvc.py toolchain).","descriptionType":"Abstract"},{"description":"If you use this software or data, please cite the paper.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20313718","contentUrl":null,"metadataVersion":2,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":4,"versionOfCount":1,"created":"2026-05-20T16:49:23Z","registered":"2026-05-20T16:49:23Z","published":null,"updated":"2026-06-12T00:45:34Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.15061623","type":"dois","attributes":{"doi":"10.5281/zenodo.15061623","identifiers":[],"creators":[{"name":"Ash O'Farrell","nameType":"Personal","familyName":"Ash O'Farrell","affiliation":["University of California Santa Cruz"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4896-1858","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"github.com/aofarrel/myco/myco_raw"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"bacteria"},{"subject":"mycobacterium-tuberculosis"},{"subject":"phylogenetics"},{"subject":"tuberculosis"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/aliases/workflow-versions/10.5281-zenodo.20651890","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/workflows/github.com/aofarrel/myco/myco_raw:7.1.0","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/api/ga4gh/trs/v2/tools/%23workflow%2Fgithub.com%2Faofarrel%2Fmyco%2Fmyco_raw/versions/7.1.0/PLAIN-WDL/descriptor/myco_raw.wdl","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.15061623","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"7.1.0","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"myco_raw\n\nmyco_raw is the version of myco to use if you already have a bunch of fastqs, divided on a per-sample basis, and you want to decontaminate them before calling variants.\n\nNotable inputs\n\nYou need your FASTQs as a nested array, where each inner array represents one sample. For example, let's say you the following samples in a google bucket located at gs://my-cool-bucket/fqs/\n\n\n\nSAMN02599053, consisting of SAMN02599053_SRR1173122_1.fq.gz, SAMN02599053_SRR1173122_2.fq.gz, SAMN02599053_SRR1173191_1.fq.gz, and SAMN02599053_SRR1173191_2.fq.gz\n\nSAMN13813990, consisting of SAMN13813990_SRR10869128_1.fq.gz and SAMN13813990_SRR10869128_2.fq.gz\n\n\nYou would input the following for paired_fastq_sets:\n\n[[\"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_2.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_2.fq.gz\"], [\"gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_1.fq.gz\", gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_2.fq.gz\"]]\n\n\nThe first array represents sample SAMN02599053. The second array represents sample SAMN13813990. You will note that SAMN02599053 has two pairs of fastqs, while SAMN13813990 only has one pair of fastqs -- this is fine!\n\nAll other inputs are documented here: inputs.md\n\nFull workflow process\n\n\n\n[0] clockwork Reference Prepare\n\nEarlier versions of this workflow ran a subworkflow that followed clockwork's reference preparation standards. This step is no longer included because the reference genome is (relatively) standardized and can therefore be put directly into downstream Docker images. We note it here for users who may wish to generate their own decontamination reference. Those users can see here for the archived subworkflow.\n\n[1] Clean and decontaminate\n\nBased on clockwork's decontamination process, which runs clockwork map_reads and clockwork remove_contam in a single WDL task. The output is a group of decontaminated fastq files.\n\nThis step will also merge FASTQs if a single sample has more than one pair of FASTQs. For example, SAMN02599053 has four fastqs associated with it:\n\n\n\nSAMN02599053_SRR1173122_1.fq.gz\n\nSAMN02599053_SRR1173122_2.fq.gz\n\nSAMN02599053_SRR1173191_1.fq.gz\n\nSAMN02599053_SRR1173191_2.fq.gz\n\n\nThe decontamination step will output a single pair: SAMN02599053_1.fastq and SAMN02599053_2.fastq\n\nAdditionally, this step will by default run fastp before decontamination takes place in order to clean the reads and perform some basic QC checks. You can flip to cleaning after decontamination by setting clean_before_decontam to false and clean_after_decontam to true. You can avoid fastp cleaning entirely by setting both of these to false, but post-decontamination QC -- as in, checking to make sure the entire sample is valid -- will run regardless.\n\n[2] Run TBProfiler\n\nRuns a sub-workflow wrapper of Thiagen's fork of TBProfiler.\n\n[3] Call variants\n\nBased on clockwork variant_call_single, which itself combines samtools, cortex, and minos. For each sample, the output is a single VCF file and a BAM file.\n\n[4] Run covstats\n\nRun covstats (from the goleft software bundle) to determine mean coverage.\n\n[5] Mask the outputs and optionally create diff files\n\nWhen feeding outputs into UShER, we want to make use of diff files. But first, we perform a little bit of data processing -- it common for some regions of the TB genome to be masked. We want to avoid those problematic regions in our final output, as well as any regions without much coverage. This task cleans up our outputs and optionally creates a diff file, one per sample, which can be used to make some happy little trees.\n\n[6] (optional) Generate UShER, Taxonium, and NextStrain trees\n\nIf decorate_trees = true, and an input tree is passed in, each sample will be placed on the tree by UShER. The resulting tree will then be converted to Taxonium format, allowing it to be viewed in taxonium. NextStrain subtree JSONs will also be generated.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.15061623","contentUrl":null,"metadataVersion":11,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":12,"versionOfCount":1,"created":"2025-03-20T22:05:22Z","registered":"2025-03-20T22:05:22Z","published":null,"updated":"2026-06-12T00:45:30Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651890","type":"dois","attributes":{"doi":"10.5281/zenodo.20651890","identifiers":[{"identifier":"oai:zenodo.org:20651890","identifierType":"oai"}],"creators":[{"name":"Ash O'Farrell","nameType":"Personal","familyName":"Ash O'Farrell","affiliation":["University of California Santa Cruz"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4896-1858","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"github.com/aofarrel/myco/myco_raw"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"bacteria"},{"subject":"mycobacterium-tuberculosis"},{"subject":"phylogenetics"},{"subject":"tuberculosis"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/aliases/workflow-versions/10.5281-zenodo.20651890","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/workflows/github.com/aofarrel/myco/myco_raw:7.1.0","relatedIdentifierType":"URL"},{"relationType":"IsIdenticalTo","relatedIdentifier":"https://dockstore.org/api/ga4gh/trs/v2/tools/%23workflow%2Fgithub.com%2Faofarrel%2Fmyco%2Fmyco_raw/versions/7.1.0/PLAIN-WDL/descriptor/myco_raw.wdl","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.15061623","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"7.1.0","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"myco_raw\n\nmyco_raw is the version of myco to use if you already have a bunch of fastqs, divided on a per-sample basis, and you want to decontaminate them before calling variants.\n\nNotable inputs\n\nYou need your FASTQs as a nested array, where each inner array represents one sample. For example, let's say you the following samples in a google bucket located at gs://my-cool-bucket/fqs/\n\n\n\nSAMN02599053, consisting of SAMN02599053_SRR1173122_1.fq.gz, SAMN02599053_SRR1173122_2.fq.gz, SAMN02599053_SRR1173191_1.fq.gz, and SAMN02599053_SRR1173191_2.fq.gz\n\nSAMN13813990, consisting of SAMN13813990_SRR10869128_1.fq.gz and SAMN13813990_SRR10869128_2.fq.gz\n\n\nYou would input the following for paired_fastq_sets:\n\n[[\"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173122_2.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_1.fq.gz\", \"gs://my-cool-bucket/fqs/SAMN02599053_SRR1173191_2.fq.gz\"], [\"gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_1.fq.gz\", gs://my-cool-bucket/fqs/SAMN13813990_SRR10869128_2.fq.gz\"]]\n\n\nThe first array represents sample SAMN02599053. The second array represents sample SAMN13813990. You will note that SAMN02599053 has two pairs of fastqs, while SAMN13813990 only has one pair of fastqs -- this is fine!\n\nAll other inputs are documented here: inputs.md\n\nFull workflow process\n\n\n\n[0] clockwork Reference Prepare\n\nEarlier versions of this workflow ran a subworkflow that followed clockwork's reference preparation standards. This step is no longer included because the reference genome is (relatively) standardized and can therefore be put directly into downstream Docker images. We note it here for users who may wish to generate their own decontamination reference. Those users can see here for the archived subworkflow.\n\n[1] Clean and decontaminate\n\nBased on clockwork's decontamination process, which runs clockwork map_reads and clockwork remove_contam in a single WDL task. The output is a group of decontaminated fastq files.\n\nThis step will also merge FASTQs if a single sample has more than one pair of FASTQs. For example, SAMN02599053 has four fastqs associated with it:\n\n\n\nSAMN02599053_SRR1173122_1.fq.gz\n\nSAMN02599053_SRR1173122_2.fq.gz\n\nSAMN02599053_SRR1173191_1.fq.gz\n\nSAMN02599053_SRR1173191_2.fq.gz\n\n\nThe decontamination step will output a single pair: SAMN02599053_1.fastq and SAMN02599053_2.fastq\n\nAdditionally, this step will by default run fastp before decontamination takes place in order to clean the reads and perform some basic QC checks. You can flip to cleaning after decontamination by setting clean_before_decontam to false and clean_after_decontam to true. You can avoid fastp cleaning entirely by setting both of these to false, but post-decontamination QC -- as in, checking to make sure the entire sample is valid -- will run regardless.\n\n[2] Run TBProfiler\n\nRuns a sub-workflow wrapper of Thiagen's fork of TBProfiler.\n\n[3] Call variants\n\nBased on clockwork variant_call_single, which itself combines samtools, cortex, and minos. For each sample, the output is a single VCF file and a BAM file.\n\n[4] Run covstats\n\nRun covstats (from the goleft software bundle) to determine mean coverage.\n\n[5] Mask the outputs and optionally create diff files\n\nWhen feeding outputs into UShER, we want to make use of diff files. But first, we perform a little bit of data processing -- it common for some regions of the TB genome to be masked. We want to avoid those problematic regions in our final output, as well as any regions without much coverage. This task cleans up our outputs and optionally creates a diff file, one per sample, which can be used to make some happy little trees.\n\n[6] (optional) Generate UShER, Taxonium, and NextStrain trees\n\nIf decorate_trees = true, and an input tree is passed in, each sample will be placed on the tree by UShER. The resulting tree will then be converted to Taxonium format, allowing it to be viewed in taxonium. NextStrain subtree JSONs will also be generated.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651890","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:45:30Z","registered":"2026-06-12T00:45:30Z","published":null,"updated":"2026-06-12T00:45:30Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651886","type":"dois","attributes":{"doi":"10.5281/zenodo.20651886","identifiers":[{"identifier":"oai:zenodo.org:20651886","identifierType":"oai"}],"creators":[{"name":"Zhang, Zijin","nameType":"Personal","givenName":"Zijin","familyName":"Zhang","nameIdentifiers":[{"nameIdentifier":"0000-0002-9968-067X","nameIdentifierScheme":"ORCID"}],"affiliation":[]}],"titles":[{"title":"CDFDatasets.jl"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"Julia"},{"subject":"Space physics"},{"subject":"Common Data Format"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/JuliaSpacePhysics/CDFDatasets.jl/tree/v0.2.2","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.17517175","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v0.2.2","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"CDFDatasets v0.2.2\n\nDiff since v0.2.1\n\nMerged pull requests:\n\n\n\nbuild: bump CommonDataFormat compat to 0.2 (#49) (@Beforerr)","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651886","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:43:14Z","registered":"2026-06-12T00:43:15Z","published":null,"updated":"2026-06-12T00:43:15Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.17517175","type":"dois","attributes":{"doi":"10.5281/zenodo.17517175","identifiers":[],"creators":[{"name":"Zhang, Zijin","nameType":"Personal","givenName":"Zijin","familyName":"Zhang","nameIdentifiers":[{"nameIdentifier":"0000-0002-9968-067X","nameIdentifierScheme":"ORCID"}],"affiliation":[]}],"titles":[{"title":"CDFDatasets.jl"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"Julia"},{"subject":"Space physics"},{"subject":"Common Data Format"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/JuliaSpacePhysics/CDFDatasets.jl/tree/v0.2.2","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.17517175","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v0.2.2","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"CDFDatasets v0.2.2\n\nDiff since v0.2.1\n\nMerged pull requests:\n\n\n\nbuild: bump CommonDataFormat compat to 0.2 (#49) (@Beforerr)","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.17517175","contentUrl":null,"metadataVersion":15,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":15,"versionOfCount":1,"created":"2025-11-03T20:13:54Z","registered":"2025-11-03T20:13:55Z","published":null,"updated":"2026-06-12T00:43:14Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651885","type":"dois","attributes":{"doi":"10.5281/zenodo.20651885","identifiers":[{"identifier":"oai:zenodo.org:20651885","identifierType":"oai"}],"creators":[{"name":"Ward, William","nameType":"Personal","givenName":"William","familyName":"Ward","affiliation":["Ward Software Defined Systems LLC"],"nameIdentifiers":[{"nameIdentifier":"0009-0004-4966-6644","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"The Epoch Project: Epochs as Bounded Invariant-Persistence Intervals"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"epoch"},{"subject":"invariant"},{"subject":"identity"},{"subject":"automata theory"},{"subject":"state machine"},{"subject":"boundary condition"},{"subject":"soul invariant"},{"subject":"persistence"},{"subject":"continuity"},{"subject":"research framework"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/Ward-Software-Defined-Systems/Epoch-Project/tree/v1.0.1","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651796","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v1.0.1","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"The Epoch Project is a documentation research framework that reframes an \"epoch\" as a bounded interval of reality defined not by duration but by the persistence of a verifiable boundary condition - a \"soul invariant\" (psi) re-checked at every transition. It models this as a six-tuple automaton E = (S, Sigma, delta, s0, F, psi) observed by a meta-level \"Ark,\" and explores the framework across discrete, continuous-manifold, branching-manifold, and substrate (recursive-nesting / the Void) derivations. The central open problem - making psi history- or trajectory-dependent - is stated as the framework's main formal lever.","descriptionType":"Abstract"},{"description":"If you use or build on this framework, please cite it as below.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651885","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:42:58Z","registered":"2026-06-12T00:42:59Z","published":null,"updated":"2026-06-12T00:42:59Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651796","type":"dois","attributes":{"doi":"10.5281/zenodo.20651796","identifiers":[],"creators":[{"name":"Ward, William","nameType":"Personal","givenName":"William","familyName":"Ward","affiliation":["Ward Software Defined Systems LLC"],"nameIdentifiers":[{"nameIdentifier":"0009-0004-4966-6644","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"The Epoch Project: Epochs as Bounded Invariant-Persistence Intervals"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"epoch"},{"subject":"invariant"},{"subject":"identity"},{"subject":"automata theory"},{"subject":"state machine"},{"subject":"boundary condition"},{"subject":"soul invariant"},{"subject":"persistence"},{"subject":"continuity"},{"subject":"research framework"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/Ward-Software-Defined-Systems/Epoch-Project/tree/v1.0.1","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651796","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v1.0.1","rightsList":[{"rights":"MIT License","rightsUri":"https://opensource.org/licenses/MIT","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"mit","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"The Epoch Project is a documentation research framework that reframes an \"epoch\" as a bounded interval of reality defined not by duration but by the persistence of a verifiable boundary condition - a \"soul invariant\" (psi) re-checked at every transition. It models this as a six-tuple automaton E = (S, Sigma, delta, s0, F, psi) observed by a meta-level \"Ark,\" and explores the framework across discrete, continuous-manifold, branching-manifold, and substrate (recursive-nesting / the Void) derivations. The central open problem - making psi history- or trajectory-dependent - is stated as the framework's main formal lever.","descriptionType":"Abstract"},{"description":"If you use or build on this framework, please cite it as below.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651796","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":3,"versionOfCount":1,"created":"2026-06-12T00:35:26Z","registered":"2026-06-12T00:35:26Z","published":null,"updated":"2026-06-12T00:42:58Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651862","type":"dois","attributes":{"doi":"10.5281/zenodo.20651862","identifiers":[{"identifier":"oai:zenodo.org:20651862","identifierType":"oai"}],"creators":[{"name":"Grier, David G.","nameType":"Personal","givenName":"David G.","familyName":"Grier","affiliation":["New York University"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-4382-5139","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"QVideo"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"camera"},{"subject":"video"},{"subject":"imaging"},{"subject":"PyQt5"},{"subject":"scientific"},{"subject":"GenICam"},{"subject":"GigE Vision"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/davidgrier/QVideo/tree/v3.16.4","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.19239402","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v3.16.4","rightsList":[{"rights":"GNU General Public License v3.0 or later","rightsUri":"https://www.gnu.org/licenses/gpl-3.0-standalone.html","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"gpl-3.0+","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"PyQt-based framework for integrating scientific cameras into research applications. Provides hardware abstraction, threading, property introspection, UI generation, image filtering, and digital video recording.","descriptionType":"Abstract"},{"description":"If you use this software, please cite it as below.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651862","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-06-12T00:41:15Z","registered":"2026-06-12T00:41:15Z","published":null,"updated":"2026-06-12T00:41:15Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.19239402","type":"dois","attributes":{"doi":"10.5281/zenodo.19239402","identifiers":[],"creators":[{"name":"Grier, David G.","nameType":"Personal","givenName":"David G.","familyName":"Grier","affiliation":["New York University"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-4382-5139","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"QVideo"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"camera"},{"subject":"video"},{"subject":"imaging"},{"subject":"PyQt5"},{"subject":"scientific"},{"subject":"GenICam"},{"subject":"GigE Vision"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/davidgrier/QVideo/tree/v3.16.4","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.19239402","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"v3.16.4","rightsList":[{"rights":"GNU General Public License v3.0 or later","rightsUri":"https://www.gnu.org/licenses/gpl-3.0-standalone.html","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"gpl-3.0+","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"PyQt-based framework for integrating scientific cameras into research applications. Provides hardware abstraction, threading, property introspection, UI generation, image filtering, and digital video recording.","descriptionType":"Abstract"},{"description":"If you use this software, please cite it as below.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.19239402","contentUrl":null,"metadataVersion":27,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":27,"versionOfCount":1,"created":"2026-03-26T17:45:40Z","registered":"2026-03-26T17:45:40Z","published":null,"updated":"2026-06-12T00:41:15Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.6084/m9.figshare.32654100","type":"dois","attributes":{"doi":"10.6084/m9.figshare.32654100","identifiers":[],"creators":[{"name":"Christoph, Adelbert","givenName":"Adelbert","familyName":"Christoph","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"School of Basic Midwifery, AEFUTHA 2026/2027 Form Is Out Now Call 08148045378 (+2348148045378) To Apply Call The Office Of The Admin (+2348148045378) For Further Information On How To Make Your Proper Registration Before The Closing Date For Admission Assistance Call 08148045378"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Other creative arts and writing not elsewhere classified","schemeUri":"http://www.abs.gov.au/ausstats/abs@.nsf/0/6BB427AB9696C225CA2574180004463E","subjectScheme":"ANZSRC Fields of Research","classificationCode":"369999"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Created"},{"date":"2026-06-12","dateType":"Updated"},{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"Software","resourceTypeGeneral":"Software"},"relatedIdentifiers":[],"relatedItems":[],"sizes":["12658 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"School of Basic Midwifery, AEFUTHA 2026/2027 Form Is Out Now Call 08148045378 (+2348148045378) To Apply Call The Office Of The Admin (+2348148045378) For Further Information On How To Make Your Proper Registration Before The Closing Date For Admission Assistance Call 08148045378","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://figshare.com/articles/software/School_of_Basic_Midwifery_AEFUTHA_2026_2027_Form_Is_Out_Now_Call_08148045378_2348148045378_To_Apply_Call_The_Office_Of_The_Admin_2348148045378_For_Further_Information_On_How_To_Make_Your_Proper_Registration_Before_The_Closing_Date_For_Admis/32654100","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:40:29Z","registered":"2026-06-12T00:40:30Z","published":null,"updated":"2026-06-12T00:40:30Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.32654100.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.32654100.v1","identifiers":[],"creators":[{"name":"Christoph, Adelbert","givenName":"Adelbert","familyName":"Christoph","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"School of Basic Midwifery, AEFUTHA 2026/2027 Form Is Out Now Call 08148045378 (+2348148045378) To Apply Call The Office Of The Admin (+2348148045378) For Further Information On How To Make Your Proper Registration Before The Closing Date For Admission Assistance Call 08148045378"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Other creative arts and writing not elsewhere classified","schemeUri":"http://www.abs.gov.au/ausstats/abs@.nsf/0/6BB427AB9696C225CA2574180004463E","subjectScheme":"ANZSRC Fields of Research","classificationCode":"369999"}],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Created"},{"date":"2026-06-12","dateType":"Updated"},{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"Software","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.32654100","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["12658 Bytes"],"formats":[],"version":"1","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"School of Basic Midwifery, AEFUTHA 2026/2027 Form Is Out Now Call 08148045378 (+2348148045378) To Apply Call The Office Of The Admin (+2348148045378) For Further Information On How To Make Your Proper Registration Before The Closing Date For Admission Assistance Call 08148045378","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://figshare.com/articles/software/School_of_Basic_Midwifery_AEFUTHA_2026_2027_Form_Is_Out_Now_Call_08148045378_2348148045378_To_Apply_Call_The_Office_Of_The_Admin_2348148045378_For_Further_Information_On_How_To_Make_Your_Proper_Registration_Before_The_Closing_Date_For_Admis/32654100/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-06-12T00:40:29Z","registered":"2026-06-12T00:40:30Z","published":null,"updated":"2026-06-12T00:40:30Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.5281/zenodo.20651826","type":"dois","attributes":{"doi":"10.5281/zenodo.20651826","identifiers":[],"creators":[{"name":"Cursor Agent","nameType":"Personal","familyName":"Cursor Agent","nameIdentifiers":[],"affiliation":[]},{"name":"Mankirat Singh Cheema","nameType":"Personal","familyName":"Mankirat Singh Cheema","nameIdentifiers":[],"affiliation":[]}],"titles":[{"title":"Mankirat47/Dao-Heart-3.15: Dao-Heart-3.15"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/Mankirat47/Dao-Heart-3.15/tree/3.15","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651826","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"3.15","rightsList":[{"rights":"Apache License 2.0","rightsUri":"http://www.apache.org/licenses/LICENSE-2.0","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"apache-2.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"Dao Heart v3.15 is an inspectable symbolic value governance and AI oversight research scaffold, combining Lighthouse perception, sovereignty aware review, narrative/value grounding, and reproducible audits. Research only, not production safety or proof of alignment.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651826","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":2,"versionOfCount":1,"created":"2026-06-12T00:37:42Z","registered":"2026-06-12T00:37:43Z","published":null,"updated":"2026-06-12T00:37:43Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.20651827","type":"dois","attributes":{"doi":"10.5281/zenodo.20651827","identifiers":[{"identifier":"oai:zenodo.org:20651827","identifierType":"oai"}],"creators":[{"name":"Cursor Agent","nameType":"Personal","familyName":"Cursor Agent","nameIdentifiers":[],"affiliation":[]},{"name":"Mankirat Singh Cheema","nameType":"Personal","familyName":"Mankirat Singh Cheema","nameIdentifiers":[],"affiliation":[]}],"titles":[{"title":"Mankirat47/Dao-Heart-3.15: Dao-Heart-3.15"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[],"contributors":[],"dates":[{"date":"2026-06-12","dateType":"Issued"}],"language":null,"types":{"ris":"COMP","bibtex":"misc","citeproc":"article","schemaOrg":"SoftwareSourceCode","resourceType":"","resourceTypeGeneral":"Software"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"https://github.com/Mankirat47/Dao-Heart-3.15/tree/3.15","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.20651826","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"3.15","rightsList":[{"rights":"Apache License 2.0","rightsUri":"http://www.apache.org/licenses/LICENSE-2.0","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"apache-2.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"Dao Heart v3.15 is an inspectable symbolic value governance and AI oversight research scaffold, combining Lighthouse perception, sovereignty aware review, narrative/value grounding, and reproducible audits. Research only, not production safety or proof of alignment.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.20651827","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-06-12T00:37:42Z","registered":"2026-06-12T00:37:42Z","published":null,"updated":"2026-06-12T00:37:42Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}}],"meta":{"total":931248,"totalPages":400,"page":1,"states":[{"id":"findable","title":"Findable","count":931248}],"resourceTypes":[{"id":"software","title":"Software","count":931248}],"created":[{"id":"2026","title":"2026","count":153729},{"id":"2025","title":"2025","count":185651},{"id":"2024","title":"2024","count":128402},{"id":"2023","title":"2023","count":111492},{"id":"2022","title":"2022","count":97363},{"id":"2021","title":"2021","count":80133},{"id":"2020","title":"2020","count":57639},{"id":"2019","title":"2019","count":39117},{"id":"2018","title":"2018","count":29326},{"id":"2017","title":"2017","count":28001}],"published":[{"id":"2026","title":"2026","count":160804},{"id":"2025","title":"2025","count":181968},{"id":"2024","title":"2024","count":128930},{"id":"2023","title":"2023","count":110331},{"id":"2022","title":"2022","count":94242},{"id":"2021","title":"2021","count":80153},{"id":"2020","title":"2020","count":57091},{"id":"2019","title":"2019","count":39098},{"id":"2018","title":"2018","count":29084},{"id":"2017","title":"2017","count":24427},{"id":"2016","title":"2016","count":11479},{"id":"2015","title":"2015","count":6322},{"id":"2014","title":"2014","count":3829},{"id":"2013","title":"2013","count":631},{"id":"2012","title":"2012","count":279},{"id":"2011","title":"2011","count":368},{"id":"2010","title":"2010","count":345}],"registered":[{"id":"2026","title":"2026","count":153528},{"id":"2025","title":"2025","count":185688},{"id":"2024","title":"2024","count":128412},{"id":"2023","title":"2023","count":111392},{"id":"2022","title":"2022","count":97322},{"id":"2021","title":"2021","count":80116},{"id":"2020","title":"2020","count":57599},{"id":"2019","title":"2019","count":39115},{"id":"2018","title":"2018","count":29321},{"id":"2017","title":"2017","count":27994}],"providers":[{"id":"cern","title":"CERN - European Organization for Nuclear Research","count":848735},{"id":"otjm","title":"Figshare Internal","count":38008},{"id":"ocean","title":"Code Ocean","count":9024},{"id":"doe","title":"Department of Energy (DOE)","count":5827},{"id":"nihod","title":"National Institutes of Health, Office of the Director (NIH OD)","count":4538},{"id":"purdue","title":"Purdue University West Lafayette","count":4212},{"id":"xklm","title":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH","count":2770},{"id":"kim","title":"Knowledgebase of Interatomic Models","count":2336},{"id":"scpr","title":"4TU.ResearchData","count":1195},{"id":"stdp","title":"ETH Zurich","count":1076}],"clients":[{"id":"cern.zenodo","title":"Zenodo","count":848707},{"id":"figshare.ars","title":"figshare Academic Research System","count":37980},{"id":"ocean.ocean","title":"Code Ocean","count":9024},{"id":"doe.osti","title":"DOE Office of Scientific and Technical Information (OSTI) Repository","count":5827},{"id":"nihod.bioc","title":"NCI BioConductor","count":4494},{"id":"purdue.hubzero","title":"HubZero","count":4212},{"id":"xklm.wejabm","title":"European Language Grid","count":2770},{"id":"kim.openkim","title":"Open Knowledgebase of Interatomic Models (OpenKIM)","count":2336},{"id":"delft.data4tu","title":"4TU.ResearchData","count":1195},{"id":"brainl.iu","title":"brainlife.io","count":1001}],"affiliations":[{"id":"ror.org/052gg0110","title":"University of Oxford","count":771},{"id":"ror.org/02e2c7k09","title":"Delft University of Technology","count":766},{"id":"ror.org/05a28rw58","title":"ETH Zurich","count":695},{"id":"ror.org/05591te55","title":"Ludwig-Maximilians-Universität München","count":654},{"id":"ror.org/04t3en479","title":"Karlsruhe Institute of Technology","count":626},{"id":"ror.org/02jx3x895","title":"University College London","count":543},{"id":"ror.org/035a68863","title":"United States Geological Survey","count":526},{"id":"ror.org/04xfq0f34","title":"RWTH Aachen University","count":512},{"id":"ror.org/02kkvpp62","title":"Technical University of Munich","count":479},{"id":"ror.org/042nb2s44","title":"Massachusetts Institute of Technology","count":458}],"prefixes":[{"id":"10.5281","title":"10.5281","count":848711},{"id":"10.6084","title":"10.6084","count":37983},{"id":"10.24433","title":"10.24433","count":9024},{"id":"10.11578","title":"10.11578","count":5827},{"id":"10.18129","title":"10.18129","count":4568},{"id":"10.57771","title":"10.57771","count":2770},{"id":"10.4231","title":"10.4231","count":2554},{"id":"10.25950","title":"10.25950","count":2336},{"id":"10.21981","title":"10.21981","count":1658},{"id":"10.4121","title":"10.4121","count":1195}],"certificates":[{"id":"CoreTrustSeal","title":"Core Trust Seal","count":1355},{"id":"DINI","title":"Dini","count":9},{"id":"RatSWD","title":"Rat Swd","count":7},{"id":"DIN 31644","title":"Din 31644","count":1},{"id":"WDS","title":"Wds","count":1}],"licenses":[{"id":"cc-by-4.0","title":"CC-BY-4.0","count":327690},{"id":"mit","title":"MIT","count":145676},{"id":"apache-2.0","title":"Apache-2.0","count":37298},{"id":"gpl-3.0","title":"GPL-3.0","count":27660},{"id":"bsd-3-clause","title":"BSD-3-clause","count":16736},{"id":"gpl-3.0+","title":"gpl-3.0+","count":11012},{"id":"cc0-1.0","title":"CC0-1.0","count":6439},{"id":"eupl-1.1","title":"EUPL-1.1","count":5891},{"id":"agpl-3.0-only","title":"agpl-3.0-only","count":4469},{"id":"mpl-2.0","title":"MPL-2.0","count":3768}],"schemaVersions":[{"id":"4","title":"Schema 4","count":889690},{"id":"2.2","title":"Schema 2.2","count":817},{"id":"3","title":"Schema 3","count":401},{"id":"V1","title":"Schema V1","count":207},{"id":"V2","title":"Schema V2","count":35},{"id":"V3","title":"Schema V3","count":15},{"id":"4.1/metadata.xsd","title":"Schema 4.1/metadata.xsd","count":3},{"id":"4.6","title":"Schema 4.6","count":2},{"id":"V4","title":"Schema V4","count":2},{"id":"4.6/","title":"Schema 4.6/","count":2}],"linkChecksStatus":[{"id":"200","title":"200","count":8779},{"id":"404","title":"404","count":157},{"id":"403","title":"403","count":8},{"id":"503","title":"503","count":5},{"id":"401","title":"401","count":1},{"id":"500","title":"500","count":1},{"id":"502","title":"502","count":1}],"subjects":[{"id":"Capsule","title":"Capsule","count":8981},{"id":"python","title":"Python","count":6648},{"id":"Java","title":"Java","count":6049},{"id":"FOS: Computer and information sciences","title":"Fos: Computer And Information Sciences","count":5945},{"id":"gCube","title":"G Cube","count":5827},{"id":"Python","title":"Python","count":5790},{"id":"Data Management System","title":"Data Management System","count":5760},{"id":"Hybrid Data Infrastructure","title":"Hybrid Data Infrastructure","count":5760},{"id":"machine learning","title":"Machine Learning","count":3309},{"id":"FOS: Biological sciences","title":"Fos: Biological Sciences","count":3201}],"fieldsOfScience":[{"id":"computer_and_information_sciences","title":"Computer and information sciences","count":5945},{"id":"biological_sciences","title":"Biological sciences","count":3201},{"id":"mathematics","title":"Mathematics","count":1821},{"id":"earth_and_related_environmental_sciences","title":"Earth and related environmental sciences","count":1611},{"id":"physical_sciences","title":"Physical sciences","count":1108},{"id":"psychology","title":"Psychology","count":671},{"id":"clinical_medicine","title":"Clinical medicine","count":600},{"id":"health_sciences","title":"Health sciences","count":517},{"id":"electrical_engineering_electronic_engineering_information_engineering","title":"Electrical engineering, electronic engineering, information engineering","count":498},{"id":"mechanical_engineering","title":"Mechanical engineering","count":461}],"citations":[],"views":[{"id":"2030","title":"2030","count":6}],"downloads":[{"id":"2030","title":"2030","count":1}]},"links":{"self":"https://api.datacite.org/dois?disable-facets=false\u0026resource-type-id=software","next":"https://api.datacite.org/dois?disable-facets=false\u0026page%5Bnumber%5D=2\u0026page%5Bsize%5D=25\u0026resource-type-id=software"}}