{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2021-04-22T12:22:34.230708+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 22, "enabled": true, "entries": { "01_Genome_correction_pipeline.tar.gz": { "checksum": "md5:e77696985f1506f6ede8e04724ae36a1", "ext": "gz", "id": "63f14424-08ae-4b7a-add6-5cec9c633bfc", "key": "01_Genome_correction_pipeline.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 71942332 }, "01_Genome_correction_pipeline_complete_tree.txt": { "checksum": "md5:5468c0ee0ea61b468f351d24e4907c99", "ext": "txt", "id": "cbf426d9-3799-4014-a519-23785d33a480", "key": "01_Genome_correction_pipeline_complete_tree.txt", "metadata": null, "mimetype": "text/plain", "size": 219968 }, "02_Genome_phasing_pipeline.tar.gz": { "checksum": "md5:57aafcf8e64fc8c3fcb520b68805f673", "ext": "gz", "id": "1aa2a9f0-f660-4d1a-95a0-17ae04cd9814", "key": "02_Genome_phasing_pipeline.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 38111382 }, "02_Genome_phasing_pipeline_complete_tree.txt": { "checksum": "md5:25422d45a4bc8ba87d87bc68f3f15626", "ext": "txt", "id": "80030854-eaf4-4f8c-b0a8-ff116befe56b", "key": "02_Genome_phasing_pipeline_complete_tree.txt", "metadata": null, "mimetype": "text/plain", "size": 804610 }, "03_Annotate_genome_pipeline.tar.gz": { "checksum": "md5:d3d8755aeef83f0eccd5b7fb30cb3d44", "ext": "gz", "id": "3e373068-7b68-48bf-afda-4987e3096883", "key": "03_Annotate_genome_pipeline.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 68589620 }, "04_Genome_annotation_conversion_v9.9_to_v10.tar.gz": { "checksum": "md5:3700033efc1f10caffba38f9653f88e7", "ext": "gz", "id": "923b77cd-c240-40a3-9cf2-0d6f9bf475ac", "key": "04_Genome_annotation_conversion_v9.9_to_v10.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 163634861 }, "05_Intron_annotation_correction.tar.gz": { "checksum": "md5:a7baa33efffe4ba1ab406a8bf5ea5ec1", "ext": "gz", "id": "24d301c2-c2f0-43f9-94cd-55f476a4337e", "key": "05_Intron_annotation_correction.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 47010946 }, "06_Fully_phased_scaffold.tar.gz": { "checksum": "md5:c7718d04a838b01c075afad3e8fbf923", "ext": "gz", "id": "d84d896b-4b56-469e-8f21-6c46e84d8646", "key": "06_Fully_phased_scaffold.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 59538542 }, "07_Pre-processing_Annotation_comparison_among_genome_versions.tar.gz": { "checksum": "md5:f056df71010d256c304d766f87569d64", "ext": "gz", "id": "0366e381-6afb-48a9-87d4-8260ff3444f0", "key": "07_Pre-processing_Annotation_comparison_among_genome_versions.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 200414056 }, "08_Compare_annotated_proteome.tar.gz": { "checksum": "md5:731a9e4e7c24a328bc60ab0f4f900a3c", "ext": "gz", "id": "b581226a-dfe2-4bca-8a4b-1673caca5a87", "key": "08_Compare_annotated_proteome.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 5166307 }, "09_Pre-processing_variant_density_and_ploidy_assessment.tar.gz": { "checksum": "md5:b2385a982665d2caf43eef939c6750a2", "ext": "gz", "id": "9e84cd79-dd36-4b98-bd2a-d6da915b209a", "key": "09_Pre-processing_variant_density_and_ploidy_assessment.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 47273077 }, "09_Pre-processing_variant_density_and_ploidy_assessment_complete_tree.txt": { "checksum": "md5:1b9c62431eb7c42874dcd97eac956b9e", "ext": "txt", "id": "e8f0de04-189b-4183-b966-d877977c95ca", "key": "09_Pre-processing_variant_density_and_ploidy_assessment_complete_tree.txt", "metadata": null, "mimetype": "text/plain", "size": 1163732 }, "10_Variant_density_and_ploidy_analysis.tar.gz": { "checksum": "md5:244ae000b809e666177b935edadc1e80", "ext": "gz", "id": "9406f1c1-a304-4758-bef5-85c53783f553", "key": "10_Variant_density_and_ploidy_analysis.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 35975076 }, "11_Transcription_and_translation_in_aneuploid_clones.tar.gz": { "checksum": "md5:ab3027dbbd93e9b99e5271562e440493", "ext": "gz", "id": "9e18c36e-b620-4226-a9be-990910f430fb", "key": "11_Transcription_and_translation_in_aneuploid_clones.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 19335263 }, "11_Transcription_and_translation_in_aneuploid_clones_complete_tree.txt": { "checksum": "md5:6f782cc5a1656c195c2700bb9f3dfa0e", "ext": "txt", "id": "2f6dc3d5-ff1d-496b-860a-9cdff09c6263", "key": "11_Transcription_and_translation_in_aneuploid_clones_complete_tree.txt", "metadata": null, "mimetype": "text/plain", "size": 22357 }, "12_Pre-processing_expression_in_allele_specific_truncated_genes.tar.gz": { "checksum": "md5:c0360d4511f8bd85e629fb848cb3c7f1", "ext": "gz", "id": "4f484e39-0e59-4587-9c33-c959bb513cb9", "key": "12_Pre-processing_expression_in_allele_specific_truncated_genes.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 38330783 }, "12_Pre-processing_expression_in_allele_specific_truncated_genes_complete_tree.txt": { "checksum": "md5:83f744d2ed65a96b32f39be2ac383e39", "ext": "txt", "id": "4008bb62-01f3-4cef-94e6-dbf88793c407", "key": "12_Pre-processing_expression_in_allele_specific_truncated_genes_complete_tree.txt", "metadata": null, "mimetype": "text/plain", "size": 4034 }, "13_Expression_on_genes_with_allele_specific_premature_termination_codons.tar.gz": { "checksum": "md5:053d5b5fdba9bb4ff16c7e6e057f4d4c", "ext": "gz", "id": "131ade84-5915-4ebf-bfc4-2bb79002fc63", "key": "13_Expression_on_genes_with_allele_specific_premature_termination_codons.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 5719887 }, "14_HiC_on_genome_with_phased_core.tar.gz": { "checksum": "md5:616279c200e6c6d9752ad239a5c3b26d", "ext": "gz", "id": "04eacc9e-b086-4c58-bd29-c8f79c911935", "key": "14_HiC_on_genome_with_phased_core.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 92500816 }, "14_HiC_on_genome_with_phased_core_complete_tree.txt": { "checksum": "md5:30abcd59d702f508961e49258c0643bc", "ext": "txt", "id": "e8771aee-38fe-44b8-9d15-6e4b032c9e20", "key": "14_HiC_on_genome_with_phased_core_complete_tree.txt", "metadata": null, "mimetype": "text/plain", "size": 18651 }, "Genome_versions_and_annotation_files.zip": { "checksum": "md5:aedbe2cb1c689d0b33b1d7018aa55103", "ext": "zip", "id": "6af02ca3-ea84-4037-af0c-8c4a6830874e", "key": "Genome_versions_and_annotation_files.zip", "metadata": null, "mimetype": "application/zip", "size": 131912877 }, "Supplementary_Tables.zip": { "checksum": "md5:abe5b800f12f126f6daba140785da616", "ext": "zip", "id": "c68c5b09-7edc-4faf-aec6-16f1a0f914e3", "key": "Supplementary_Tables.zip", "metadata": null, "mimetype": "application/zip", "size": 759647 } }, "order": [], "total_bytes": 1028448824 }, "id": "4674608", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/4674608/access", "access_links": "https://zenodo.org/api/records/4674608/access/links", "access_request": "https://zenodo.org/api/records/4674608/access/request", "access_users": "https://zenodo.org/api/records/4674608/access/users", "archive": "https://zenodo.org/api/records/4674608/files-archive", "archive_media": "https://zenodo.org/api/records/4674608/media-files-archive", "communities": "https://zenodo.org/api/records/4674608/communities", "communities-suggestions": "https://zenodo.org/api/records/4674608/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.4674608", "draft": "https://zenodo.org/api/records/4674608/draft", "files": "https://zenodo.org/api/records/4674608/files", "latest": "https://zenodo.org/api/records/4674608/versions/latest", "latest_html": "https://zenodo.org/records/4674608/latest", "media_files": "https://zenodo.org/api/records/4674608/media-files", "parent": "https://zenodo.org/api/records/4674607", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.4674607", "parent_html": "https://zenodo.org/records/4674607", "requests": "https://zenodo.org/api/records/4674608/requests", "reserve_doi": "https://zenodo.org/api/records/4674608/draft/pids/doi", "self": "https://zenodo.org/api/records/4674608", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.4674608", "self_html": "https://zenodo.org/records/4674608", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:4674608/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:4674608/sequence/default", "versions": "https://zenodo.org/api/records/4674608/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "additional_descriptions": [ { "description": "The work was funded by an ERC Starting Grant (3D_Tryps 715466). R.O.C was supported by a Georg Forster Fellowship (Humboldt Foundation).", "type": { "id": "notes", "title": { "de": "Anmerkungen", "en": "Notes" } } } ], "creators": [ { "affiliations": [ { "name": "Department of Veterinary Sciences, Experimental Parasitology, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Lena-Christ-Str. 48, 82152 Planegg-Martinsried, Germany; Biomedical Center Munich, Department of Physiological Chemistry, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Gro\u00dfhaderner Str. 9, 82152 Planegg-Martinsried, Germany" } ], "person_or_org": { "family_name": "Cosentino", "given_name": "Ra\u00fal Oscar", "identifiers": [ { "identifier": "0000-0003-2124-8198", "scheme": "orcid" } ], "name": "Cosentino, Ra\u00fal Oscar", "type": "personal" } }, { "affiliations": [ { "name": "Department of Veterinary Sciences, Experimental Parasitology, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Lena-Christ-Str. 48, 82152 Planegg-Martinsried, Germany; Biomedical Center Munich, Department of Physiological Chemistry, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Gro\u00dfhaderner Str. 9, 82152 Planegg-Martinsried, Germany" } ], "person_or_org": { "family_name": "Brink", "given_name": "Benedikt", "identifiers": [ { "identifier": "0000-0002-2291-8870", "scheme": "orcid" } ], "name": "Brink, Benedikt", "type": "personal" } }, { "affiliations": [ { "name": "Department of Veterinary Sciences, Experimental Parasitology, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Lena-Christ-Str. 48, 82152 Planegg-Martinsried, Germany; Biomedical Center Munich, Department of Physiological Chemistry, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Gro\u00dfhaderner Str. 9, 82152 Planegg-Martinsried, Germany" } ], "person_or_org": { "family_name": "Siegel", "given_name": "T. Nicolai", "identifiers": [ { "identifier": "0000-0002-1715-7907", "scheme": "orcid" } ], "name": "Siegel, T. Nicolai", "type": "personal" } } ], "description": "
This repository contains the data analysis workflows, the supplementary tables and genome and annotation version from the manuscript entitled "A phased genome assembly for allele-specific analysis in Trypanosoma brucei" https://doi.org/10.1101/2021.04.13.439624
\n\nDue to space limitations in Zenodo, for some workflows, full datasets could not be uploaded. For those workflows we provide the directory tree of the complete data analysis folder.
\n\nAbstract
\n\nMany eukaryotic organisms are diploid or even polyploid, i.e. they harbour two or more independent copies of each chromosome. Yet, to date most reference genome assemblies represent a mosaic consensus sequence in which the homologous chromosomes have been collapsed into one sequence. This procedure generates sequence artefacts and impedes analyses of allele-specific mechanisms. Here, we report the allele-specific genome assembly of the diploid unicellular protozoan parasite Trypanosoma brucei.
\n\nAs a first step, we called variants on the allele-collapsed assembly of the T. brucei Lister 427 isolate using short-read error-corrected PacBio reads. We identified ~96 thousand heterozygote variants across the genome (average of 4.2 variants / kb), and observed that the variant density along the chromosomes was highly uneven. Several long (>100 kb) regions of loss-of-heterozigosity (LOH) were identified, suggesting recent recombination events between the alleles. By analysing available genomic sequencing data of multiple Lister 427 derived clones, we found that most LOH regions were conserved, except for some that were specific to clones adapted to the insect lifecycle stage. Surprisingly, we also found that some Lister 427 clones were aneuploid. We found evidence of trisomy in chromosome five (Chr5), Chr2, Chr6 and Chr7. Moreover, by analysing RNA-seq data, we showed that the transcript level is proportional to the ploidy, evidencing the lack of a general expression control at the transcript level in T. brucei.
\n\nAs a second step, to generate an allele-specific genome assembly, we used two powerful datatypes for haplotype reconstruction: raw long reads (PacBio) and chromosome conformation (Hi-C) data. With this approach, we were able to assign 99.5% of all the heterozygote variants to a specific homologous chromosome, building a 66 Mb long T. brucei Lister 427 allele-specific genome assembly. Hereby, we identified genes with allele-specific premature termination codons and showed that differences in allele-specific expression at the level of transcription and translation can be accurately monitored with the fully phased genome assembly.
\n\nThe obtained reference-grade allele-specific genome assembly of T. brucei will enable the analysis of allele-specific phenomena, as well as the better understanding of recombination and evolutionary processes. Furthermore, it will serve as a standard to ‘benchmark’ much needed automatic genome assembly pipelines for highly heterozygous wild species isolates.
", "funding": [ { "award": { "acronym": "3D_Tryps", "id": "00k4n6c32::715466", "identifiers": [ { "identifier": "https://cordis.europa.eu/projects/715466", "scheme": "url" } ], "number": "715466", "program": "H2020", "title": { "en": "The role of three-dimensional genome architecture in antigenic variation" } }, "funder": { "id": "00k4n6c32", "name": "European Commission" } } ], "publication_date": "2021-04-09", "publisher": "Zenodo", "related_identifiers": [ { "identifier": "10.1101/2021.04.13.439624", "relation_type": { "id": "isreferencedby", "title": { "de": "Wird referenziert von", "en": "Is referenced by" } }, "resource_type": { "id": "publication-preprint", "title": { "de": "Preprint", "en": "Preprint" } }, "scheme": "doi" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "subjects": [ { "subject": "ALLELE-SPECIFIC GENOME TRYPANOSOMA BRUCEI LOSS-OF-HETEROZIGOSITY ANEUPLOIDY" } ], "title": "A phased genome assembly for allele-specific analysis in Trypanosoma brucei", "version": "v1.0" }, "parent": { "access": { "owned_by": { "user": 201256 } }, "communities": { "entries": [ { "access": { "member_policy": "open", "members_visibility": "restricted", "record_policy": "open", "review_policy": "closed", "visibility": "public" }, "children": { "allow": true }, "created": "2022-11-23T15:53:29.436323+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "f0a8b890-f97a-4eb2-9eac-8b8a712d3a6c", "links": {}, "metadata": { "curation_policy": "The EU Open Research Repository serves as a repository for research outputs (data, software, posters, presentations, publications, etc) which have been funded under an EU research funding programme such as Horizon Europe, Euratom or earlier Framework Programmes.
\nThe community is managed by CERN on behalf of the European Commission.
\nZenodo’s general policies and Terms of Use apply to all content.
\nThe EU Open Research Repository accepts all digital research objects which is a research output stemming from one of EU’s research and innovation funding programmes. The funding programmes currently include:
\nHorizon Europe (including ERC, MSCA), earlier Framework Programmes (eg Horizon 2020) as well as Euratom.
\nIn line with the principle as open as possible, as closed as necessary both public and restricted content is accepted. See note on how Zenodo handles restricted content.
\nEU programme beneficiaries are eligible to submit content to the community. The community supports three types of content submissions:
\nSubmission via an EU Project Community (through user interface or programmatic APIs).
\nSubmission directly to the EU Open Research Repository.
\nAutomated harvesting from existing Zenodo content.
\nA representative of an EU project may request an EU Project Community and invite other project participants as members of the community. The project community is linked to one or more European Commission grants. All records in the project community are automatically integrated into the EU Open Research Repository immediately upon acceptance into the project community.
\nAny user may submit a record directly to the EU Open Research Repository. The submission will be moderated by Zenodo staff for compliance with the minimal required metadata requirements and its correctness.
\nRecords found among Zenodo’s existing content will on a regular basis automatically be integrated if they are found to comply with the requirements. The submissions through this method are integrated into the EU Open Research Repository with delay in a fully automated way.
\nRecords in the EU Open Research Repository are required to comply with the following minimal metadata requirements:
\nVisibility: Both public and restricted (with or without embargo and/or access request)
\nResource types: All resource types.
\nLicenses: Public and embargoed records MUST specify a license.
\nFunding information: Records MUST specify at least one grant from the European Commission.
\nCreators: Creators SHOULD be identified with a persistent identifier (e.g. ORCID, GND, …), and affiliations SHOULD be identified with a persistent identifier (e.g. ROR, ISNI, …)
\nSubjects: Records SHOULD specify one or more fields of science from the European Science Vocabulary.
\nAll submissions will undergo automated curation checks for compliance with the policy. Submissions through project communities are reviewed by the project community. Submission directly to the EU Open Research Repository is reviewed by Zenodo staff.
\nCommunity curators may at any point edit metadata of the records in the community without notice through human or automated processing. The curators may at their sole discretion remove records from the community that are deemed not to comply with the content and curation policy or which are deemed of insufficient quality.
\nThe content and curation policy is subject to change by the community owner at any time and without notice, other than through updating this page.
", "description": "Open repository for EU-funded research outputs from Horizon Europe, Euratom and earlier Framework Programmes.", "organizations": [ { "id": "00k4n6c32" } ], "page": "The EU Open Research Repository is a Zenodo-community dedicated to fostering open science and enhancing the visibility and accessibility of research outputs funded by the European Union. The community is managed by CERN on behalf of the European Commission.
\nThe mission of the repository is to support the implementation of the EU's open science policy, providing a trusted and comprehensive space for researchers to share their research outputs such as data, software, reports, presentations, posters and more. The EU Open Research Repository simplifies the process of complying with open science requirements, ensuring that research outputs from Horizon Europe, Euratom, and earlier Framework Programmes are freely accessible, thereby accelerating scientific discovery and innovation.
\nThe EU Open Research Repository serves as a complementary platform to the Open Research Europe (ORE) publishing platform. Open Research Europe focuses on providing a publishing venue for peer-reviewed articles, ensuring that research meets rigorous academic standards. The EU Open Research Repository provides a space for all the other research outputs including data sets, software, posters, and presentations that are out of scope for ORE. This holistic approach enables researchers to not only publish their findings but also share the underlying data and materials that support their work, fostering transparency and reproducibility in the scientific process.
\nCurrently in its pilot phase and set to be fully operational during autumn 2024, the EU Open Research Repository is constantly evolving. Efforts are committed to integrating cutting-edge features, including automated curation checks and FAIR (Findable, Accessible, Interoperable, and Reusable) assistance, to further support the research community. The goal is to provide researchers with a simple goto solution for making their publicly funded research open and as FAIR as possible.
\nThe EU Open Research Repository is funded by the European Union under grant agreement no. 101122956(HORIZON-ZEN). For more information about the project see https://about.zenodo.org/projects/horizon-zen/.
", "title": "EU Open Research Repository (Pilot)", "type": { "id": "organization" }, "website": "https://research-and-innovation.ec.europa.eu" }, "revision_id": 16, "slug": "eu", "theme": { "brand": "horizon", "enabled": true, "style": { "font": { "family": "Arial, sans-serif", "size": "16px", "weight": 600 }, "mainHeaderBackgroundColor": "#FFFFFF", "primaryColor": "#004494", "primaryTextColor": "#FFFFFF", "secondaryColor": "#FFD617", "secondaryTextColor": "#000000", "tertiaryColor": "#e3eefd", "tertiaryTextColor": "#1c5694" } }, "updated": "2024-03-20T06:47:47.577483+00:00" } ], "ids": [ "f0a8b890-f97a-4eb2-9eac-8b8a712d3a6c" ] }, "id": "4674607", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.4674607", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.4674608", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:4674608", "provider": "oai" } }, "revision_id": 3, "stats": { "all_versions": { "data_volume": 8210595457.0, "downloads": 175, "unique_downloads": 151, "unique_views": 282, "views": 308 }, "this_version": { "data_volume": 8210375489.0, "downloads": 174, "unique_downloads": 150, "unique_views": 278, "views": 302 } }, "status": "published", "updated": "2021-04-22T12:27:25.316497+00:00", "versions": { "index": 1, "is_latest": true } }