Journal article Open Access
{ "files": [ { "links": { "self": "https://zenodo.org/api/files/4f3aa8e4-c067-4829-a575-7b1433a8a818/sample_tumor_annotation.RData" }, "checksum": "md5:ead3ae779654613b66e694966e5be294", "bucket": "4f3aa8e4-c067-4829-a575-7b1433a8a818", "key": "sample_tumor_annotation.RData", "type": "rdata", "size": 35476 }, { "links": { "self": "https://zenodo.org/api/files/4f3aa8e4-c067-4829-a575-7b1433a8a818/TCGA_SAMBAR.RData" }, "checksum": "md5:cb555d2e45f3b7c34919f0d3f31e796d", "bucket": "4f3aa8e4-c067-4829-a575-7b1433a8a818", "key": "TCGA_SAMBAR.RData", "type": "rdata", "size": 5907025 } ], "owners": [ 33747 ], "doi": "10.5281/zenodo.1494861", "stats": { "version_unique_downloads": 45.0, "unique_views": 167.0, "views": 187.0, "version_views": 271.0, "unique_downloads": 38.0, "version_unique_views": 240.0, "volume": 172332529.0, "version_downloads": 66.0, "downloads": 58.0, "version_volume": 219588729.0 }, "links": { "doi": "https://doi.org/10.5281/zenodo.1494861", "conceptdoi": "https://doi.org/10.5281/zenodo.1494839", "bucket": "https://zenodo.org/api/files/4f3aa8e4-c067-4829-a575-7b1433a8a818", "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.1494839.svg", "html": "https://zenodo.org/record/1494861", "latest_html": "https://zenodo.org/record/1494861", "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.1494861.svg", "latest": "https://zenodo.org/api/records/1494861" }, "conceptdoi": "10.5281/zenodo.1494839", "created": "2018-11-23T10:45:00.098716+00:00", "updated": "2020-01-20T17:31:18.317140+00:00", "conceptrecid": "1494839", "revision": 5, "id": 1494861, "metadata": { "access_right_category": "success", "doi": "10.5281/zenodo.1494861", "description": "<p>This dataset contains gene and pathway mutation scores for 5,805 primary tumors from 23 different cancer types from The Cancer Genome Atlas (TCGA).<br>\n<br>\nGene mutation scores of 2,219 cancer-associated genes were calculated by normalizing the number of non-silent mutations in a gene (obtained from .maf files from TCGA) by the gene's length. We used SAMBAR (Subtyping Agglomerated Mutations By Annotation Relations) to calculate pathway mutation scores. In short, SAMBAR takes the sum of mutation scores of all genes belonging to a biological pathway and then corrects these scores for the pathway's gene set size and the number of times a gene is represented in the complete set of pathways. Please see <a href=\"https://www.nature.com/articles/s41416-018-0109-7\">our publication</a> in the <em>British Journal of Cancer</em> for methodological details.</p>\n\n<p>In the RData file "TCGA_SAMBAR.RData", we share the following objects:</p>\n\n<p>- <strong>gene_scores</strong>: a 2219 by 5805 numeric matrix including gene (rows) mutation scores for each sample (columns).</p>\n\n<p>- <strong>pathway_scores</strong>: a 1066 by 5805 numeric matrix including pathway (rows) mutation scores for each sample (columns).<br>\n<br>\nThe file "sample_tumor_annotation.RData" contains the object:<br>\n<br>\n- <strong>sample_annotation</strong>: a 5805 by 2 character matrix including sample names (first column) and the tumor type the sample belongs to (<a href=\"https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations\">TCGA Study Abbreviations</a>).</p>", "contributors": [ { "orcid": "0000-0001-8221-7139", "affiliation": "Genentech Inc.", "type": "Researcher", "name": "Paulson, Joseph Nathaniel" }, { "affiliation": "Bristol-Myers Squibb", "type": "Researcher", "name": "Salzman, Peter" }, { "affiliation": "University of Massachusetts Boston", "type": "Researcher", "name": "Ding, Wei" }, { "orcid": "0000-0002-2702-5879", "affiliation": "Harvard TH Chan School of Public Health", "type": "Researcher", "name": "Quackenbush, John" } ], "title": "Gene and pathway mutation scores for 5,805 primary tumors from TCGA", "license": { "id": "CC-BY-3.0" }, "journal": { "volume": "118", "issue": "11", "pages": "1492-1501", "title": "British Journal of Cancer" }, "relations": { "version": [ { "count": 2, "index": 1, "parent": { "pid_type": "recid", "pid_value": "1494839" }, "is_last": true, "last_child": { "pid_type": "recid", "pid_value": "1494861" } } ] }, "access_right": "open", "communities": [ { "id": "mkuijjer" } ], "references": [ "Kuijjer, Marieke Lydia, et al. Br J Cancer. 2018 May;118(11):1492-1501" ], "keywords": [ "somatic mutations", "mutations", "SAMBAR", "de-sparsification", "cancer", "TCGA", "mutation data", "mutation scores", "pathway mutation scores", "biological pathways", "gene mutation scores", "subtypes", "cancer subtypes", "pan-cancer" ], "publication_date": "2018-11-23", "creators": [ { "orcid": "0000-0001-6280-3130", "affiliation": "Centre for Molecular Medicine Norway, University of Oslo", "name": "Kuijjer, Marieke Lydia" } ], "notes": "This work was funded through a grant from the NVIDIA foundation (grant no. 2014-133322 (3953)). This work was additionally supported by a Postdoctoral Fellowship Program from the Charles A. King Trust Fund, Sara Elizabeth O'Brien Trust, Bank of America, N.A., co-Trustees.", "resource_type": { "subtype": "article", "type": "publication", "title": "Journal article" }, "related_identifiers": [ { "scheme": "doi", "identifier": "10.1038/s41416-018-0109-7", "relation": "references" }, { "scheme": "doi", "identifier": "10.5281/zenodo.1494839", "relation": "isVersionOf" } ] } }
All versions | This version | |
---|---|---|
Views | 271 | 187 |
Downloads | 66 | 58 |
Data volume | 219.6 MB | 172.3 MB |
Unique views | 240 | 167 |
Unique downloads | 45 | 38 |