diff --git a/.secrets.baseline b/.secrets.baseline index df3646f7d..8a43c1416 100644 --- a/.secrets.baseline +++ b/.secrets.baseline @@ -169,7 +169,7 @@ "filename": "docs/API/Users_Guide/Submission.md", "hashed_secret": "93f5b94e262e685fee4a419438d60e82fafaf491", "is_verified": false, - "line_number": 2389, + "line_number": 1202, "is_secret": false }, { @@ -177,7 +177,7 @@ "filename": "docs/API/Users_Guide/Submission.md", "hashed_secret": "313355a8530a54c23567f7bbedd9f804bb269820", "is_verified": false, - "line_number": 2509, + "line_number": 1441, "is_secret": false }, { @@ -185,7 +185,7 @@ "filename": "docs/API/Users_Guide/Submission.md", "hashed_secret": "b47ceb76f45ab4e8b52da270875d85fdd9b7fc33", "is_verified": false, - "line_number": 2580, + "line_number": 1512, "is_secret": false } ], @@ -285,5 +285,5 @@ } ] }, - "generated_at": "2024-07-12T14:45:44Z" + "generated_at": "2024-07-12T16:08:34Z" } diff --git a/Data_Portal_V1_UG.yml b/Data_Portal_V1_UG.yml deleted file mode 100644 index 46e8e8061..000000000 --- a/Data_Portal_V1_UG.yml +++ /dev/null @@ -1,27 +0,0 @@ -# -# GDC Docs - Config -# - -site_name: GDC Docs -site_url: http://docs.gdc.cancer.gov -repo_url: https://github.com/NCI-GDC/gdc-docs -copyright: "© 2015-2016" -theme_dir: theme -pages: -- Data Portal v1.0: - - Getting Started: 'Data_Portal_V1/Users_Guide/Getting_Started.md' - - Projects: 'Data_Portal_V1/Users_Guide/Projects.md' - - Exploration: Data_Portal_V1/Users_Guide/Exploration.md - - Repository: Data_Portal_V1/Users_Guide/Repository.md - - Genes and Mutations: Data_Portal_V1/Users_Guide/Genes_and_Mutations.md - - Annotations: 'Data_Portal_V1/Users_Guide/Annotations.md' - - Advanced Search: 'Data_Portal_V1/Users_Guide/Advanced_Search.md' - - Authentication: 'Data_Portal_V1/Users_Guide/Authentication.md' - - File Cart: 'Data_Portal_V1/Users_Guide/Cart.md' - - Image Viewer: 'Data_Portal_V1/Users_Guide/Image_viewer.md' - - Release Notes: 'Data_Portal_V1/Release_Notes/Data_Portal_V1_Release_Notes.md' -extra: - project_root_dir: '/' - project_org: 'GDC' - project_description: 'GDC Docs' - version: 1.0 diff --git a/docs/API/Users_Guide/Data_Analysis.md b/docs/API/Users_Guide/Data_Analysis.md index da6a3d020..56ca5cfcd 100644 --- a/docs/API/Users_Guide/Data_Analysis.md +++ b/docs/API/Users_Guide/Data_Analysis.md @@ -9,6 +9,9 @@ The following data analysis endpoints are available from the GDC API: |__Node__| __Endpoint__ | __Description__ | |---|---|---| |__Genes__| __/genes__ | Allows users to access summary information about each gene using its Ensembl ID. | +|__Gene Expression__|__/gene_expression/availability__|Allows users to retrieve the availability of gene expression data for specific cases and/or genes.| +||__/gene_expression/values__|Get gene expression values for specified cases and genes.| +||__/gene_expression/gene_selection__|Select the most variably expressed genes for a collection of cases and genes.| |__SSMS__| __/ssms__ | Allows users to access information about each somatic mutation. For example, a `ssm` would represent the transition of C to T at position 52000 of chromosome 1. | ||__/ssms/``__|Get information about a specific ssm using a ``, often supplemented with the `expand` option to show fields of interest. | || __/ssm_occurrences__ | A `ssm` entity as applied to a single instance (case). An example of a `ssm occurrence` would be that the transition of C to T at position 52000 of chromosome 1 occurred in patient TCGA-XX-XXXX. | @@ -165,6 +168,215 @@ __Example 2:__ A user wants a subset of elements such as a list of coordinates f (truncated) ``` +## Gene Expression Examples + +### Gene Expression Availability Endpoint + +The purpose of this endpoint is to retrieve the availability of gene expression data for cases, genes, or both. The availability response informs the user if gene expression data exists for each case or gene, which are specified with case and gene IDs. Gene expression data is only available for protein-coding genes. + +__Example 1__: A user wants to get the availability of gene expression data for a set of cases and genes. + +```Filter +{ + "case_ids": [ + "6d4f38db-a97b-4dc0-8dc5-2ac7f2cc5e38", + "e3b32485-b204-43a7-93a5-601408fcdf96" + ], + "gene_ids": [ + "ENSG00000141510", + "ENSG00000181143" + ] +} +``` + +```Shell +curl -X 'POST' \ + 'https://api.gdc.cancer.gov/gene_expression/availability' \ + -H 'accept: application/json' \ + -H 'Content-Type: application/json' \ + -d '{ + "case_ids": [ + "6d4f38db-a97b-4dc0-8dc5-2ac7f2cc5e38", + "e3b32485-b204-43a7-93a5-601408fcdf96" + ], + "gene_ids": [ + "ENSG00000141510", + "ENSG00000181143" + ] +}' +``` + +```Response +{ + "cases": { + "details": [ + { + "case_id": "6d4f38db-a97b-4dc0-8dc5-2ac7f2cc5e38", + "has_gene_expression_values": false + }, + { + "case_id": "e3b32485-b204-43a7-93a5-601408fcdf96", + "has_gene_expression_values": true + } + ], + "with_gene_expression_count": 1, + "without_gene_expression_count": 1 + }, + "genes": { + "details": [ + { + "gene_id": "ENSG00000141510", + "has_gene_expression_values": true + }, + { + "gene_id": "ENSG00000181143", + "has_gene_expression_values": true + } + ], + "with_gene_expression_count": 2, + "without_gene_expression_count": 0 + } +} +``` + +### Gene Expression Values Endpoint + +The purpose of this endpoint is to retrieve the gene expression values for the given cases and genes. The response is a TSV containing the expression values for genes to cases. +The `tsv_units` of gene expression data must be defined by exactly one of the following: + +* `uqfpkm` - FPKM-UQ values. More information on calculations can be found [here](/Data/Bioinformatics_Pipelines/Expression_mRNA_Pipeline/#calculations). +* `median_centered_log2_uqfpkm` - Median-centered log2(FPKM-UQ+1) values. + +The `median_centered_log2_uqfpkm` is calculated through the following steps: + +1. Calculate the Median: Determine the median of all provided log2(uqfpkm + 1) values. +1. Compute Median-Centered Values: Subtract the median from each log2(uqfpkm + 1) value. +1. Generate the Result Sequence: Create a new sequence with the median-centered values, preserving the original order. + +__Example 1__: A user wants to get expression values using case IDs and gene IDs. + +```Filter +{ + "case_ids": [ + "6d4f38db-a97b-4dc0-8dc5-2ac7f2cc5e38", + "e3b32485-b204-43a7-93a5-601408fcdf96", + "000ead0d-abf5-4606-be04-1ea31b999840", + "001ab32d-f924-4753-ad67-4366fb845ae6" + ], + "gene_ids": [ + "ENSG00000141510", + "ENSG00000181143" + ], + "tsv_units": "median_centered_log2_uqfpkm", + "format": "tsv" +} +``` + +```Shell +curl -X 'POST' \ + 'https://api.gdc.cancer.gov/gene_expression/values' \ + -H 'accept: text/tab-separated-values' \ + -H 'Content-Type: application/json' \ + -d '{ + "case_ids": [ + "6d4f38db-a97b-4dc0-8dc5-2ac7f2cc5e38", + "e3b32485-b204-43a7-93a5-601408fcdf96", + "000ead0d-abf5-4606-be04-1ea31b999840", + "001ab32d-f924-4753-ad67-4366fb845ae6" + ], + "gene_ids": [ + "ENSG00000141510", + "ENSG00000181143" + ], + "tsv_units": "median_centered_log2_uqfpkm", + "format": "tsv" +}' +``` + +```Response +gene_id 000ead0d-abf5-4606-be04-1ea31b999840 001ab32d-f924-4753-ad67-4366fb845ae6 e3b32485-b204-43a7-93a5-601408fcdf96 +ENSG00000141510 -0.58248 1.75830 0.00000 +ENSG00000181143 -0.02529 0.00000 3.52293 +``` + +### Gene Expression Gene Selection Endpoint + +Select the most variably expressed genes for a collection of cases and collection of genes. The request must define a collection of cases, a collection of genes, and a selection size. A minimum expression value may optionally be defined. + +A collection of cases must be defined by case IDs. + +A collection of genes must be defined by exactly one of the following: + +* `gene_ids` +* `gene_type` which has only one value: `protein_coding`. + +A selection size (`selection_size`) defines the maximum number of genes to select. + +An optional threshold (`min_median_log2_uqfpkm`) defines a minimum value for expression. Defaults to `1`. + +__Example 1__: A user wants to get the most variably expressed genes for a list of case UUIDs and a list of Ensembl gene IDs. + +```Filter +{ + "case_ids": [ + "000ead0d-abf5-4606-be04-1ea31b999840", + "001ab32d-f924-4753-ad67-4366fb845ae6", + "0024c94c-88ff-49d9-8dc4-bf77f832d85e", + "003f4f85-3244-4132-8c9d-c29f09382269", + "005d0639-c923-470f-a179-02a4dbb5cdf2", + "006931bb-f5b1-4aa4-b0a8-af517a912db0", + "0084e8b6-57fc-48b6-aa77-fec6e45161d2", + "008d3744-e7f0-41a5-a419-702960cf1ccb", + "0094e07c-1595-402e-9d38-68b9cac71e7b", + "00bd58bd-223d-433e-b60a-5bf355f342b1" + ], + "gene_ids": [ + "ENSG00000141510", + "ENSG00000181143" + ], + "selection_size": 1 +} +``` + +```Shell +curl -X 'POST' \ + 'https://api.gdc.cancer.gov/gene_expression/gene_selection' \ + -H 'accept: application/json' \ + -H 'Content-Type: application/json' \ + -d '{ + "case_ids": [ + "000ead0d-abf5-4606-be04-1ea31b999840", + "001ab32d-f924-4753-ad67-4366fb845ae6", + "0024c94c-88ff-49d9-8dc4-bf77f832d85e", + "003f4f85-3244-4132-8c9d-c29f09382269", + "005d0639-c923-470f-a179-02a4dbb5cdf2", + "006931bb-f5b1-4aa4-b0a8-af517a912db0", + "0084e8b6-57fc-48b6-aa77-fec6e45161d2", + "008d3744-e7f0-41a5-a419-702960cf1ccb", + "0094e07c-1595-402e-9d38-68b9cac71e7b", + "00bd58bd-223d-433e-b60a-5bf355f342b1" + ], + "gene_ids": [ + "ENSG00000141510", + "ENSG00000181143" + ], + "selection_size": 1 +}' +``` + +```Response +{ + "gene_selection": [ + { + "log2_uqfpkm_stddev": 0.9962971125913709, + "log2_uqfpkm_median": 2.904457107848132, + "gene_id": "ENSG00000141510", + "symbol": "TP53" + } + ] +} +``` + ## Simple Somatic Mutation Endpoint Examples __Example 1__: Similar to the `/genes` endpoint, a user would like to retrieve information about the mutation based on its COSMIC ID. This would be accomplished by creating a JSON filter, which will then be encoded to URL for the `curl` command. diff --git a/docs/API/Users_Guide/Submission.md b/docs/API/Users_Guide/Submission.md index 0bb2ad64d..4a8b54d76 100644 --- a/docs/API/Users_Guide/Submission.md +++ b/docs/API/Users_Guide/Submission.md @@ -46,26 +46,6 @@ JSON is the default format for metadata submission. Submission API calls with JS Metadata files must be uploaded in raw, unencoded form. Binary mode should be used, if available, to ensure that file contents are not encoded by the upload tool before transmission. For example, when using the `curl` command-line tool, the `--data-binary` switch should be used instead of `--data`. The `--data-binary` switch is required for uploading TSV files. -#### BCR XML - -While JSON and TSV are the recommended formats for submitting metadata, the GDC API can also extract metadata elements from BCR XML files. Users wishing to submit metadata as BCR XML must contact GDC User Services and ensure that appropriate element mapping is in place before initiating XML submission. Current mapping can be found in [GitHub](https://github.com/NCI-GDC/gdcdatamodel/tree/develop/gdcdatamodel/xml_mappings). - -To submit BCR XML, make `PUT` requests with the `Content-Type: application/xml` header to the following URLs, replacing Program.name and Project.code as desribed in [Submission Endpoint](#submission_endpoint) (above): - -0. For Biospecimen BCR XML: `https://api.gdc.cancer.gov/v0/submission/Program.name/Project.code/xml/biospecimen/bcr/` -0. For Clinical BCR XML: `https://api.gdc.cancer.gov/v0/submission/Program.name/Project.code/xml/clinical/bcr/`. - -Biospecimen BCR XML creates Case entities in the GDC Data Model, whereas Clinical BCR XML does not. Unless the associated cases already exist in the GDC, Biospecimen BCR XML must be uploaded before Clinical BCR XML. - -BCR XML files can be submitted in dry run mode, described [below](#dry-run-transactions), by appending `_dry_run` to the above URLs. - -The following is a sample shell command for submitting an XML file: - - curl --request PUT --header "X-Auth-Token: $token" --header 'Content-Type: application/xml' --data-binary @biospecimen.xml 'https://api.gdc.cancer.gov/v0/submission/GDC/INTERNAL/xml/biospecimen/bcr/_dry_run' - ->**NOTE:** A typical BCR XML file contains more information than what is extracted and indexed by the GDC. XML files submitted to the above endpoints are not retained or distributed to GDC data users, so the same files should also be submitted as data files (i.e. as clinical or biospecimen supplements). - - ### Data File Formats The GDC API accepts a variety of data files after their metadata has been registered: BAM and FASTQ files, clinical and biospecimen supplements, slide images, and other file types. Supported data file formats are listed on the [GDC Data Dictionary](https://docs.gdc.cancer.gov/Data_Dictionary/viewer/#?view=table-entity-list&anchor=submittable_data_file). @@ -1034,1396 +1014,348 @@ New nodes are created in Request1. Nodes in state `validated` are updated in Re } ``` +## Retrieving Entities -#### Updating a sample using a BCR XML - -Entities are created in Command1. These entities are later released. Command2 demonstrates updating entity information via XML submission. +### Entities Endpoint -=== "Command1" +JSON objects representing submitted entities can be retrieved with a GET request to the `entities` endpoint. This endpoint retrieves entities by UUID. A single UUID or a comma-separated list of UUIDs can be passed to this endpoint as a query. +=== "Command" + ```shell - curl --request PUT --header "X-Auth-Token: $token" --header 'Content-Type: application/xml' --data-binary @BCR_biospecimen.xml 'https://api.gdc.cancer.gov/v0/submission/QA/REGRESSION/xml/biospecimen/bcr/' + token=$( * Links to the case summary page have been removed for annotations that concern a redaction of the case. +* __ProteinPaint__: + * A new option to toggle lollipops pointing up or down is now available. +* __OncoMatrix__: + * Advanced sorting options for power users have been added. + * Implemented a prototype for adding gene expression rows. +* __Gene Expression Clustering__: + * Allows re-sort cases by dictionary variable, gene mutation, or expression level. +* __Sequence Reads__: + * Adds ability to visualize truncated BAM slice when the slice file size exceeds 20MB and streaming is terminated. * __Cohorts__ created from analysis tools now consistently consist of a specific list of cases that will remain unchanged after a data release. This includes cohorts created from the gene and mutation summary pages. * The files tables in the __Cart__ and the __Repository__ now allow searching for files based on the associated cases' submitter ID and UUID. * In the __case summary page__, values whose units are days, e.g. Days to Death or Days to Birth, are now displayed in years and days as appropriate for the user's convenience. @@ -58,7 +67,7 @@ * The Best Overall Response card in the Treatments category of the __Cohort Builder__ has been moved to a new position in the category. * The text referencing the deletion of custom sets in the __Manage Sets__ page has been updated. * The Access column has been added to the Source Files and Download Analyses Files tables in the __file summary page__. -* Text within the downloaded histogram image has been updated for greater clarity in the __Clinical Data Analysis__ tool. +* Text within the downloaded histogram image has been updated for greater clarity in the __Clinical Data Analysis__ tool. * Filter panels in the __Projects__, __Mutation Frequency__, and __Repository__ tools have been standardized and now consistently allow scrolling to occur independently of the tables on the right. ### Bugs Fixed Since Last Release @@ -83,11 +92,23 @@ * __Mutation Frequency__: * Gene/mutation sets created from the tables in the Mutation Frequency tool will now contain the expected genes/mutations even if the cohort has Available Data filters or Biospecimen filters. * Users will no longer be able to create several cohorts in quick succession from Mutation Frequency without waiting for previous actions to be completed. +* __OncoMatrix__: + * Made OncoMatrix react to divide-by term edits from the label click menu. + * Fixed the continuous term scale for density plots. + * Gene expression variable may not show expression data for all applicable cases, especially with a large cohort size. +* __Gene Expression Clustering__: + * Fixed the continuous term scale for density plots. +* __Sequence Reads__: + * The tool now displays the correct number of available BAM files when a cohort filter is in use. +* __Cohort MAF__: + * Added the "tumor_bam_uuid" column. +* Limited the CSS reset to avoid conflict with embedded styles, by using scoped normalize CSS rules. +* Fixed conflicting CSS that can alter portal styling. * Fixed an issue where __Sample Sheet__ downloads can be incomplete due to missing sample type information. * Addressed an issue where changes to default filters in the __Cohort Builder__ and the __Repository__ may not be reflected after a release. * The __Query Expressions__ section now correctly displays a maximum of 3 rows by default. Additionally, the button to display more than 3 rows at a time is enabled only when the cohort query exceeds 3 rows. * The loading spinner is no longer displayed above the other areas of the Analysis Center when the __Cohort Comparison__ tool is loading. -* Default values in the Custom Bins modal within the __Clinical Data Analysis__ tool are now properly updated when the user toggles between displaying continuous values in days and years. +* Default values in the Custom Bins modal within the __Clinical Data Analysis__ tool are now properly updated when the user toggles between displaying continuous values in days and years. * The right side of the chart on the __Home Page__ is no longer cut off at smaller browser sizes. * Tooltips are no longer displayed when there is no description available for filter properties. @@ -107,9 +128,12 @@ * Spinners on the Download Cart and Download Associated Data buttons may be displayed longer than expected. This is a visual issue and does not affect the use of these buttons. * Using multiple browser tabs with the portal when adding or removing files from the cart may result in the cart not being updated as expected. * In the __files, cases, and annotations tables__, the case ID search field is case-sensitive. If the search does not return the expected results, try changing the input to uppercase as case IDs are most commonly uppercased. -* __Cohorts__ filtered by mutated genes and SSMs not in those genes may unexpectedly result in 0 cases. +* __Cohorts__ filtered by mutated genes and SSMs not in those genes will result in 0 cases since the mutations have to belong to those particular genes in order to match cases for the results. As a workaround, first filter the cohort by the mutated genes and export the cohort using the Export Cohort feature in the Cohort Bar. Then, reimport the cohort using the Import New Cohort feature before applying the SSM filters. * The __Slide Image Viewer__ will display a black image temporarily if a user zooms in on a slide then switches to another slide. * The annotations table in the __file summary page__ does not include the Case ID column. This column is planned to be added in a future update. +* In __ProteinPaint__, the "Gene Expression" option is non-functional when filtering samples in a sub-track. +* In __Gene Expression Clustering__, the tooltip is not displayed when clicking an expression data cell. +* The custom range inputs for the __Age at Index__ card in the __Cohort Builder__ are not behaving as expected. As a workaround, use the predefined ranges available. Alternatively, use the custom range inputs on the Days tab to query for ages in years. ## Release 2.1.0 @@ -118,7 +142,7 @@ ### New Features and Changes * __Annotations Browser__ - * The Annotations Browser and annotation summary page have been implemented. + * The Annotations Browser and annotation summary page have been implemented. * __Repository__: * Files can now be filtered by Tissue Type, Tumor Descriptor, Specimen Type, and Preservation Method. * Metadata and Sample Sheet downloads have been added to the Repository. @@ -147,7 +171,7 @@ * Allow visualizing SSM in any genomic locus, besides "protein" mode. * Support creating a single-case cohort. * The performance of the __Clinical Data Analysis__ tool has been improved, especially when large cohorts are used with QQ plots. -* __Quick Search__ now returns results for the latest versions of files when searching for older versions of those files. +* __Quick Search__ now returns results for the latest versions of files when searching for older versions of those files. * The X button on the __Unexpected Error__ dialog box has been removed. * Buttons for launching demos have been removed from the selection view of __Cohort Comparison__ and __Set Operations__. * Responsiveness improvements have been made to the __Analysis Center__ and the __Cohort Bar__. diff --git a/docs/Data_Portal/Users_Guide/Repository.md b/docs/Data_Portal/Users_Guide/Repository.md index 6595c704d..95dba232d 100644 --- a/docs/Data_Portal/Users_Guide/Repository.md +++ b/docs/Data_Portal/Users_Guide/Repository.md @@ -34,6 +34,10 @@ As most users are searching for specific types of files, a set of commonly-used * **Workflow Type**: Bioinformatics workflow used to generate or harmonize the data file * **Platform**: Technological platform on which experimental data was produced * **Access**: Indicator of whether access to the data file is open or controlled +* **Tissue Type**: Type of tissue collected, such as "Normal" or "Tumor" +* **Tumor Descriptor**: Description of the disease present in the tumor specimen, such as "Primary" or "Metastatic" +* **Specimen Type**: Type of material taken. This includes particular types of cellular molecules, cells, tissues, organs, body fluids, embryos, and body excretory substances. +* **Preservation Method**: Method used to preserve the sample, such as "OCT" or "Snap Frozen" Values within each facet can be sorted alphabetically by choosing the "Name" header on the top left of each card. Alternatively, the "Files" header may be selected to sort the values by the number of files available. diff --git a/docs/Data_Portal/Users_Guide/Video_Tutorials.md b/docs/Data_Portal/Users_Guide/Video_Tutorials.md index 4badeb360..11f04aa5b 100644 --- a/docs/Data_Portal/Users_Guide/Video_Tutorials.md +++ b/docs/Data_Portal/Users_Guide/Video_Tutorials.md @@ -72,6 +72,12 @@ A cohort can be analyzed by selecting an analysis tool in the Analysis Center. T +Cohort Level MAF +Download an aggregated set of variants in MAF format based on the cases in your active cohort. + + + + Gene Expression Clustering Display gene expression visualization diff --git a/docs/Data_Submission_Portal/Users_Guide/Data_Submission_Walkthrough.md b/docs/Data_Submission_Portal/Users_Guide/Data_Submission_Walkthrough.md index f0c7db049..d3ab93052 100644 --- a/docs/Data_Submission_Portal/Users_Guide/Data_Submission_Walkthrough.md +++ b/docs/Data_Submission_Portal/Users_Guide/Data_Submission_Walkthrough.md @@ -234,7 +234,14 @@ One of the main features of the GDC is the genomic data harmonization workflow. [![GDC Data Model 3](images/GDC-Data-Model-Sample.png)](images/GDC-Data-Model-Sample.png "Click to see the full image.") -A `sample` submission has the same general structure as a `case` submission as it will require a unique key and a link to the `case`. However, `sample` entities require one additional value: `sample_type`. This peripheral data is required because it is necessary for the data to be interpreted. For example, an investigator using this data would need to know whether the `sample` came from tumor or normal tissue. +A `sample` submission has the same general structure as a `case` submission as it will require a unique key and a link to the `case`. However, `sample` entities require four additional values: + +* `tissue_type` +* `tumor_descriptor` +* `specimen_type` +* `preservation_method` + +This peripheral data is required because it is necessary for the data to be interpreted. For example, an investigator using this data would need to know whether the `sample` came from tumor or normal tissue. [![Dictionary Sample](images/Dictionary_Sample.png)](images/Dictionary_Sample.png "Click to see the full image.") @@ -242,8 +249,10 @@ Submitting a [__Sample__](https://docs.gdc.cancer.gov/Data_Dictionary/viewer/#?v * __`submitter_id`:__ A unique key to identify the `sample`. * __`cases.submitter_id`:__ The unique key that was used for the `case` that links the `sample` to the `case`. -* __`sample_type`:__ Type of the `sample`. Named for its cellular source, molecular composition, and/or therapeutic treatment. * __`tissue_type`:__ Text term that represents a description of the kind of tissue collected with respect to disease status or proximity to tumor tissue. +* __`tumor_descriptor`:__ Text that describes the kind of disease present in the tumor specimen as related to a specific timepoint. +* __`specimen_type`:__ The type of a material sample taken from a biological entity for testing, diagnostic, propagation, treatment or research purposes. This includes particular types of cellular molecules, cells, tissues, organs, body fluids, embryos, and body excretory substances. +* __`preservation_method`:__ Text term that represents the method used to preserve the sample. >__Note:__ The `case` must be "committed" to the project before a `sample` can be linked to it. This also applies to all other links between entities. @@ -253,14 +262,16 @@ Submitting a [__Sample__](https://docs.gdc.cancer.gov/Data_Dictionary/viewer/#?v "cases": { "submitter_id": "PROJECT-INTERNAL-000055" }, - "sample_type": "Blood Derived Normal", - "submitter_id": "Blood-00001SAMPLE_55" - "tissue_type": "Normal" + "submitter_id": "Blood-00001SAMPLE_55", + "tissue_type": "Normal", + "tumor_descriptor": "Not Applicable", + "specimen_type": "Peripheral Blood NOS", + "preservation_method": "Frozen" } ``` ```TSV -type cases.submitter_id submitter_id sample_type tissue_type -sample PROJECT-INTERNAL-000055 Blood-00001SAMPLE_55 Blood Derived Normal Normal +type cases.submitter_id submitter_id tissue_type specimen_type tumor_descriptor preservation_method +sample PROJECT-INTERNAL-000055 Blood-00001SAMPLE_55 Normal Peripheral Blood NOS Not Applicable Frozen ``` ## Portion, Analyte and Aliquot Submission @@ -597,14 +608,17 @@ Registering a BAM file (or any other type) can be performed in one step by inclu "cases": { "submitter_id": "PROJECT-INTERNAL-000055" }, - "sample_type": "Blood Derived Normal", - "submitter_id": "Blood-00001_55" + "submitter_id": "Blood-00001SAMPLE_55", + "tissue_type": "Normal", + "tumor_descriptor": "Not Applicable", + "specimen_type": "Peripheral Blood NOS", + "preservation_method": "Frozen" }, { "type": "portion", "submitter_id": "Blood-portion-000055", "samples": { - "submitter_id": "Blood-00001_55" + "submitter_id": "Blood-00001SAMPLE_55" } }, { diff --git a/docs/Data_Submission_Portal/Users_Guide/Samples.tsv b/docs/Data_Submission_Portal/Users_Guide/Samples.tsv index 5254ae3f2..b523af7eb 100644 --- a/docs/Data_Submission_Portal/Users_Guide/Samples.tsv +++ b/docs/Data_Submission_Portal/Users_Guide/Samples.tsv @@ -1,101 +1,101 @@ -type submitter_id cases.submitter_id sample_type -sample Blood-00001_api1 GDC-INTERNAL-1 Blood Derived Normal -sample Blood-00001_api2 GDC-INTERNAL-2 Blood Derived Normal -sample Blood-00001_api3 GDC-INTERNAL-3 Primary Tumor -sample Blood-00001_api4 GDC-INTERNAL-4 Blood Derived Normal -sample Blood-00001_api5 GDC-INTERNAL-5 Blood Derived Normal -sample Blood-00001_api6 GDC-INTERNAL-6 Blood Derived Normal -sample Blood-00001_api7 GDC-INTERNAL-7 Primary Tumor -sample Blood-00001_api8 GDC-INTERNAL-8 Blood Derived Normal -sample Blood-00001_api9 GDC-INTERNAL-9 Blood Derived Normal -sample Blood-00001_api10 GDC-INTERNAL-10 Blood Derived Normal -sample Blood-00001_api11 GDC-INTERNAL-11 Blood Derived Normal -sample Blood-00001_api12 GDC-INTERNAL-12 Blood Derived Normal -sample Blood-00001_api13 GDC-INTERNAL-13 Primary Tumor -sample Blood-00001_api14 GDC-INTERNAL-14 Blood Derived Normal -sample Blood-00001_api15 GDC-INTERNAL-15 Blood Derived Normal -sample Blood-00001_api16 GDC-INTERNAL-16 Primary Tumor -sample Blood-00001_api17 GDC-INTERNAL-17 Blood Derived Normal -sample Blood-00001_api18 GDC-INTERNAL-18 Blood Derived Normal -sample Blood-00001_api19 GDC-INTERNAL-19 Primary Tumor -sample Blood-00001_api20 GDC-INTERNAL-20 Blood Derived Normal -sample Blood-00001_api21 GDC-INTERNAL-21 Blood Derived Normal -sample Blood-00001_api22 GDC-INTERNAL-22 Blood Derived Normal -sample Blood-00001_api23 GDC-INTERNAL-23 Blood Derived Normal -sample Blood-00001_api24 GDC-INTERNAL-24 Blood Derived Normal -sample Blood-00001_api25 GDC-INTERNAL-25 Primary Tumor -sample Blood-00001_api26 GDC-INTERNAL-26 Blood Derived Normal -sample Blood-00001_api27 GDC-INTERNAL-27 Blood Derived Normal -sample Blood-00001_api28 GDC-INTERNAL-28 Blood Derived Normal -sample Blood-00001_api29 GDC-INTERNAL-29 Primary Tumor -sample Blood-00001_api30 GDC-INTERNAL-30 Primary Tumor -sample Blood-00001_api31 GDC-INTERNAL-31 Primary Tumor -sample Blood-00001_api32 GDC-INTERNAL-32 Blood Derived Normal -sample Blood-00001_api33 GDC-INTERNAL-33 Blood Derived Normal -sample Blood-00001_api34 GDC-INTERNAL-34 Blood Derived Normal -sample Blood-00001_api35 GDC-INTERNAL-35 Blood Derived Normal -sample Blood-00001_api36 GDC-INTERNAL-36 Primary Tumor -sample Blood-00001_api37 GDC-INTERNAL-37 Blood Derived Normal -sample Blood-00001_api38 GDC-INTERNAL-38 Blood Derived Normal -sample Blood-00001_api39 GDC-INTERNAL-39 Primary Tumor -sample Blood-00001_api40 GDC-INTERNAL-40 Blood Derived Normal -sample Blood-00001_api41 GDC-INTERNAL-41 Blood Derived Normal -sample Blood-00001_api42 GDC-INTERNAL-42 Blood Derived Normal -sample Blood-00001_api43 GDC-INTERNAL-43 Blood Derived Normal -sample Blood-00001_api44 GDC-INTERNAL-44 Blood Derived Normal -sample Blood-00001_api45 GDC-INTERNAL-45 Primary Tumor -sample Blood-00001_api46 GDC-INTERNAL-46 Blood Derived Normal -sample Blood-00001_api47 GDC-INTERNAL-47 Primary Tumor -sample Blood-00001_api48 GDC-INTERNAL-48 Blood Derived Normal -sample Blood-00001_api49 GDC-INTERNAL-49 Primary Tumor -sample Blood-00001_api50 GDC-INTERNAL-50 Blood Derived Normal -sample Blood-00001_api51 GDC-INTERNAL-51 Primary Tumor -sample Blood-00001_api52 GDC-INTERNAL-52 Blood Derived Normal -sample Blood-00001_api53 GDC-INTERNAL-53 Blood Derived Normal -sample Blood-00001_api54 GDC-INTERNAL-54 Primary Tumor -sample Blood-00001_api55 GDC-INTERNAL-55 Primary Tumor -sample Blood-00001_api56 GDC-INTERNAL-56 Blood Derived Normal -sample Blood-00001_api57 GDC-INTERNAL-57 Blood Derived Normal -sample Blood-00001_api58 GDC-INTERNAL-58 Primary Tumor -sample Blood-00001_api59 GDC-INTERNAL-59 Blood Derived Normal -sample Blood-00001_api60 GDC-INTERNAL-60 Blood Derived Normal -sample Blood-00001_api61 GDC-INTERNAL-61 Primary Tumor -sample Blood-00001_api62 GDC-INTERNAL-62 Blood Derived Normal -sample Blood-00001_api63 GDC-INTERNAL-63 Blood Derived Normal -sample Blood-00001_api64 GDC-INTERNAL-64 Blood Derived Normal -sample Blood-00001_api65 GDC-INTERNAL-65 Primary Tumor -sample Blood-00001_api66 GDC-INTERNAL-66 Blood Derived Normal -sample Blood-00001_api67 GDC-INTERNAL-67 Blood Derived Normal -sample Blood-00001_api68 GDC-INTERNAL-68 Primary Tumor -sample Blood-00001_api69 GDC-INTERNAL-69 Primary Tumor -sample Blood-00001_api70 GDC-INTERNAL-70 Primary Tumor -sample Blood-00001_api71 GDC-INTERNAL-71 Blood Derived Normal -sample Blood-00001_api72 GDC-INTERNAL-72 Primary Tumor -sample Blood-00001_api73 GDC-INTERNAL-73 Blood Derived Normal -sample Blood-00001_api74 GDC-INTERNAL-74 Blood Derived Normal -sample Blood-00001_api75 GDC-INTERNAL-75 Blood Derived Normal -sample Blood-00001_api76 GDC-INTERNAL-76 Primary Tumor -sample Blood-00001_api77 GDC-INTERNAL-77 Primary Tumor -sample Blood-00001_api78 GDC-INTERNAL-78 Blood Derived Normal -sample Blood-00001_api79 GDC-INTERNAL-79 Primary Tumor -sample Blood-00001_api80 GDC-INTERNAL-80 Blood Derived Normal -sample Blood-00001_api81 GDC-INTERNAL-81 Blood Derived Normal -sample Blood-00001_api82 GDC-INTERNAL-82 Blood Derived Normal -sample Blood-00001_api83 GDC-INTERNAL-83 Primary Tumor -sample Blood-00001_api84 GDC-INTERNAL-84 Blood Derived Normal -sample Blood-00001_api85 GDC-INTERNAL-85 Blood Derived Normal -sample Blood-00001_api86 GDC-INTERNAL-86 Blood Derived Normal -sample Blood-00001_api87 GDC-INTERNAL-87 Blood Derived Normal -sample Blood-00001_api88 GDC-INTERNAL-88 Primary Tumor -sample Blood-00001_api89 GDC-INTERNAL-89 Blood Derived Normal -sample Blood-00001_api90 GDC-INTERNAL-90 Blood Derived Normal -sample Blood-00001_api91 GDC-INTERNAL-91 Primary Tumor -sample Blood-00001_api92 GDC-INTERNAL-92 Blood Derived Normal -sample Blood-00001_api93 GDC-INTERNAL-93 Blood Derived Normal -sample Blood-00001_api94 GDC-INTERNAL-94 Primary Tumor -sample Blood-00001_api95 GDC-INTERNAL-95 Blood Derived Normal -sample Blood-00001_api96 GDC-INTERNAL-96 Blood Derived Normal -sample Blood-00001_api97 GDC-INTERNAL-97 Blood Derived Normal -sample Blood-00001_api98 GDC-INTERNAL-98 Primary Tumor -sample Blood-00001_api99 GDC-INTERNAL-99 Blood Derived Normal -sample Blood-00001_api100 GDC-INTERNAL-100 Blood Derived Normal +type submitter_id cases.submitter_id tissue_type specimen_type tumor_descriptor preservation_method +sample Blood-00001_api1 GDC-INTERNAL-1 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api2 GDC-INTERNAL-2 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api3 GDC-INTERNAL-3 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api4 GDC-INTERNAL-4 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api5 GDC-INTERNAL-5 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api6 GDC-INTERNAL-6 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api7 GDC-INTERNAL-7 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api8 GDC-INTERNAL-8 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api9 GDC-INTERNAL-9 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api10 GDC-INTERNAL-10 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api11 GDC-INTERNAL-11 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api12 GDC-INTERNAL-12 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api13 GDC-INTERNAL-13 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api14 GDC-INTERNAL-14 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api15 GDC-INTERNAL-15 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api16 GDC-INTERNAL-16 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api17 GDC-INTERNAL-17 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api18 GDC-INTERNAL-18 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api19 GDC-INTERNAL-19 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api20 GDC-INTERNAL-20 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api21 GDC-INTERNAL-21 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api22 GDC-INTERNAL-22 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api23 GDC-INTERNAL-23 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api24 GDC-INTERNAL-24 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api25 GDC-INTERNAL-25 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api26 GDC-INTERNAL-26 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api27 GDC-INTERNAL-27 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api28 GDC-INTERNAL-28 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api29 GDC-INTERNAL-29 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api30 GDC-INTERNAL-30 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api31 GDC-INTERNAL-31 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api32 GDC-INTERNAL-32 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api33 GDC-INTERNAL-33 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api34 GDC-INTERNAL-34 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api35 GDC-INTERNAL-35 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api36 GDC-INTERNAL-36 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api37 GDC-INTERNAL-37 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api38 GDC-INTERNAL-38 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api39 GDC-INTERNAL-39 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api40 GDC-INTERNAL-40 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api41 GDC-INTERNAL-41 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api42 GDC-INTERNAL-42 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api43 GDC-INTERNAL-43 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api44 GDC-INTERNAL-44 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api45 GDC-INTERNAL-45 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api46 GDC-INTERNAL-46 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api47 GDC-INTERNAL-47 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api48 GDC-INTERNAL-48 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api49 GDC-INTERNAL-49 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api50 GDC-INTERNAL-50 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api51 GDC-INTERNAL-51 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api52 GDC-INTERNAL-52 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api53 GDC-INTERNAL-53 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api54 GDC-INTERNAL-54 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api55 GDC-INTERNAL-55 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api56 GDC-INTERNAL-56 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api57 GDC-INTERNAL-57 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api58 GDC-INTERNAL-58 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api59 GDC-INTERNAL-59 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api60 GDC-INTERNAL-60 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api61 GDC-INTERNAL-61 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api62 GDC-INTERNAL-62 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api63 GDC-INTERNAL-63 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api64 GDC-INTERNAL-64 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api65 GDC-INTERNAL-65 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api66 GDC-INTERNAL-66 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api67 GDC-INTERNAL-67 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api68 GDC-INTERNAL-68 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api69 GDC-INTERNAL-69 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api70 GDC-INTERNAL-70 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api71 GDC-INTERNAL-71 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api72 GDC-INTERNAL-72 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api73 GDC-INTERNAL-73 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api74 GDC-INTERNAL-74 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api75 GDC-INTERNAL-75 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api76 GDC-INTERNAL-76 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api77 GDC-INTERNAL-77 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api78 GDC-INTERNAL-78 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api79 GDC-INTERNAL-79 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api80 GDC-INTERNAL-80 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api81 GDC-INTERNAL-81 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api82 GDC-INTERNAL-82 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api83 GDC-INTERNAL-83 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api84 GDC-INTERNAL-84 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api85 GDC-INTERNAL-85 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api86 GDC-INTERNAL-86 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api87 GDC-INTERNAL-87 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api88 GDC-INTERNAL-88 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api89 GDC-INTERNAL-89 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api90 GDC-INTERNAL-90 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api91 GDC-INTERNAL-91 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api92 GDC-INTERNAL-92 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api93 GDC-INTERNAL-93 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api94 GDC-INTERNAL-94 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api95 GDC-INTERNAL-95 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api96 GDC-INTERNAL-96 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api97 GDC-INTERNAL-97 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api98 GDC-INTERNAL-98 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api99 GDC-INTERNAL-99 Normal Peripheral Blood NOS Not Applicable Frozen +sample Blood-00001_api100 GDC-INTERNAL-100 Normal Peripheral Blood NOS Not Applicable Frozen diff --git a/docs/Data_Transfer_Tool/Users_Guide/Preparing_for_Data_Download_and_Upload.md b/docs/Data_Transfer_Tool/Users_Guide/Preparing_for_Data_Download_and_Upload.md index b64bd91fa..ec51ce193 100644 --- a/docs/Data_Transfer_Tool/Users_Guide/Preparing_for_Data_Download_and_Upload.md +++ b/docs/Data_Transfer_Tool/Users_Guide/Preparing_for_Data_Download_and_Upload.md @@ -9,20 +9,20 @@ The GDC Data Transfer Tool is intended to be used in conjunction with the [GDC D The GDC Data Transfer Tool supports downloading multiple files listed in a GDC manifest file. Manifest files can be generated and downloaded directly from the GDC Data Portal: -First, select the data files of interest. Click the *Cart* button in the row corresponding to the file desired. The button will turn green to indicate that the file has been selected. +First, select the data files of interest. Click the *Cart* button in the row corresponding to the file desired. The button will turn blue to indicate that the file has been selected. -![GDC Data Portal: Selecting Files of Interest](images/09-15_Data-Portal-File-Selection.png "Selecting Files of Interest") +![GDC Data Portal: Selecting Files of Interest](images/06-20_Data-Portal-File-Selection.png "Selecting Files of Interest") -Once all files of interest have been selected, click on the *Cart* button in the upper right-hand corner. This will bring up the cart page, which provides an overview of all currently selected files. This list of files can be downloaded as a manifest file by clicking on the green *Download* button and selecting *Manifest* from the drop down. +Once all files of interest have been selected, click on the *Cart* button in the upper right-hand corner. This will bring up the cart page, which provides an overview of all currently selected files. This list of files can be downloaded as a manifest file by clicking on the *Download Cart* button and selecting *Manifest* from the drop down. -![GDC Data Portal: Cart Page](images/09-15-v2_Data-Portal-Cart-Page.png) +![GDC Data Portal: Cart Page](images/06-20-v2_Data-Portal-Cart-Page.png) ### Obtaining UUIDs for Data Download A manifest file is not required to download files from GDC. The GDC Data Transfer Tool will accept file UUID(s) instead of a manifest file for downloading individual data files. To obtain a data file's UUID from the GDC Data Portal, click the file name to find its detail page including its GDC UUID. -![GDC Data Portal: Detailed File Page](images/09-22_Data-portal-file-detail-pagev2.png) +![GDC Data Portal: Detailed File Page](images/06-20_Data-portal-file-detail-pagev2.png) ### Obtaining an Authentication Token for Data Downloads @@ -33,7 +33,7 @@ To generate a token, first log in to the GDC Data Portal by clicking the *Login* Clicking the username will open a drop-down menu. Select *Download Token* from the menu to generate an authentication token. -![GDC Data Portal User Dropdown Menu](images/auth_example_download_token-2.png) +![GDC Data Portal User Dropdown Menu](images/06-20_auth_example_download_token-2.png) **NOTE:** The authentication token should be kept in a secure location, as it allows access to all data accessible by the associated user. diff --git a/docs/Data_Transfer_Tool/Users_Guide/images/06-20-v2_Data-Portal-Cart-Page.png b/docs/Data_Transfer_Tool/Users_Guide/images/06-20-v2_Data-Portal-Cart-Page.png new file mode 100644 index 000000000..be69ca35a Binary files /dev/null and b/docs/Data_Transfer_Tool/Users_Guide/images/06-20-v2_Data-Portal-Cart-Page.png differ diff --git a/docs/Data_Transfer_Tool/Users_Guide/images/06-20_Data-Portal-File-Selection.png b/docs/Data_Transfer_Tool/Users_Guide/images/06-20_Data-Portal-File-Selection.png new file mode 100644 index 000000000..2afc3a150 Binary files /dev/null and b/docs/Data_Transfer_Tool/Users_Guide/images/06-20_Data-Portal-File-Selection.png differ diff --git a/docs/Data_Transfer_Tool/Users_Guide/images/06-20_Data-portal-file-detail-pagev2.png b/docs/Data_Transfer_Tool/Users_Guide/images/06-20_Data-portal-file-detail-pagev2.png new file mode 100644 index 000000000..a91574589 Binary files /dev/null and b/docs/Data_Transfer_Tool/Users_Guide/images/06-20_Data-portal-file-detail-pagev2.png differ diff --git a/docs/Data_Transfer_Tool/Users_Guide/images/06-20_auth_example_download_token-2.png b/docs/Data_Transfer_Tool/Users_Guide/images/06-20_auth_example_download_token-2.png new file mode 100644 index 000000000..cf4cb37b6 Binary files /dev/null and b/docs/Data_Transfer_Tool/Users_Guide/images/06-20_auth_example_download_token-2.png differ diff --git a/docs/Encyclopedia/pages/GATK4_MuTect2_Tumor-Only.md b/docs/Encyclopedia/pages/GATK4_MuTect2_Tumor-Only.md new file mode 100644 index 000000000..31b898977 --- /dev/null +++ b/docs/Encyclopedia/pages/GATK4_MuTect2_Tumor-Only.md @@ -0,0 +1,29 @@ +# GATK4 MuTect2 Tumor-Only + +## Description ## + +GATK4 MuTect2 Tumor-Only is a somatic variant calling pipeline utilized in the GDC for analyzing tumor-only whole exome sequencing (WXS) and targeted sequencing data without normal samples. + +## Overview ## + +GATK4 MuTect2 Tumor-Only is a pipeline used for WXS and targeted sequencing somatic variant calling at the GDC. Somatic variant calling is performed with GATK4 MuTect2 Tumor-Only using tumor alignments and generates single nucleotide variants (SNVs) data. + +### Input + +* Tumor BAM - WXS or Targeted Sequencing + +### Output + +* VCF (Data Type: Raw Simple Somatic Mutation) + +## References ## + +1. [DNA-Seq Analysis Pipeline](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/) +1. [Tumor-Only Variant Calling Workflow](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/#tumor-only-variant-calling-workflow) + +## External Links ## + +* [Overview of GDC Harmonization Workflows](https://github.com/NCI-GDC/gdc-workflow-overview/blob/master/README.md) +* [GDC Data Portal](https://portal.gdc.cancer.gov) + +Categories: Workflow Type \ No newline at end of file diff --git a/docs/Encyclopedia/pages/GATK4_MuTect2_Tumor-Only_Annotation.md b/docs/Encyclopedia/pages/GATK4_MuTect2_Tumor-Only_Annotation.md new file mode 100644 index 000000000..dcdc361eb --- /dev/null +++ b/docs/Encyclopedia/pages/GATK4_MuTect2_Tumor-Only_Annotation.md @@ -0,0 +1,30 @@ +# GATK4 MuTect2 Tumor-Only Annotation + +## Description ## + +GATK4 MuTect2 Tumor-Only Annotation is a workflow used in GDC whole exome sequencing (WXS) and targeted sequencing harmonization. + + +## Overview ## + +GATK4 MuTect2 Tumor-Only Annotation is a workflow utilized in the GDC for annotating somatic variants identified in tumor-only whole exome sequencing (WXS) and targeted sequencing data. + +### Input + +* Tumor VCF - WXS or Targeted Sequencing + +### Output + +* VCF (Data Type: Annotated Somatic Mutation) +* MAF (Data Type: Annotated Somatic Mutation) + +## References ## + +1. [DNA-Seq Analysis Pipeline](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/) +1. [Tumor-Only Variant Annotation Workflow](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/#tumor-only-variant-annotation-workflow) + +## External Links ## + +* [GDC Data Portal](https://portal.gdc.cancer.gov) + +Categories: Workflow Type \ No newline at end of file diff --git a/docs/Encyclopedia/pages/MuSE.md b/docs/Encyclopedia/pages/MuSE.md new file mode 100644 index 000000000..17e3ffb6e --- /dev/null +++ b/docs/Encyclopedia/pages/MuSE.md @@ -0,0 +1,32 @@ +# MuSE + +## Description ## + +MuSE is a somatic variant calling pipeline used in GDC whole exome sequencing (WXS) and targeted sequencing harmonization. + +## Overview ## + +MuSE is one of the four pipelines used for WXS and targeted sequencing somatic variant calling at the GDC. Somatic variant calling is performed with MuSE using tumor and normal alignments and generates single-nucleotide polymorphism (SNP) data. + +### Input +* Tumor BAM - WXS or Targeted Sequencing +* Normal BAM - WXS or Targeted Sequencing + +### Output + +* VCF (Data Type: Raw Simple Somatic Mutation) + +[![MuSE Pipeline Diagram](https://gdc.cancer.gov/files/public/image/muse-somatic-variant-calling-pipeline.png)](https://gdc.cancer.gov/files/public/image/muse-somatic-variant-calling-pipeline.png "Click to see the full image.") + +## References ## + +1. [MuSE Command Line Parameters at the GDC](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/#muse) +1. [DNA Seq Processing at the GDC](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/) + +## External Links ## + +* [MuSE at MDACC](https://bioinformatics.mdanderson.org/public-software/muse/) +* [Overview of GDC Harmonization Workflows](https://github.com/NCI-GDC/gdc-workflow-overview/blob/master/README.md) +* [GDC Data Portal](https://portal.gdc.cancer.gov) + +Categories: Workflow Type \ No newline at end of file diff --git a/docs/Encyclopedia/pages/MuSE_Annotation.md b/docs/Encyclopedia/pages/MuSE_Annotation.md new file mode 100644 index 000000000..c68c77409 --- /dev/null +++ b/docs/Encyclopedia/pages/MuSE_Annotation.md @@ -0,0 +1,28 @@ +# MuSE Annotation + +## Description ## + +MuSE Annotation is a somatic mutation annotation pipeline in GDC whole exome sequencing (WXS) and targeted sequencing harmonization. + +## Overview ## + +MuSE Annotation is a workflow in the GDC that annotates somatic variants identified by the MuSE variant calling pipeline. + +### Input + +* VCF (Data Type: Raw Simple Somatic Mutation) + +### Output + +* MAF (Data Type: Annotated Somatic Mutation) +* VCF (Data Type: Annotated Somatic Mutation) + +## References ## + +1. [DNA-Seq Analysis Pipeline](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/) + +## External Links ## + +* [GDC Data Portal](https://portal.gdc.cancer.gov) + +Categories: Workflow Type \ No newline at end of file diff --git a/docs/Encyclopedia/pages/MuTect2.md b/docs/Encyclopedia/pages/MuTect2.md new file mode 100644 index 000000000..9ccf58439 --- /dev/null +++ b/docs/Encyclopedia/pages/MuTect2.md @@ -0,0 +1,31 @@ +# MuTect2 + +## Description ## + +MuTect2 is a somatic variant calling pipeline used in GDC whole exome sequencing (WXS) and targeted sequencing harmonization. + +## Overview ## + +MuTect2 is one of the four pipelines used for WXS and targeted sequencing somatic variant calling at the GDC. Somatic variant calling is performed with MuTect2 using tumor and normal alignments and generates single-nucleotide polymorphism (SNP) data. + +### Input + +* Tumor BAM - WXS or Targeted Sequencing +* Normal BAM - WXS or Targeted Sequencing + +### Output + +* VCF (Data Type: Raw Simple Somatic Mutation) + + +## References ## +1. [MuTect2 Command Line Parameters at the GDC](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/#mutect2) +1. [DNA Seq Processing at the GDC](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/) + + +## External Links ## +* [MuTect2 at the Broad](https://gatk.broadinstitute.org/hc/en-us/articles/360037593851-Mutect2) +* [Overview of GDC Harmonization Workflows](https://github.com/NCI-GDC/gdc-workflow-overview/blob/master/README.md) +* [GDC Data Portal](https://portal.gdc.cancer.gov) + +Categories: Workflow Type diff --git a/docs/Encyclopedia/pages/MuTect2_Annotation.md b/docs/Encyclopedia/pages/MuTect2_Annotation.md new file mode 100644 index 000000000..cadeb83b4 --- /dev/null +++ b/docs/Encyclopedia/pages/MuTect2_Annotation.md @@ -0,0 +1,28 @@ +# MuTect2 Annotation + +## Description ## + +MuTect2 Annotation is a somatic mutation annotation pipeline in GDC whole exome sequencing (WXS) and targeted sequencing harmonization. + +## Overview ## + +MuTect2 Annotation is a workflow in the GDC that annotates somatic variants identified by the MuTect2 variant calling pipeline. + +### Input + +* VCF (Data Type: Raw Simple Somatic Mutation) + +### Output + +* MAF (Data Type: Annotated Somatic Mutation) +* VCF (Data Type: Annotated Somatic Mutation) + +## References ## + +1. [DNA-Seq Analysis Pipeline](/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/) + +## External Links ## + +* [GDC Data Portal](https://portal.gdc.cancer.gov) + +Categories: Workflow Type \ No newline at end of file diff --git a/mkdocs.yml b/mkdocs.yml index 98e01af9b..a4d1a30e9 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -66,16 +66,6 @@ nav: - For Developers: Data_Portal/Users_Guide/Developers_Guide.md - Release Notes: Data_Portal/Release_Notes/Data_Portal_Release_Notes.md - fa-file-text Download PDF /Data_Portal/PDF/Data_Portal_UG.pdf: Data_Portal/PDF/index.md - - Data Portal v1.0: - - Getting Started: Data_Portal_V1/Users_Guide/Getting_Started.md - - Projects: Data_Portal_V1/Users_Guide/Projects.md - - Exploration: Data_Portal_V1/Users_Guide/Exploration.md - - Analysis: Data_Portal_V1/Users_Guide/Custom_Set_Analysis.md - - Repository: Data_Portal_V1/Users_Guide/Repository.md - - Advanced Search: Data_Portal_V1/Users_Guide/Advanced_Search.md - - Cart and File Download: Data_Portal_V1/Users_Guide/Cart.md - - Release Notes: Data_Portal_V1/Release_Notes/Data_Portal_V1_Release_Notes.md - - fa-file-text Download PDF /Data_Portal_V1/PDF/Data_Portal_V1_UG.pdf: Data_Portal_V1/PDF/index.md - Data Submission: - Before Submitting Data to the GDC Portal: Data_Submission_Portal/Users_Guide/Checklist.md - Data Submission Overview: Data_Submission_Portal/Users_Guide/Data_Submission_Overview.md diff --git a/theme/homepage.html b/theme/homepage.html index 1225cb360..ab49249f0 100644 --- a/theme/homepage.html +++ b/theme/homepage.html @@ -8,9 +8,9 @@ ('For Researchers', '#1db888', '/img/hp-icons-researcher.png', [ ('Understand the Data in the GDC', '/Data/Introduction/'), ('Access Controlled Data in the GDC', '/Data/Data_Security/Data_Security/'), - ('Explore Data in the GDC', '/Data_Portal_V1/Users_Guide/Exploration/'), + ('Explore Mutations in the GDC', '/Data_Portal/Users_Guide/mutation_frequency/'), ('Download Files in the GDC', '/Data_Transfer_Tool/Users_Guide/Preparing_for_Data_Download_and_Upload/'), - ('Analyze Data in the GDC', '/Data_Portal_V1/Users_Guide/Custom_Set_Analysis/') + ('Analyze Data in the GDC', '/Data_Portal/Users_Guide/analysis_center/') ]), ('For Data Submitters', '#676bc0', '/img/hp-icons-submitter.png', [ ('View the GDC Data Dictionary', '/Data_Dictionary/viewer/'),