diff --git a/overview/tool_catalog/index.html b/overview/tool_catalog/index.html
index fc3ab626..105fcede 100644
--- a/overview/tool_catalog/index.html
+++ b/overview/tool_catalog/index.html
@@ -3,7 +3,7 @@
diff --git a/resources/js/config.js b/resources/js/config.js
index e0c4a160..f7c82612 100644
--- a/resources/js/config.js
+++ b/resources/js/config.js
@@ -1 +1 @@
-var __DOCS_CONFIG__ = {"id":"nDlbk3h3250R78VK/vbEflgIiwXA+y4LpRF","key":"5EmnJJ9/mtMIRq4+SoBcGe6kxoMCI7TNJE8lwOawEWE.AfNSkWEaqMMEu7pjBUTjiorIxDoIMEUgQA2creVBQanNrQqaYh9hX9+l7WMoIiKl1OW3Fy6k4UOqUAiDTA6enw.30","base":"/","host":"","version":"1.0.0","useRelativePaths":true,"documentName":"index.html","appendDocumentName":false,"trailingSlash":true,"preloadSearch":false,"cacheBustingToken":"3.5.0.751044021183","cacheBustingStrategy":"query","sidebarFilterPlaceholder":"Filter","toolbarFilterPlaceholder":"Filter","showSidebarFilter":true,"filterNotFoundMsg":"No member names found containing the query \"{query}\"","maxHistoryItems":15,"homeIcon":"
","access":[{"value":"public","label":"Public"},{"value":"protected","label":"Protected"}],"toolbarLinks":[{"id":"fields","label":"Fields"},{"id":"properties","label":"Properties"},{"id":"methods","label":"Methods"},{"id":"events","label":"Events"}],"sidebar":[{"n":"/","l":"HTAN: The Missing Manual"},{"n":"overview","l":"Overview","c":false,"i":[{"n":"introduction","l":"Introduction to HTAN"},{"n":"centers","l":"HTAN Centers"},{"n":"data_levels","l":"HTAN Data Levels"},{"n":"tool_catalog","l":"HTAN Tool Catalog"}]},{"n":"data_model","l":"Data Model","c":false,"i":[{"n":"overview","l":"Data Model"},{"n":"identifiers","l":"Identifiers"},{"n":"clinical","l":"Clinical Metadata"},{"n":"biospecimens","l":"Biospecimen Metadata"},{"n":"sequencing","l":"Sequencing Data"},{"n":"imaging","l":"Imaging Data"},{"n":"spatial_transcriptomics","l":"Spatial Transcriptomics"},{"n":"relationships","l":"Relationship Model"}]},{"n":"open_access","l":"Open Access Data","c":false,"i":[{"n":"introduction","l":"Open Access Data"},{"n":"portal","l":"Using the HTAN Data Portal"},{"n":"cell_by_gene","l":"Visualizing Single Cell Data via CellxGene"},{"n":"minerva","l":"Visualizing Multiplex Imaging Data via Minerva"},{"n":"image_data_commons","l":"Accessing Images via Image Data Commons (IDC)"},{"n":"cds_imaging","l":"Accessing Images via SB-CGC Cancer Data Service (CDS)"},{"n":"biq_query","l":"Google BigQuery"}]},{"n":"access_controlled","l":"Access Controlled Data","c":false,"i":[{"n":"introduction","l":"Access-Controlled Data"},{"n":"db_gap","l":"Requesting dbGaP Access"},{"n":"cds_access","l":"NCI's Cancer Data Service"},{"n":"sb-cgc_access","l":"SB-CGC Cancer Data Service (CDS) Explorer"}]}],"search":{"mode":0,"minChars":2,"maxResults":20,"placeholder":"Search","hotkeys":["k"],"noResultsFoundMsg":"Sorry, no results found.","recognizeLanguages":true,"languages":[0],"preload":false},"resources":{"History_Title_Label":"History","History_ClearLink_Label":"Clear","History_NoHistory_Label":"No history items","API_AccessFilter_Label":"Access","API_ParameterSection_Label":"PARAMETERS","API_SignatureSection_Label":"SIGNATURE","API_CopyHint_Label":"Copy","API_CopyNameHint_Label":"Copy name","API_CopyLinkHint_Label":"Copy link","API_CopiedAckHint_Label":"Copied!","API_MoreOverloads_Label":"more","API_MoreDropdownItems_Label":"More","API_OptionalParameter_Label":"optional","API_DefaultParameterValue_Label":"Default value","API_InheritedFilter_Label":"Inherited","Search_Input_Placeholder":"Search","Toc_Contents_Label":"Contents","Toc_RelatedClasses_Label":"Related Classes","History_JustNowTime_Label":"just now","History_AgoTime_Label":"ago","History_YearTime_Label":"y","History_MonthTime_Label":"mo","History_DayTime_Label":"d","History_HourTime_Label":"h","History_MinuteTime_Label":"m","History_SecondTime_Label":"s"}};
+var __DOCS_CONFIG__ = {"id":"+250wtmpigB+qdZ1qDkcvLkSddGvBj9v417","key":"RVhGwhb8hlsIOTGyLeFJQcVFk/tmyJ6m/AS8r4kceY8.fwmck0XGXOge6YuD836t+QBYHNZF3V/Hn0RH5KnLD83TL/WTS/j4SVEkXXNrpZXbKgHQi9rvvT+mahz1B2dc1w.37","base":"/","host":"","version":"1.0.0","useRelativePaths":true,"documentName":"index.html","appendDocumentName":false,"trailingSlash":true,"preloadSearch":false,"cacheBustingToken":"3.5.0.751044209728","cacheBustingStrategy":"query","sidebarFilterPlaceholder":"Filter","toolbarFilterPlaceholder":"Filter","showSidebarFilter":true,"filterNotFoundMsg":"No member names found containing the query \"{query}\"","maxHistoryItems":15,"homeIcon":"
","access":[{"value":"public","label":"Public"},{"value":"protected","label":"Protected"}],"toolbarLinks":[{"id":"fields","label":"Fields"},{"id":"properties","label":"Properties"},{"id":"methods","label":"Methods"},{"id":"events","label":"Events"}],"sidebar":[{"n":"/","l":"HTAN: The Missing Manual"},{"n":"overview","l":"Overview","c":false,"i":[{"n":"introduction","l":"Introduction to HTAN"},{"n":"centers","l":"HTAN Centers"},{"n":"data_levels","l":"HTAN Data Levels"},{"n":"tool_catalog","l":"HTAN Tool Catalog"}]},{"n":"data_model","l":"Data Model","c":false,"i":[{"n":"overview","l":"Data Model"},{"n":"identifiers","l":"Identifiers"},{"n":"clinical","l":"Clinical Metadata"},{"n":"biospecimens","l":"Biospecimen Metadata"},{"n":"sequencing","l":"Sequencing Data"},{"n":"imaging","l":"Imaging Data"},{"n":"spatial_transcriptomics","l":"Spatial Transcriptomics"},{"n":"relationships","l":"Relationship Model"}]},{"n":"open_access","l":"Open Access Data","c":false,"i":[{"n":"introduction","l":"Open Access Data"},{"n":"portal","l":"Using the HTAN Data Portal"},{"n":"cell_by_gene","l":"Visualizing Single Cell Data via CellxGene"},{"n":"minerva","l":"Visualizing Multiplex Imaging Data via Minerva"},{"n":"image_data_commons","l":"Accessing Images via Image Data Commons (IDC)"},{"n":"cds_imaging","l":"Accessing Images via SB-CGC Cancer Data Service (CDS)"},{"n":"biq_query","l":"Google BigQuery"}]},{"n":"access_controlled","l":"Access Controlled Data","c":false,"i":[{"n":"introduction","l":"Access-Controlled Data"},{"n":"db_gap","l":"Requesting dbGaP Access"},{"n":"cds_access","l":"NCI's Cancer Data Service"},{"n":"sb-cgc_access","l":"SB-CGC Cancer Data Service (CDS) Explorer"}]}],"search":{"mode":0,"minChars":2,"maxResults":20,"placeholder":"Search","hotkeys":["k"],"noResultsFoundMsg":"Sorry, no results found.","recognizeLanguages":true,"languages":[0],"preload":false},"resources":{"History_Title_Label":"History","History_ClearLink_Label":"Clear","History_NoHistory_Label":"No history items","API_AccessFilter_Label":"Access","API_ParameterSection_Label":"PARAMETERS","API_SignatureSection_Label":"SIGNATURE","API_CopyHint_Label":"Copy","API_CopyNameHint_Label":"Copy name","API_CopyLinkHint_Label":"Copy link","API_CopiedAckHint_Label":"Copied!","API_MoreOverloads_Label":"more","API_MoreDropdownItems_Label":"More","API_OptionalParameter_Label":"optional","API_DefaultParameterValue_Label":"Default value","API_InheritedFilter_Label":"Inherited","Search_Input_Placeholder":"Search","Toc_Contents_Label":"Contents","Toc_RelatedClasses_Label":"Related Classes","History_JustNowTime_Label":"just now","History_AgoTime_Label":"ago","History_YearTime_Label":"y","History_MonthTime_Label":"mo","History_DayTime_Label":"d","History_HourTime_Label":"h","History_MinuteTime_Label":"m","History_SecondTime_Label":"s"}};
diff --git a/resources/js/search.json b/resources/js/search.json
index 0f1f7b23..52924943 100644
--- a/resources/js/search.json
+++ b/resources/js/search.json
@@ -1 +1 @@
-[[{"i":"htan-the-missing-manual","l":"HTAN: The Missing Manual","p":["Written by the HTAN Data Coordinating Center (DCC), with contributions from Adam Taylor, Clarisse Lau, Vésteinn Thorsson, Ino de Bruijn, David Gibbs, Ethan Cerami and Alex Lash."]},{"l":"About this Manual","p":["HTAN: The Missing Manual provides an overview of Human Tumor Atlas Network (HTAN) data and the various modes of data access. If you have any questions regarding the manual or HTAN data, please contact us at: htan@googlegroups.com.","The manual can be found at https://docs.humantumoratlas.org/."]},{"l":"Content Updates","p":["Date","Comment","2023-06-01","Second version of manual","2022-09-28","First version of manual."]}],[{"l":"Introduction to HTAN","p":["The Human Tumor Atlas Network (HTAN) is a National Cancer Institute-funded Cancer Moonshot initiative focused on studying the transitions of human cancers as they evolve from precancerous lesions to advanced disease.","The network consists of ten research centers and a Data Coordinating Center (DCC). Five of the research centers are focused on developing pre-cancer atlases, and the remaining five centers are focused on developing tumor atlases. We also have two pilot projects, one focused on pre-cancer atlases, and one focused on tumor atlases.","Each research center is responsible for gathering and processing samples, and running their own experimental assays. Assays vary by center, but most centers have a strong focus on single cell RNA-Seq and a wide range of multiplex imaging modalities.","All centers are required to submit their clinical, biospecimen and assay data to the HTAN DCC using a common HTAN Data Model. The DCC makes HTAN data available to the wider scientific community.","Complete information regarding the HTAN network is available at: https://humantumoratlas.org/.","You can explore all open access data within the HTAN Data Portal at: https://humantumoratlas.org/explore.","A complete list of HTAN Publications is available on Google Scholar.","The current status of data uploads (refreshed every 4 hours) is available on the HTAN Dashboard."]}],[{"l":"HTAN Centers","p":["Area of Focus","Atlas Type","Boston University","Breast","Children’s Hospital of Philadelphia","Colorectal","Contact Institution or Project Name","Dana-Farber Cancer Institute","Duke University","Familial Adenomatous Polyposis","For details on each center, please see: https://humantumoratlas.org/research-network.","Harvard Medical School","HTA1","HTA10","HTA11","HTA12","HTA13","HTA14","HTA2","HTA3","HTA4","HTA5","HTA6","HTA7","HTA8","HTA9","Human Tumor Atlas Pilot Project (HTAPP)","Lung","Melanoma and Clonal Hematopoiesis","Memorial Sloan Kettering Cancer Center","Multiple Cancer Types","Oregon Health Science University","Pediatric","Pilot Project","Pre-Cancer Atlas","Pre-Cancer Atlas Pilot Project (PCAPP)","Prefix","Stanford University","Technology Comparison","The HTAN Network consists of ten research centers, and two pilot projects. We also run multiple trans-network projects, referred to as TNPs. Each research center or TNP Project is identified with a unique HTAN prefix.","TNP Atlas","TNP: SARDANA","TNP: Tissue MicroArray (TMA)","Tumor Atlas","Vanderbilt University","Washington University in St. Louis"]}],[{"l":"HTAN Data Levels","p":["HTAN data is categorized into two data access levels:","Open access: includes de-identified clinical and biospecimen data, multiplex images, and processed genomic data. This data is available via the HTAN Data Portal. See Open Access Data.","Access controlled: includes unprocessed genomic data, e.g. BAM files. Similar to TCGA BAM files, this data is available via an approved dbGaP mechanism. See Controlled-Access Data.","We maintain a running update of HTAN data releases and updates at: https://data.humantumoratlas.org/data-updates."]}],[{"l":"HTAN Tool Catalog","p":["The HTAN Network consists of ten research centers and two pilot projects. The results from each project have been built using an array of computational tools, now collected into a catalog which is available on the portal. These tools are sure to be compatible with HTAN data!","For the most current listing of available tools, please see the HTAN data portal."]}],[{"l":"Data Model","p":["All HTAN Centers are required to encode their data and metadata in the common HTAN Data Model. The HTAN Data Model was created via a community Request for Comment (RFC) process, with participation from all HTAN Centers, and covers clinical data, biospecimen data, genomic data and multiplex imaging data.","As much as possible, the HTAN Data Model leverages previously defined data standards across the scientific research community, including the NCI Genomic Data Commons, the Human Cell Atlas, the Human Biomolecular Atlas Program (HuBMAP) and the Minimum Information about Tissue Imaging (MITI) reporting guidelines.","Complete information regarding the HTAN Data Model is available at: https://data.humantumoratlas.org/standards."]}],[{"l":"Identifiers","p":["All research participants, biospecimens and derived data within HTAN are associated with a unique HTAN identifier.","Boston University","Children's Hospital of Philadelphia","Dana-Farber Cancer Institute","Derivative data includes anything derived from a research participant, including biospecimens such as samples, tissue blocks, slides, aliquots, analytes, and data files that result from assaying those biospecimens. These identifiers follow the pattern:","Duke University","For example, if research participant 1 within the CHOP project has provided three samples, you would have three HTAN IDs, such as:","Harvard Medical School","HTA1","HTA10","HTA11","HTA12","HTA13","HTA14","HTA2","HTA3","HTA4","HTA5","HTA6","HTA7","HTA8","HTA9","HTAN Center ID","HTAN ID Provenance","HTAPP Pilot Project","If a single data file is generated from one of those samples, that file could have an HTAN ID such as:","Memorial Sloan Kettering Cancer Center","More detailed information about HTAN Identifiers may be found in the HTAN Identifiers SOP.","Note that the explicit linking of participants to biospecimens to assays is not encoded in the HTAN Identifier. Rather, the linking is encoded in explicit metadata elements (see Relationship Model).","Oregon Health Sciences University","PCAPP Pilot Project","Pilot Project or Contact PI Institution","Research participants are identified with the following pattern:","Stanford University","TNP SARDANA","TNP TMA","Vanderbilt University","Washington University","Where the htan_center_id is derived from the identifier prefix table below."]}],[{"l":"Clinical Metadata","p":["The HTAN clinical data model consists of three tiers. Tier 1 is in alignment with the Genomic Data Commons (GDC) guidelines for clinical data, while Tiers 2 and 3 are HTAN extensions to the GDC model.","Tier","Notes","1","Tier 1 is based entirely on the clinical data model used by the NCI Genomic Data Commons (GDC) [6]. It consists of seven categories of clinical data (see GDC Table below).","2","Disease-agnostic extensions to the GDC Clinical Data Model.","3","Disease-specific extensions to the GDC Clinical Data Model. This covers additional elements for Acute Lymphoblastic Leukemia (ALL), Brain Cancer, Breast Cancer, Lung Cancer, Melanoma, Ovarian Cancer, Pancreatic Cancer, Prostate Cancer and Sarcoma."]},{"l":"GDC Clinical Data Model","p":["A visit by a patient or study participant to a medical professional. A clinical encounter that encompasses planned and unplanned trial interventions, procedures and assessments that may be performed on a subject. A visit has a start and an end, each described with a rule. The process by which information about the health status of an individual is obtained before and after a study has officially closed; an activity that continues something that has already begun or that repeats something that has already been done.","Clinically relevant patient information not immediately resulting from genetic predispositions.","Complete details regarding all clinical data elements is available at: https://data.humantumoratlas.org/standard/clinical","Data for the characterization of the patient by means of segmenting the population (e.g., characterization by age, sex, or race).","Data from the investigation, analysis and recognition of the presence and nature of disease, condition, or injury from expressed signs and symptoms; also, the scientific determination of any kind; the concise results of such an investigation.","Demographics","Diagnosis","Exposure","Family History","Follow-up","GDC Category","GDC Description","Information pertaining to any molecular tests performed on the patient during a clinical event.","Molecular Test","Record of a patient's background regarding cancer events of blood relatives.","Record of the administration and intention of therapeutic agents provided to a patient to alter the course of a pathologic process.","The GDC Clinical Data Model consists of seven categories of clinical data.","Therapy"]}],[{"l":"Biospecimen Metadata","p":["The HTAN biospecimen data model is designed to capture essential biospecimen data elements, including:","Acquisition method, e.g. autopsy, biopsy, fine needle aspirate, etc.","Topography Code, indicating site within the body, e.g. based on ICD-O-3.","Collection information e.g. time, duration of ischemia, temperature, etc.","Processing of parent biospecimen information e.g. fresh, frozen, etc.","Biospecimen and derivative clinical metadata ie Histologic Morphology Code, e.g. based on ICD-O-3.","Coordinates for derivative biospecimen from their parent biospecimen.","Processing of derivative biospecimen for downstream analysis e.g. dissociation, sectioning, analyte isolation, etc.","Complete details are available online at: https://data.humantumoratlas.org/standard/biospecimen"]}],[{"l":"Sequencing Data","p":["1","2","3","4","Aligned BAMs","Aligned primary data","Definition","Derived biomolecular data","Example Data","FASTQs, unaligned BAMs","Gene expression matrix files, VCFs, etc.","HTAN has adopted the GENCODE 34 Gene Transfer Format ( GTF) comprehensive gene annotation file (GENCODE 34 GTF) and filtered files (GENCODE 34 GTF with genes only; GENCODE 34 GTF with genes only and retaining only chromosome X copy of pseudoautosomal region) for HTAN gene annotation. Note that HTAN also includes data generated with other gene models, as the process of implementing the standard is ongoing. Within HTAN metadata files, the reference genome used can be found in the attribute “Genomic Reference” and “Genomic Reference URL”.","HTAN supports multiple sequencing modalities including Single Cell and Single Nucleus RNA Seq (sc/snRNASeq), Single Cell ATAC Seq, Bulk RNA Seq and Bulk DNA Seq.","In alignment with The Cancer Genome Atlas and the NCI Genomic Data Commons, sequencing data are divided into four levels:","Level","Raw data","Sample level summary data.","t-SNE plot coordinates, etc.","The HTAN standard for gene annotations is GENCODE Version 34. GENCODE is used for gene definitions by many consortia, including ENCODE, NCI Genomic Data Commons, Human Cell Atlas, and PCAWG (Pan-Cancer Analysis of Whole Genomes). Ensembl gene content is essentially identical to that of GENCODE ( FAQ) and interconversion is possible."]}],[{"l":"Imaging Data","p":["The HTAN data model for imaging data is based upon the Minimum Information about Tissue Imaging (MITI) reporting guidelines. These comprise minimal metadata for highly multiplexed tissue images and were developed in consultation with methods developers, experts in imaging metadata (e.g., DICOM and OME) and multiple large-scale atlas projects; they are guided by existing standards and accommodate most multiplexed imaging technologies and both centralized and distributed data storage.","For further information on the MITI guidelines, please see the MITI website, specification on Github, and Nature Methods publication.","The HTAN data model for imaging was intended primarily for multiplexed imaging such as CODEX, CyCIF, and IMC, in addition to brightfield imaging of H&E stained tissues.","As with Sequencing data, the imaging data model is split into data levels as follows:","Level","Description","1","Raw imaging data requiring tiling, stitching, illumination correction, registration or other pre-processing.","2","Imaging data compiled into a single file format, preferably a tiled and pyramidal OME-TIFF. Accompanied by a csv file containing channel metadata.","3","Segmentation mask, Validated channel metadata, QC checked image.","4","An object-by-feature table (typically cell-by-marker) generated from the segmentation mask and image.","Before preparing imaging data for upload to DCC, please consult HTAN Imaging Data Requirements."]}],[{"l":"Spatial Transcriptomics","p":["Alignment workflows downstream of Spatial Transcriptomics RNA-seq Level 1.","Auxiliary data associated with spot/slide analysis (aligned Images, quality control files, etc) from Spatial Transcriptomics.","Description","Files contain raw RNA-seq data associated with spot/slide data.","Imaging data compiled into a single file format, preferably a tiled and pyramidal OME-TIFF.","Imaging Level 2","Level","Processed data files based on Spatial Transcriptomics RNA-seq Level 2 and Spatial Transcriptomics Auxiliary files.","Processed data files based on Spatial Transcriptomics RNA-seq Level 3.","Spatial transcriptomic datasets are typically comprised of RNA-sequencing data at varying levels, coupled with imaging data and an auxiliary set of files used in or generated by processing workflows for spatial transcriptomics:","Spatial Transcriptomics Auxiliary Files","Spatial Transcriptomics RNA-seq Level 1","Spatial Transcriptomics RNA-seq Level 2","Spatial Transcriptomics RNA-seq Level 3","Spatial Transcriptomics RNA-seq Level 4","The HTAN data model currently supports 10X Visium data, but additional platforms will be added in the near future including Nanostring GeoMX and Pick-Seq.","The HTAN data model for spatial transcriptomics data is based upon both imaging and single cell sequencing data models. These form a collection of metadata fields where transcriptomic levels (or gene or protein level measures) can be mapped to locations on a tissue slide, and were developed in consultation with the data generating centers who are both experts in imaging metadata (e.g. DICOM and OME) and multiple large-scale atlas projects."]}],[{"l":"Relationship Model","p":["Each atlas in HTAN contains data provided by multiple research participants, who have donated biospecimens (see Figure below). The metadata allows one to trace back any data file to the donated biospecimen. Level 1 raw data files are directly linked to the corresponding biospecimen, whereas processed level 2-4 data files are linked to lower level parent data files. Note also that biospecimens can be connected recursively.","HTAN ID Provenance"]},{"l":"HTAN ID Provenance Table","p":["The HTAN DCC has constructed an ID Provenance BigQuery table, which contains upstream biospecimen and participant information for each HTAN data file. The motivation for constructing the table arose from the need for a straightforward method of showcasing how HTAN data files are linked to biospecimens and patients.","Although this information is available in HTAN, connections among assay file levels and parent relationships (both biospecimen and file) were previously only accessible by tracing through parent identifiers. Having all ID information in one place can significantly speed up analyses, exploration, and data sharing.","The Provenance BigQuery table is accessible via ISB-CGC. See the Google BigQuery section for more details."]},{"l":"Biospecimen Attribute Definitions","p":["Given the complexity of biospecimen relationships, we've adopted the following nomenclature to describe biospecimen lineages:","Originating Biospecimen: the biopsied or resected biospecimen from the patient from which the assay data were derived","Assayed Biospecimen: the biospecimen directly assayed using the experimental platform","Biospecimen Path: path of biospecimens from Originating to Assayed; comma-separated"]},{"l":"Provenance Table Construction","p":["As illustrated in the figure above, biospecimens can be subsampled multiple times. However, HTAN metadata tables provide only the immediate parent biospecimen. To assemble the full biospecimen path, we perform a series of joins on the biospecimen table, walking up the parent biospecimen ancestry chain until no further parents are found.","Similarly, we can have up to four data file ‘levels’. Each data file is linked using its provided parent HTAN data file ID(s).","We then join biospecimen information with file-level annotations to form the final ID provenance table.","Provenance Table Columns"]},{"l":"Table Contents","p":["In addition to upstream biospecimen and participant IDs, the provenance table also includes a number of informational columns, such as entityId(Synapse ID of the source file), HTAN_Center(text version of center code), and Data_Release and CDS_Release which indicate which HTAN Portal release and CDS release the file was included in, respectively.","Provenance Table Columns"]}],[{"l":"Open Access Data","p":["Open access HTAN data is available via:","The HTAN Data Portal","NCI Image Data Commons (IDC)","Google BigQuery"]}],[{"l":"Using the HTAN Data Portal","p":["The HTAN Data Portal provides access to all open access HTAN data. To get started, go to: https://data.humantumoratlas.org/explore.","To orient you to the HTAN Data Portal, consider the example of accessing precancerous polyp data from Vanderbilt University, as described in their recent Cell publication.","By default, HTAN data is organized by research center:","HTAN Portal: Home Page","If you scroll down on the page, you will see Vanderbilt University:","HTAN Portal: Vanderbilt Atlas","As of this writing, you can see that the Vanderbilt Colon Atlas project has 90 cases and 193 biospecimens."]},{"l":"Downloading Metadata","p":["Once you have identified the project of interest, you can click the download metadata button:","HTAN Portal: Download Metadata","You will then be prompted with a dialog box of all metadata associated with the specified project. For example:","HTAN Portal: Metadata Table","Behind the scenes, HTAN leverages the Synapse Platform created and maintained by Sage Bionetworks. Each piece of HTAN data is automatically assigned a unique Synapse identifier, such as syn25010909. In the screenshot above, you can see that the Vanderbilt project has multiple metadata files, each associated with a unique Synapse identifier.","If you click on any of the Synapse links above, you can immediately download a comma separated value (CSV) file associated with the metadata category. There is no need to create a Synapse account or log into Synapse. For example, here we have download the Vanderbilt biospecimen file and loaded it into Excel:","HTAN Tabular Data within Excel","Once you have downloaded metadata files, you can parse them in your favorite programming language, such as R or Python. To understand the individual columns within each metadata file, please refer to the HTAN Data Model."]},{"l":"Exploring Available Data","p":["At this point, the Files tab is likely to contain hundreds of files, and may be difficult to navigate. You can further refine the files table by clicking on the Assay Type or File Type filters. This will trigger pop-up windows that describe the assay and file type categories available within the Vanderbilt project. For example, if you click Assay Type you will see:","Clicking Level 4 here will now filter the File table to only include Level 4 sequencing data that consists of Single Cell RNA Seq h5ad formatted files:","Clicking View Details on any of these files will pop open a metadata table. For example:","Data that is available within the Vanderbilt project is set to bold. You can therefore see that the Vanderbilt project has Bulk DNA, H&E Images, Multiplex ImmunoFluorescence images and Single Cell RNA Seq Data.","HTAN Portal: Files Tab","HTAN Portal: Filter by Assay Type","HTAN Portal: Filter by File Type","HTAN Portal: Filter by HTAN Center","HTAN Portal: Filter by Vanderbilt University","HTAN Portal: Filters","HTAN Portal: Metadata Details","HTAN Portal: Multiple Filters Enabled","HTAN Portal: Removing Filters","If you click scRNA-seq, the file table will automatically update. You can then select the File Type filter to drill-down even further:","If you click the Cases or Biospecimens tabs, you can browse available metadata. Clicking the Files tab will take you to an interactive table listing all files available for download.","Note that you can remove any existing filters by clicking on any of the “chips” in the page header. For example, if you want to remove the Level 4 filter, just click the Level 4 chip:","The HTAN Data Portal provides a unified interface for filtering and exploring HTAN data sets. Each filter is available at the top of the page:","To get started, you can click the Atlas pull-down menu, and select the Vanderbilt HTAN center:","Your selection will now be reflected in the user interface:"]},{"l":"Downloading Open Access Data","p":["Once you have specified your filter criteria, the Files tab will display all matching files. At this point, you may see two types of files:","Open Access Files; and","Access Controlled Files","To download open access files, you will need to first create a free account on the Synapse data platform. To register an account, goto https://www.synapse.org/, and click the Register button.","Once registered and logged into Synapse, you can then click through from the HTAN Data Portal to the corresponding page on Synapse. For example, this CSV file corresponds to single cell data generated by the Vanderbilt project:","Synapse Page","You can click the Download Options button to download the file. To retrieve the same file via R, Python or via the command line, click the Download Options button and select Programmatic Options.","To download access-controlled files, please refer to Access Controlled Data Access."]}],[{"l":"Visualizing Single Cell Data via CellxGene","p":["Through our collaboration with the Chan Zuckerberg Initiative (CZI), we make HTAN single cell RNA seq data available via CellxGene. CellxGene enables you to visualize and explore large-scale single cell data sets. For complete details on CellxGene, please refer to the online documentation.","HTAN data sets with CellxGene visualization are denoted on the main home page in the rightmost column. Clicking the CellxGene logo will take you directly to CellxGene.","HTAN Portal: Links to CellxGene","Example HTAN data from MSKCC, as visualized in CellxGene is shown below:","CellxGene: Example MSKCC HTAN Data"]}],[{"l":"Visualizing Multiplex Imaging Data via Minerva","p":["Through our collaboration with the Laboratory of Systems Pharmacology (LSP) at Harvard Medical School, many HTAN images can be visualized via Minerva, a web-based tool that enables interactive viewing and fast sharing of large image data.","Where a Minerva story is available on the HTAN Data Portal, a link will be visible when hovering over the thumbnail image in the View Column.","HTAN Portal: Links to Minerva","For most images, a basic Minerva story has been prepared using Auto Minerva, a tool to prepare default Minerva stories with optimized channel thresholds. An example prepared with Auto Minerva is shown below.","HTAN Portal: Auto Minerva Example","The image can be zoomed and panned with the mouse. Channel groups can be selected using the bar on the right. Selected metadata is shown in the left panel and can be collapsed. Point, box and polygon annotations can be generated and shared as a URL.","For some images, centers have provided custom Minerva stories leveraging features such as waypoints, annotations, data overlays and narrative text. An example custom Minerva story is shown below.","HTAN Portal: Curated Minerva Example"]}],[{"i":"accessing-images-via-image-data-commons-idc","l":"Accessing Images via Image Data Commons (IDC)","p":["HTAN Imaging Level 2 data is now available through the NCI Imaging Data Commons (IDC).","Imaging Data Commons hosts versions of the HTAN Imaging Level 2 data converted to DICOM-TIFF dual personality files. For further information and an example open source implementation, see online reference.","For further information on using the IDC, you can explore their online documentation."]},{"l":"Filtering for HTAN Images in the IDC portal","p":["From the homepage of the Imaging Data Commons, click the purple Explore link to explore image data.","HTAN data can be selected by selecting in the Collection group in the left-hand bar (you may need to click \"show more\" to reveal all collections).","IDC: Filter for HTAN Images","Pie charts show the breakdown of selected metadata attributes.","By checking collections (e.g. HTAN WUSTL), cases (participants), studies (biospecimens), and series (images), the study instances of selected images may be found."]},{"l":"Download Images from IDC","p":["HTAN data is shared under a CC-BY 4.0 license, and is available to download as DICOM images without egress costs from IDC thanks to support from the Google public datasets program. For complete details, see IDC Documentation on Downloading Data. Basic download instructions are also included on the HTAN portal for files released by the IDC, by selecting the filename.","HTAN Data Portal: IDC Download Details","Note that individual DICOM files representing each channel and pyramid level may need to be sorted or converted back to TIFF files for reuse in image analysis tools."]},{"l":"Viewing Images via the IDC SLIM Viewer","p":["Clicking they eye icon in the view column on the IDC portal, or the IDC link when hovering over the thumbnail in the HTAN portal, takes the user to IDC’s interactive SLIM viewer. This interactive viewer provides image exploration and pre-rendered scenes.","IDC: Interactive SLIM Viewer"]}],[{"i":"accessing-images-via-sb-cgc-cancer-data-service-cds","l":"Accessing Images via SB-CGC Cancer Data Service (CDS)","p":["HTAN Imaging Level 2 data is now available through the NCI SB-CGC Cancer Data Service (CDS).","Data access via Seven Bridges Cancer Genomics Cloud (SB-CGC) requires a CGC account [register here]. For further information on using SB-CGC resources including programmatic access options, you can explore their online documentation."]},{"l":"Filtering for HTAN Images in the CDS File Repository","p":["From the SB-CGC dashboard, click Cancer Data Service Explorer under the Data tab.","CDS: Accessing the CDS file explorer","Select Explore files","From the sidebar, filter by Dataset: HTAN and Experimental Strategy: ImagingLevel2","CDS: Filter by HTAN study CDS: Filter for imaging data","This provides a listing of all HTAN Imaging Level 2 data that is currently available through CDS.","CDS: HTAN Imaging Data on CDS"]},{"l":"Download Images from CDS","p":["Additional filters are available for further selection including Data format, Site, etc., as well as text search fields to search files by Filename, case ID (HTAN Participant ID), and sample ID (HTAN Biospecimen ID).","Once you have filtered to your files of interest, click Copy to project to add the selected files to the SB-CGC project of your choosing (create a new project if you do not have one set up).","CDS: Add selected files to project","You will be automatically re-directed to the Files tab of your SB-CGC project. From here, check the boxes of the files you would like to save. Clicking Download will download the selected images to your local machine.","CDS: Download selected imaging files"]}],[{"l":"Google BigQuery","p":["Google BigQuery is a massively-parallel analytics engine ideal for working with tabular data. Through our collaboration with the Institute for Systems Biology Cancer Gateway in the Cloud (ISB-CGC), open-access HTAN BigQuery tables are now available, and updated with each major HTAN release.","HTAN BigQuery tables can be accessed through the ISB-CGC Table Search UI and via the HTAN Data Portal.","For complete documentation regarding ISB-CGC BigQuery functionality, check out their online documentation.","You must have a Google account to access Google Big Query.","Google Cloud Platform’s free tier allows users to access many common Google Cloud resources, including BigQuery free of charge and query up to 1 TB of data per month for free."]},{"l":"Accessing Metadata tables","p":["HTAN metadata is organized by data type and level (see HTAN Data Model), with each BigQuery table containing data from all HTAN Centers combined.","Metadata tables can be accessed from the Atlases tab of the HTAN Data Portal. Click the icon under the Metadata column and scroll down to the Google BigQuery link at the bottom of the popup window.","HTAN Portal: Accessing Metadata","HTAN Portal: Linking to BiqQuery Tables","This link will take you to the ISB-CGC Table Search UI filtered to HTAN tables. Browse the table listing to find your table of interest, and click the magnifying glass icon under Open to launch the table in the BigQuery console.","ISB-CGC: Table Search ISB-CGC: Table Browser","Alternatively, you can start at the ISB-CGC Table Search UI and select Launch under BigQuery Table Search.","ISB-CGC: Launch BigQuery","Then filter for HTAN tables by selecting HTAN from the Program dropdown.","ISB-CGC: Filter for HTAN Table"]},{"l":"Example Query","p":["As an example, this simple query tabulates the overall distribution of gender in HTAN, as reported in the HTAN Clinical Demographics BigQuery table isb-cgc-bq.HTAN_versioned.clinical_tier1_demographics_r2. For complete details on running queries and the Biq Query syntax, refer to the Google BiqQuery Documentation.","ISB-CGC: Sample Query"]},{"l":"Accessing Single Cell Tables","p":["We currently host multiple single cell BigQuery tables via ISB-CGC. These tables are derived from level 4 H5AD AnnData files submitted by HTAN centers.","When a BigQuery table is available for a given file, a link will be visible in the View Column of the HTAN Data Portal.","HTAN Portal: BigQuery Links","This link will take you to the ISB-CGC Table Search UI listing for the selected single cell file. Click the magnifying glass icon under Open to launch the table in the BigQuery console.","BigQuery: Details BigQuery: Details"]},{"i":"example-query-1","l":"Example Query","p":["In this example, we query the single cell RNA seq-derived gene expression data for non-epithelial cells in colon polyps published by the Vanderbilt HTAN center. We filter cells to those expressing the leukocyte marker CD45, coded by gene PTPRC, and enumerate cells by their identified phenotype (B = B cell, T = T cell, END = endothelial, FIB = fibroblast, MAS = mast cell, MYE = myeloid, PLA = plasma).","Example BiqQuery on Single Cell Data"]},{"l":"Accessing Cell Spatial Data","p":["We also host a number of tables that contain information on cellular locations and the estimated expression of key marker protein based multiplexed imaging followed by cell segmentation. These tables are available on ISB-CGC and are derived from Imaging Level 4 t-CyCif files submitted by HTAN centers.","Example BiqQuery Cell Spatial Data"]},{"l":"BigQuery Notebooks","p":["ISB-CGC hosts a public repository of community-generated computational notebooks. The HTAN DCC has contributed a number of R and Python notebooks, illustrating how to query, perform analyses, and generate results using the publicly available HTAN BigQuery tables.","To access HTAN R and Python notebooks, visit the 'HTAN Notebooks' page of the Institute for Systems Biology Cancer Gateway in the Cloud (ISB-CGC) documentation","ISB-CGC: R and Python Computational Notebooks hosted on GitHub"]}],[{"l":"Access-Controlled Data","p":["Access-controlled HTAN data requires dbGaP access approval for study phs002371, and is currently only available via the National Cancer Institute's Cancer Data Services (CDS)."]}],[{"l":"Requesting dbGaP Access","p":["For access-controlled HTAN data, you must first complete a dbGaP request.","To get started on your dbGaP request, first navigate to the HTAN dbGap page at: phs002371, and click the Request Access button. You will be prompted to login to dbGaP. Once logged in, click the Create New Research Project button, and follow the on-screen application process.","As per dbGaP instructions, you will be prompted for relevant information, including:","A research statement and a nontechnical summary statement describing your planned use of the data.","The name of the institutional signing official who will certify the terms of use assurances on behalf of your institution.","A list of all internal investigators at your institution who will share access to the data for the proposed research.","A list of external collaborating investigators.","The name of the information technology (IT) Director.","dbGaP will notify you when your application has been approved."]}],[{"i":"ncis-cancer-data-service","l":"NCI's Cancer Data Service","p":["NOTE: dbGaP approval for HTAN study phs002371 is required in order to access HTAN lower-level genomics data, such as RNAseq FASTQ and BAM files.","The CDS Portal, within NCI's Cancer Research Data Commons (CRDC), provides an interface to filter and select data from a variety of NCI programs, including controlled-access, primary sequence data from the Human Tumor Atlas Network (HTAN).","In order to access these HTAN data within the CDS Portal, navigate to the portal in a web browser and click on the Explore CDS Data button on the landing page.","On the Data Explorer page, expand the STUDY section on the left sidebar, scroll down, and check the box next to Human Tumor Atlas (HTAN) primary sequence data.","This action will change the summary panel to reflect selecting HTAN data only.","Scroll down, or click on the Collapse View tab on the upper right just below the query summary line in order to see the tabulated view of all of the participants, samples or files in HTAN.","Click on the Add All Files button, or select the check boxes next to all Participants, Samples or Files for a subselection and then click on the Add Selected button. This action will update your cart icon in the upper right corner.","Clicking on the cart icon, will bring up a list of the selected files. Click on the Download Manifest button in the upper right to download a CSV-formated (Excel compatible) file of this file list.","Once this file manifest is downloaded, it will have to be uploaded into your Seven Bridges Cancer Genomics Cloud account, in order for you to be able to download, or otherwise compute on, these data."]}],[{"i":"sb-cgc-cancer-data-service-cds-explorer","l":"SB-CGC Cancer Data Service (CDS) Explorer","p":["NOTE: dbGaP approval for HTAN study phs002371 is required in order to access HTAN lower-level genomics data, such as RNAseq FASTQ and BAM files.","Once your dbGaP application has been approved, you can access HTAN data via the Cancer Data Service browser within the Seven Bridges Cancer Genomics Cloud. To do so, head to Seven Bridges Cancer Genomics Cloud, and log in with your ERA Commons credentials.","Once logged in, navigate to the top navigation bar, and select Data > Cancer Data Service Explorer.","Seven Bridges: Data","You can then use the faceted search interface in the left column to filter for HTAN files.","Seven Bridges: HTAN Data","Using Seven Bridges Cancer Genomics Cloud is beyond the scope of this manual. To get started, please refer to the extensive online documentation and support options."]}]]
\ No newline at end of file
+[[{"i":"htan-the-missing-manual","l":"HTAN: The Missing Manual","p":["Written by the HTAN Data Coordinating Center (DCC), with contributions from Adam Taylor, Clarisse Lau, Vésteinn Thorsson, Ino de Bruijn, David Gibbs, Ethan Cerami and Alex Lash."]},{"l":"About this Manual","p":["HTAN: The Missing Manual provides an overview of Human Tumor Atlas Network (HTAN) data and the various modes of data access. If you have any questions regarding the manual or HTAN data, please contact us at: htan@googlegroups.com.","The manual can be found at https://docs.humantumoratlas.org/."]},{"l":"Content Updates","p":["Date","Comment","2023-06-01","Second version of manual","2022-09-28","First version of manual."]}],[{"l":"Introduction to HTAN","p":["The Human Tumor Atlas Network (HTAN) is a National Cancer Institute-funded Cancer Moonshot initiative focused on studying the transitions of human cancers as they evolve from precancerous lesions to advanced disease.","The network consists of ten research centers and a Data Coordinating Center (DCC). Five of the research centers are focused on developing pre-cancer atlases, and the remaining five centers are focused on developing tumor atlases. We also have two pilot projects, one focused on pre-cancer atlases, and one focused on tumor atlases.","Each research center is responsible for gathering and processing samples, and running their own experimental assays. Assays vary by center, but most centers have a strong focus on single cell RNA-Seq and a wide range of multiplex imaging modalities.","All centers are required to submit their clinical, biospecimen and assay data to the HTAN DCC using a common HTAN Data Model. The DCC makes HTAN data available to the wider scientific community.","Complete information regarding the HTAN network is available at: https://humantumoratlas.org/.","You can explore all open access data within the HTAN Data Portal at: https://humantumoratlas.org/explore.","A complete list of HTAN Publications is available on Google Scholar.","The current status of data uploads (refreshed every 4 hours) is available on the HTAN Dashboard."]}],[{"l":"HTAN Centers","p":["Area of Focus","Atlas Type","Boston University","Breast","Children’s Hospital of Philadelphia","Colorectal","Contact Institution or Project Name","Dana-Farber Cancer Institute","Duke University","Familial Adenomatous Polyposis","For details on each center, please see: https://humantumoratlas.org/research-network.","Harvard Medical School","HTA1","HTA10","HTA11","HTA12","HTA13","HTA14","HTA2","HTA3","HTA4","HTA5","HTA6","HTA7","HTA8","HTA9","Human Tumor Atlas Pilot Project (HTAPP)","Lung","Melanoma and Clonal Hematopoiesis","Memorial Sloan Kettering Cancer Center","Multiple Cancer Types","Oregon Health Science University","Pediatric","Pilot Project","Pre-Cancer Atlas","Pre-Cancer Atlas Pilot Project (PCAPP)","Prefix","Stanford University","Technology Comparison","The HTAN Network consists of ten research centers, and two pilot projects. We also run multiple trans-network projects, referred to as TNPs. Each research center or TNP Project is identified with a unique HTAN prefix.","TNP Atlas","TNP: SARDANA","TNP: Tissue MicroArray (TMA)","Tumor Atlas","Vanderbilt University","Washington University in St. Louis"]}],[{"l":"HTAN Data Levels","p":["HTAN data is categorized into two data access levels:","Open access: includes de-identified clinical and biospecimen data, multiplex images, and processed genomic data. This data is available via the HTAN Data Portal. See Open Access Data.","Access controlled: includes unprocessed genomic data, e.g. BAM files. Similar to TCGA BAM files, this data is available via an approved dbGaP mechanism. See Controlled-Access Data.","We maintain a running update of HTAN data releases and updates at: https://data.humantumoratlas.org/data-updates."]}],[{"l":"HTAN Tool Catalog","p":["The HTAN Network consists of ten research centers and two pilot projects. The results from each project have been built using an array of computational tools, now collected into a catalog which is available on the portal. These tools are sure to be compatible with HTAN data!","For the most current listing of available tools, please see the HTAN data portal."]}],[{"l":"Data Model","p":["All HTAN Centers are required to encode their data and metadata in the common HTAN Data Model. The HTAN Data Model was created via a community Request for Comment (RFC) process, with participation from all HTAN Centers, and covers clinical data, biospecimen data, genomic data and multiplex imaging data.","As much as possible, the HTAN Data Model leverages previously defined data standards across the scientific research community, including the NCI Genomic Data Commons, the Human Cell Atlas, the Human Biomolecular Atlas Program (HuBMAP) and the Minimum Information about Tissue Imaging (MITI) reporting guidelines.","Complete information regarding the HTAN Data Model is available at: https://data.humantumoratlas.org/standards."]}],[{"l":"Identifiers","p":["All research participants, biospecimens and derived data within HTAN are associated with a unique HTAN identifier.","Boston University","Children's Hospital of Philadelphia","Dana-Farber Cancer Institute","Derivative data includes anything derived from a research participant, including biospecimens such as samples, tissue blocks, slides, aliquots, analytes, and data files that result from assaying those biospecimens. These identifiers follow the pattern:","Duke University","For example, if research participant 1 within the CHOP project has provided three samples, you would have three HTAN IDs, such as:","Harvard Medical School","HTA1","HTA10","HTA11","HTA12","HTA13","HTA14","HTA2","HTA3","HTA4","HTA5","HTA6","HTA7","HTA8","HTA9","HTAN Center ID","HTAN ID Provenance","HTAPP Pilot Project","If a single data file is generated from one of those samples, that file could have an HTAN ID such as:","Memorial Sloan Kettering Cancer Center","More detailed information about HTAN Identifiers may be found in the HTAN Identifiers SOP.","Note that the explicit linking of participants to biospecimens to assays is not encoded in the HTAN Identifier. Rather, the linking is encoded in explicit metadata elements (see Relationship Model).","Oregon Health Sciences University","PCAPP Pilot Project","Pilot Project or Contact PI Institution","Research participants are identified with the following pattern:","Stanford University","TNP SARDANA","TNP TMA","Vanderbilt University","Washington University","Where the htan_center_id is derived from the identifier prefix table below."]}],[{"l":"Clinical Metadata","p":["The HTAN clinical data model consists of three tiers. Tier 1 is in alignment with the Genomic Data Commons (GDC) guidelines for clinical data, while Tiers 2 and 3 are HTAN extensions to the GDC model.","Tier","Notes","1","Tier 1 is based entirely on the clinical data model used by the NCI Genomic Data Commons (GDC) [6]. It consists of seven categories of clinical data (see GDC Table below).","2","Disease-agnostic extensions to the GDC Clinical Data Model.","3","Disease-specific extensions to the GDC Clinical Data Model. This covers additional elements for Acute Lymphoblastic Leukemia (ALL), Brain Cancer, Breast Cancer, Lung Cancer, Melanoma, Ovarian Cancer, Pancreatic Cancer, Prostate Cancer and Sarcoma."]},{"l":"GDC Clinical Data Model","p":["A visit by a patient or study participant to a medical professional. A clinical encounter that encompasses planned and unplanned trial interventions, procedures and assessments that may be performed on a subject. A visit has a start and an end, each described with a rule. The process by which information about the health status of an individual is obtained before and after a study has officially closed; an activity that continues something that has already begun or that repeats something that has already been done.","Clinically relevant patient information not immediately resulting from genetic predispositions.","Complete details regarding all clinical data elements is available at: https://data.humantumoratlas.org/standard/clinical","Data for the characterization of the patient by means of segmenting the population (e.g., characterization by age, sex, or race).","Data from the investigation, analysis and recognition of the presence and nature of disease, condition, or injury from expressed signs and symptoms; also, the scientific determination of any kind; the concise results of such an investigation.","Demographics","Diagnosis","Exposure","Family History","Follow-up","GDC Category","GDC Description","Information pertaining to any molecular tests performed on the patient during a clinical event.","Molecular Test","Record of a patient's background regarding cancer events of blood relatives.","Record of the administration and intention of therapeutic agents provided to a patient to alter the course of a pathologic process.","The GDC Clinical Data Model consists of seven categories of clinical data.","Therapy"]}],[{"l":"Biospecimen Metadata","p":["The HTAN biospecimen data model is designed to capture essential biospecimen data elements, including:","Acquisition method, e.g. autopsy, biopsy, fine needle aspirate, etc.","Topography Code, indicating site within the body, e.g. based on ICD-O-3.","Collection information e.g. time, duration of ischemia, temperature, etc.","Processing of parent biospecimen information e.g. fresh, frozen, etc.","Biospecimen and derivative clinical metadata ie Histologic Morphology Code, e.g. based on ICD-O-3.","Coordinates for derivative biospecimen from their parent biospecimen.","Processing of derivative biospecimen for downstream analysis e.g. dissociation, sectioning, analyte isolation, etc.","Complete details are available online at: https://data.humantumoratlas.org/standard/biospecimen"]}],[{"l":"Sequencing Data","p":["1","2","3","4","Aligned BAMs","Aligned primary data","Definition","Derived biomolecular data","Example Data","FASTQs, unaligned BAMs","Gene expression matrix files, VCFs, etc.","HTAN has adopted the GENCODE 34 Gene Transfer Format ( GTF) comprehensive gene annotation file (GENCODE 34 GTF) and filtered files (GENCODE 34 GTF with genes only; GENCODE 34 GTF with genes only and retaining only chromosome X copy of pseudoautosomal region) for HTAN gene annotation. Note that HTAN also includes data generated with other gene models, as the process of implementing the standard is ongoing. Within HTAN metadata files, the reference genome used can be found in the attribute “Genomic Reference” and “Genomic Reference URL”.","HTAN supports multiple sequencing modalities including Single Cell and Single Nucleus RNA Seq (sc/snRNASeq), Single Cell ATAC Seq, Bulk RNA Seq and Bulk DNA Seq.","In alignment with The Cancer Genome Atlas and the NCI Genomic Data Commons, sequencing data are divided into four levels:","Level","Raw data","Sample level summary data.","t-SNE plot coordinates, etc.","The HTAN standard for gene annotations is GENCODE Version 34. GENCODE is used for gene definitions by many consortia, including ENCODE, NCI Genomic Data Commons, Human Cell Atlas, and PCAWG (Pan-Cancer Analysis of Whole Genomes). Ensembl gene content is essentially identical to that of GENCODE ( FAQ) and interconversion is possible."]}],[{"l":"Imaging Data","p":["The HTAN data model for imaging data is based upon the Minimum Information about Tissue Imaging (MITI) reporting guidelines. These comprise minimal metadata for highly multiplexed tissue images and were developed in consultation with methods developers, experts in imaging metadata (e.g., DICOM and OME) and multiple large-scale atlas projects; they are guided by existing standards and accommodate most multiplexed imaging technologies and both centralized and distributed data storage.","For further information on the MITI guidelines, please see the MITI website, specification on Github, and Nature Methods publication.","The HTAN data model for imaging was intended primarily for multiplexed imaging such as CODEX, CyCIF, and IMC, in addition to brightfield imaging of H&E stained tissues.","As with Sequencing data, the imaging data model is split into data levels as follows:","Level","Description","1","Raw imaging data requiring tiling, stitching, illumination correction, registration or other pre-processing.","2","Imaging data compiled into a single file format, preferably a tiled and pyramidal OME-TIFF. Accompanied by a csv file containing channel metadata.","3","Segmentation mask, Validated channel metadata, QC checked image.","4","An object-by-feature table (typically cell-by-marker) generated from the segmentation mask and image.","Before preparing imaging data for upload to DCC, please consult HTAN Imaging Data Requirements."]}],[{"l":"Spatial Transcriptomics","p":["Alignment workflows downstream of Spatial Transcriptomics RNA-seq Level 1.","Auxiliary data associated with spot/slide analysis (aligned Images, quality control files, etc) from Spatial Transcriptomics.","Description","Files contain raw RNA-seq data associated with spot/slide data.","Imaging data compiled into a single file format, preferably a tiled and pyramidal OME-TIFF.","Imaging Level 2","Level","Processed data files based on Spatial Transcriptomics RNA-seq Level 2 and Spatial Transcriptomics Auxiliary files.","Processed data files based on Spatial Transcriptomics RNA-seq Level 3.","Spatial transcriptomic datasets are typically comprised of RNA-sequencing data at varying levels, coupled with imaging data and an auxiliary set of files used in or generated by processing workflows for spatial transcriptomics:","Spatial Transcriptomics Auxiliary Files","Spatial Transcriptomics RNA-seq Level 1","Spatial Transcriptomics RNA-seq Level 2","Spatial Transcriptomics RNA-seq Level 3","Spatial Transcriptomics RNA-seq Level 4","The HTAN data model currently supports 10X Visium data, but additional platforms will be added in the near future including Nanostring GeoMX and Pick-Seq.","The HTAN data model for spatial transcriptomics data is based upon both imaging and single cell sequencing data models. These form a collection of metadata fields where transcriptomic levels (or gene or protein level measures) can be mapped to locations on a tissue slide, and were developed in consultation with the data generating centers who are both experts in imaging metadata (e.g. DICOM and OME) and multiple large-scale atlas projects."]}],[{"l":"Relationship Model","p":["Each atlas in HTAN contains data provided by multiple research participants, who have donated biospecimens (see Figure below). The metadata allows one to trace back any data file to the donated biospecimen. Level 1 raw data files are directly linked to the corresponding biospecimen, whereas processed level 2-4 data files are linked to lower level parent data files. Note also that biospecimens can be connected recursively.","HTAN ID Provenance"]},{"l":"HTAN ID Provenance Table","p":["The HTAN DCC has constructed an ID Provenance BigQuery table, which contains upstream biospecimen and participant information for each HTAN data file. The motivation for constructing the table arose from the need for a straightforward method of showcasing how HTAN data files are linked to biospecimens and patients.","Although this information is available in HTAN, connections among assay file levels and parent relationships (both biospecimen and file) were previously only accessible by tracing through parent identifiers. Having all ID information in one place can significantly speed up analyses, exploration, and data sharing.","The Provenance BigQuery table is accessible via ISB-CGC. See the Google BigQuery section for more details."]},{"l":"Biospecimen Attribute Definitions","p":["Given the complexity of biospecimen relationships, we've adopted the following nomenclature to describe biospecimen lineages:","Originating Biospecimen: the biopsied or resected biospecimen from the patient from which the assay data were derived","Assayed Biospecimen: the biospecimen directly assayed using the experimental platform","Biospecimen Path: path of biospecimens from Originating to Assayed; comma-separated"]},{"l":"Provenance Table Construction","p":["As illustrated in the figure above, biospecimens can be subsampled multiple times. However, HTAN metadata tables provide only the immediate parent biospecimen. To assemble the full biospecimen path, we perform a series of joins on the biospecimen table, walking up the parent biospecimen ancestry chain until no further parents are found.","Similarly, we can have up to four data file ‘levels’. Each data file is linked using its provided parent HTAN data file ID(s).","We then join biospecimen information with file-level annotations to form the final ID provenance table.","Provenance Table Columns"]},{"l":"Table Contents","p":["In addition to upstream biospecimen and participant IDs, the provenance table also includes a number of informational columns, such as entityId(Synapse ID of the source file), HTAN_Center(text version of center code), and Data_Release and CDS_Release which indicate which HTAN Portal release and CDS release the file was included in, respectively.","Provenance Table Columns"]}],[{"l":"Open Access Data","p":["Open access HTAN data is available via:","The HTAN Data Portal","NCI Image Data Commons (IDC)","Google BigQuery"]}],[{"l":"Using the HTAN Data Portal","p":["The HTAN Data Portal provides access to all open access HTAN data. To get started, go to: https://data.humantumoratlas.org/explore.","To orient you to the HTAN Data Portal, consider the example of accessing precancerous polyp data from Vanderbilt University, as described in their recent Cell publication.","By default, HTAN data is organized by research center:","HTAN Portal: Home Page","If you scroll down on the page, you will see Vanderbilt University:","HTAN Portal: Vanderbilt Atlas","As of this writing, you can see that the Vanderbilt Colon Atlas project has 90 cases and 193 biospecimens."]},{"l":"Downloading Metadata","p":["Once you have identified the project of interest, you can click the download metadata button:","HTAN Portal: Download Metadata","You will then be prompted with a dialog box of all metadata associated with the specified project. For example:","HTAN Portal: Metadata Table","Behind the scenes, HTAN leverages the Synapse Platform created and maintained by Sage Bionetworks. Each piece of HTAN data is automatically assigned a unique Synapse identifier, such as syn25010909. In the screenshot above, you can see that the Vanderbilt project has multiple metadata files, each associated with a unique Synapse identifier.","If you click on any of the Synapse links above, you can immediately download a comma separated value (CSV) file associated with the metadata category. There is no need to create a Synapse account or log into Synapse. For example, here we have download the Vanderbilt biospecimen file and loaded it into Excel:","HTAN Tabular Data within Excel","Once you have downloaded metadata files, you can parse them in your favorite programming language, such as R or Python. To understand the individual columns within each metadata file, please refer to the HTAN Data Model."]},{"l":"Exploring Available Data","p":["At this point, the Files tab is likely to contain hundreds of files, and may be difficult to navigate. You can further refine the files table by clicking on the Assay Type or File Type filters. This will trigger pop-up windows that describe the assay and file type categories available within the Vanderbilt project. For example, if you click Assay Type you will see:","Clicking Level 4 here will now filter the File table to only include Level 4 sequencing data that consists of Single Cell RNA Seq h5ad formatted files:","Clicking View Details on any of these files will pop open a metadata table. For example:","Data that is available within the Vanderbilt project is set to bold. You can therefore see that the Vanderbilt project has Bulk DNA, H&E Images, Multiplex ImmunoFluorescence images and Single Cell RNA Seq Data.","HTAN Portal: Files Tab","HTAN Portal: Filter by Assay Type","HTAN Portal: Filter by File Type","HTAN Portal: Filter by HTAN Center","HTAN Portal: Filter by Vanderbilt University","HTAN Portal: Filters","HTAN Portal: Metadata Details","HTAN Portal: Multiple Filters Enabled","HTAN Portal: Removing Filters","If you click scRNA-seq, the file table will automatically update. You can then select the File Type filter to drill-down even further:","If you click the Cases or Biospecimens tabs, you can browse available metadata. Clicking the Files tab will take you to an interactive table listing all files available for download.","Note that you can remove any existing filters by clicking on any of the “chips” in the page header. For example, if you want to remove the Level 4 filter, just click the Level 4 chip:","The HTAN Data Portal provides a unified interface for filtering and exploring HTAN data sets. Each filter is available at the top of the page:","To get started, you can click the Atlas pull-down menu, and select the Vanderbilt HTAN center:","Your selection will now be reflected in the user interface:"]},{"l":"Downloading Open Access Data","p":["Once you have specified your filter criteria, the Files tab will display all matching files. At this point, you may see two types of files:","Open Access Files; and","Access Controlled Files","To download open access files, you will need to first create a free account on the Synapse data platform. To register an account, goto https://www.synapse.org/, and click the Register button.","Once registered and logged into Synapse, you can then click through from the HTAN Data Portal to the corresponding page on Synapse. For example, this CSV file corresponds to single cell data generated by the Vanderbilt project:","Synapse Page","You can click the Download Options button to download the file. To retrieve the same file via R, Python or via the command line, click the Download Options button and select Programmatic Options.","To download access-controlled files, please refer to Access Controlled Data Access."]}],[{"l":"Visualizing Single Cell Data via CellxGene","p":["Through our collaboration with the Chan Zuckerberg Initiative (CZI), we make HTAN single cell RNA seq data available via CellxGene. CellxGene enables you to visualize and explore large-scale single cell data sets. For complete details on CellxGene, please refer to the online documentation.","HTAN data sets with CellxGene visualization are denoted on the main home page in the rightmost column. Clicking the CellxGene logo will take you directly to CellxGene.","HTAN Portal: Links to CellxGene","Example HTAN data from MSKCC, as visualized in CellxGene is shown below:","CellxGene: Example MSKCC HTAN Data"]}],[{"l":"Visualizing Multiplex Imaging Data via Minerva","p":["Through our collaboration with the Laboratory of Systems Pharmacology (LSP) at Harvard Medical School, many HTAN images can be visualized via Minerva, a web-based tool that enables interactive viewing and fast sharing of large image data.","Where a Minerva story is available on the HTAN Data Portal, a link will be visible when hovering over the thumbnail image in the View Column.","HTAN Portal: Links to Minerva","For most images, a basic Minerva story has been prepared using Auto Minerva, a tool to prepare default Minerva stories with optimized channel thresholds. An example prepared with Auto Minerva is shown below.","HTAN Portal: Auto Minerva Example","The image can be zoomed and panned with the mouse. Channel groups can be selected using the bar on the right. Selected metadata is shown in the left panel and can be collapsed. Point, box and polygon annotations can be generated and shared as a URL.","For some images, centers have provided custom Minerva stories leveraging features such as waypoints, annotations, data overlays and narrative text. An example custom Minerva story is shown below.","HTAN Portal: Curated Minerva Example"]}],[{"i":"accessing-images-via-image-data-commons-idc","l":"Accessing Images via Image Data Commons (IDC)","p":["HTAN Imaging Level 2 data is now available through the NCI Imaging Data Commons (IDC).","Imaging Data Commons hosts versions of the HTAN Imaging Level 2 data converted to DICOM-TIFF dual personality files. For further information and an example open source implementation, see online reference.","For further information on using the IDC, you can explore their online documentation."]},{"l":"Filtering for HTAN Images in the IDC portal","p":["From the homepage of the Imaging Data Commons, click the purple Explore link to explore image data.","HTAN data can be selected by selecting in the Collection group in the left-hand bar (you may need to click \"show more\" to reveal all collections).","IDC: Filter for HTAN Images","Pie charts show the breakdown of selected metadata attributes.","By checking collections (e.g. HTAN WUSTL), cases (participants), studies (biospecimens), and series (images), the study instances of selected images may be found."]},{"l":"Download Images from IDC","p":["HTAN data is shared under a CC-BY 4.0 license, and is available to download as DICOM images without egress costs from IDC thanks to support from the Google public datasets program. For complete details, see IDC Documentation on Downloading Data. Basic download instructions are also included on the HTAN portal for files released by the IDC, by selecting the filename.","HTAN Data Portal: IDC Download Details","Note that individual DICOM files representing each channel and pyramid level may need to be sorted or converted back to TIFF files for reuse in image analysis tools."]},{"l":"Viewing Images via the IDC SLIM Viewer","p":["Clicking they eye icon in the view column on the IDC portal, or the IDC link when hovering over the thumbnail in the HTAN portal, takes the user to IDC’s interactive SLIM viewer. This interactive viewer provides image exploration and pre-rendered scenes.","IDC: Interactive SLIM Viewer"]}],[{"i":"accessing-images-via-sb-cgc-cancer-data-service-cds","l":"Accessing Images via SB-CGC Cancer Data Service (CDS)","p":["HTAN Imaging Level 2 data is now available through the NCI SB-CGC Cancer Data Service (CDS).","NOTE: dbGaP approval for HTAN study phs002371 is required in order to access HTAN lower-level genomics data, such as RNAseq FASTQ and BAM files.","Data access via Seven Bridges Cancer Genomics Cloud (SB-CGC) requires a CGC account [register here]. For further information on using SB-CGC resources including programmatic access options, you can explore their online documentation."]},{"l":"Filtering for HTAN Images in the CDS File Repository","p":["From the SB-CGC dashboard, click Cancer Data Service Explorer under the Data tab.","CDS: Accessing the CDS file explorer","Select Explore files","From the sidebar, filter by Dataset: HTAN and Experimental Strategy: ImagingLevel2","CDS: Filter by HTAN study CDS: Filter for imaging data","This provides a listing of all HTAN Imaging Level 2 data that is currently available through CDS.","CDS: HTAN Imaging Data on CDS"]},{"l":"Download Images from CDS","p":["Additional filters are available for further selection including Data format, Site, etc., as well as text search fields to search files by Filename, case ID (HTAN Participant ID), and sample ID (HTAN Biospecimen ID).","Once you have filtered to your files of interest, click Copy to project to add the selected files to the SB-CGC project of your choosing (create a new project if you do not have one set up).","CDS: Add selected files to project","You will be automatically re-directed to the Files tab of your SB-CGC project. From here, check the boxes of the files you would like to save. Clicking Download will download the selected images to your local machine.","CDS: Download selected imaging files"]}],[{"l":"Google BigQuery","p":["Google BigQuery is a massively-parallel analytics engine ideal for working with tabular data. Through our collaboration with the Institute for Systems Biology Cancer Gateway in the Cloud (ISB-CGC), open-access HTAN BigQuery tables are now available, and updated with each major HTAN release.","HTAN BigQuery tables can be accessed through the ISB-CGC Table Search UI and via the HTAN Data Portal.","For complete documentation regarding ISB-CGC BigQuery functionality, check out their online documentation.","You must have a Google account to access Google Big Query.","Google Cloud Platform’s free tier allows users to access many common Google Cloud resources, including BigQuery free of charge and query up to 1 TB of data per month for free."]},{"l":"Accessing Metadata tables","p":["HTAN metadata is organized by data type and level (see HTAN Data Model), with each BigQuery table containing data from all HTAN Centers combined.","Metadata tables can be accessed from the Atlases tab of the HTAN Data Portal. Click the icon under the Metadata column and scroll down to the Google BigQuery link at the bottom of the popup window.","HTAN Portal: Accessing Metadata","HTAN Portal: Linking to BiqQuery Tables","This link will take you to the ISB-CGC Table Search UI filtered to HTAN tables. Browse the table listing to find your table of interest, and click the magnifying glass icon under Open to launch the table in the BigQuery console.","ISB-CGC: Table Search ISB-CGC: Table Browser","Alternatively, you can start at the ISB-CGC Table Search UI and select Launch under BigQuery Table Search.","ISB-CGC: Launch BigQuery","Then filter for HTAN tables by selecting HTAN from the Program dropdown.","ISB-CGC: Filter for HTAN Table"]},{"l":"Example Query","p":["As an example, this simple query tabulates the overall distribution of gender in HTAN, as reported in the HTAN Clinical Demographics BigQuery table isb-cgc-bq.HTAN_versioned.clinical_tier1_demographics_r2. For complete details on running queries and the Biq Query syntax, refer to the Google BiqQuery Documentation.","ISB-CGC: Sample Query"]},{"l":"Accessing Single Cell Tables","p":["We currently host multiple single cell BigQuery tables via ISB-CGC. These tables are derived from level 4 H5AD AnnData files submitted by HTAN centers.","When a BigQuery table is available for a given file, a link will be visible in the View Column of the HTAN Data Portal.","HTAN Portal: BigQuery Links","This link will take you to the ISB-CGC Table Search UI listing for the selected single cell file. Click the magnifying glass icon under Open to launch the table in the BigQuery console.","BigQuery: Details BigQuery: Details"]},{"i":"example-query-1","l":"Example Query","p":["In this example, we query the single cell RNA seq-derived gene expression data for non-epithelial cells in colon polyps published by the Vanderbilt HTAN center. We filter cells to those expressing the leukocyte marker CD45, coded by gene PTPRC, and enumerate cells by their identified phenotype (B = B cell, T = T cell, END = endothelial, FIB = fibroblast, MAS = mast cell, MYE = myeloid, PLA = plasma).","Example BiqQuery on Single Cell Data"]},{"l":"Accessing Cell Spatial Data","p":["We also host a number of tables that contain information on cellular locations and the estimated expression of key marker protein based multiplexed imaging followed by cell segmentation. These tables are available on ISB-CGC and are derived from Imaging Level 4 t-CyCif files submitted by HTAN centers.","Example BiqQuery Cell Spatial Data"]},{"l":"BigQuery Notebooks","p":["ISB-CGC hosts a public repository of community-generated computational notebooks. The HTAN DCC has contributed a number of R and Python notebooks, illustrating how to query, perform analyses, and generate results using the publicly available HTAN BigQuery tables.","To access HTAN R and Python notebooks, visit the 'HTAN Notebooks' page of the Institute for Systems Biology Cancer Gateway in the Cloud (ISB-CGC) documentation","ISB-CGC: R and Python Computational Notebooks hosted on GitHub"]}],[{"l":"Access-Controlled Data","p":["Access-controlled HTAN data requires dbGaP access approval for study phs002371, and is currently only available via the National Cancer Institute's Cancer Data Services (CDS)."]}],[{"l":"Requesting dbGaP Access","p":["For access-controlled HTAN data, you must first complete a dbGaP request.","To get started on your dbGaP request, first navigate to the HTAN dbGap page at: phs002371, and click the Request Access button. You will be prompted to login to dbGaP. Once logged in, click the Create New Research Project button, and follow the on-screen application process.","As per dbGaP instructions, you will be prompted for relevant information, including:","A research statement and a nontechnical summary statement describing your planned use of the data.","The name of the institutional signing official who will certify the terms of use assurances on behalf of your institution.","A list of all internal investigators at your institution who will share access to the data for the proposed research.","A list of external collaborating investigators.","The name of the information technology (IT) Director.","dbGaP will notify you when your application has been approved."]}],[{"i":"ncis-cancer-data-service","l":"NCI's Cancer Data Service","p":["NOTE: dbGaP approval for HTAN study phs002371 is required in order to access HTAN lower-level genomics data, such as RNAseq FASTQ and BAM files.","The CDS Portal, within NCI's Cancer Research Data Commons (CRDC), provides an interface to filter and select data from a variety of NCI programs, including controlled-access, primary sequence data from the Human Tumor Atlas Network (HTAN).","In order to access these HTAN data within the CDS Portal, navigate to the portal in a web browser and click on the Explore CDS Data button on the landing page.","On the Data Explorer page, expand the STUDY section on the left sidebar, scroll down, and check the box next to Human Tumor Atlas (HTAN) primary sequence data.","This action will change the summary panel to reflect selecting HTAN data only.","Scroll down, or click on the Collapse View tab on the upper right just below the query summary line in order to see the tabulated view of all of the participants, samples or files in HTAN.","Click on the Add All Files button, or select the check boxes next to all Participants, Samples or Files for a subselection and then click on the Add Selected button. This action will update your cart icon in the upper right corner.","Clicking on the cart icon, will bring up a list of the selected files. Click on the Download Manifest button in the upper right to download a CSV-formated (Excel compatible) file of this file list.","Once this file manifest is downloaded, it will have to be uploaded into your Seven Bridges Cancer Genomics Cloud account, in order for you to be able to download, or otherwise compute on, these data."]}],[{"i":"sb-cgc-cancer-data-service-cds-explorer","l":"SB-CGC Cancer Data Service (CDS) Explorer","p":["NOTE: dbGaP approval for HTAN study phs002371 is required in order to access HTAN lower-level genomics data, such as RNAseq FASTQ and BAM files.","Once your dbGaP application has been approved, you can access HTAN data via the Cancer Data Service browser within the Seven Bridges Cancer Genomics Cloud. To do so, head to Seven Bridges Cancer Genomics Cloud, and log in with your ERA Commons credentials.","Once logged in, navigate to the top navigation bar, and select Data > Cancer Data Service Explorer.","Seven Bridges: Data","You can then use the faceted search interface in the left column to filter for HTAN files.","Seven Bridges: HTAN Data","Using Seven Bridges Cancer Genomics Cloud is beyond the scope of this manual. To get started, please refer to the extensive online documentation and support options."]}]]
\ No newline at end of file
diff --git a/sitemap.xml.gz b/sitemap.xml.gz
index e8882418..52bef5e6 100644
Binary files a/sitemap.xml.gz and b/sitemap.xml.gz differ