From 2c73e8ebf836769e9ea68c84b39156a76832333a Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Mon, 3 Mar 2025 10:00:41 -0500
Subject: [PATCH 01/11] Add files via upload

---
 R/target_cn.R            | 21 +++++++++++++++++++++
 R/target_methylation.R   | 21 +++++++++++++++++++++
 R/target_methylation_1.R | 17 +++++++++++++++++
 R/tcga_proteome.R        | 29 +++++++++++++++++++++++++++++
 R/tcga_slides.R          | 25 +++++++++++++++++++++++++
 R/tcga_slides_1.R        | 27 +++++++++++++++++++++++++++
 6 files changed, 140 insertions(+)
 create mode 100644 R/target_cn.R
 create mode 100644 R/target_methylation.R
 create mode 100644 R/target_methylation_1.R
 create mode 100644 R/tcga_proteome.R
 create mode 100644 R/tcga_slides.R
 create mode 100644 R/tcga_slides_1.R

diff --git a/R/target_cn.R b/R/target_cn.R
new file mode 100644
index 0000000..547a681
--- /dev/null
+++ b/R/target_cn.R
@@ -0,0 +1,21 @@
+library(GenomicDataCommons)
+library(dplyr)
+library(tibble)
+#Clear Cell Sarcoma of the Kidney. Disease Type. Complex Mixed and Stromal Neoplasms. Primary Site. Kidney. Program. TARGET
+
+
+cn_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |>  GenomicDataCommons::filter( analysis.workflow_type == 'ASCAT2')  |> manifest()
+n<-which(cn_manifest_CCSK$access=='open')
+
+#save dat to file
+write.csv(cn_manifest_CCSK[n,],file='out.txt',quote=FALSE,row.names=FALSE)
+##########----------#######################
+#select files
+for( i in seq(1,length(n)))
+{
+#
+id<-0;
+        id<-as.character(cn_manifest_CCSK[n[i],1])
+###### 
+gdcdata(id)
+}
diff --git a/R/target_methylation.R b/R/target_methylation.R
new file mode 100644
index 0000000..1f54692
--- /dev/null
+++ b/R/target_methylation.R
@@ -0,0 +1,21 @@
+library(GenomicDataCommons)
+library(dplyr)
+library(tibble)
+#Clear Cell Sarcoma of the Kidney. Disease Type. Complex Mixed and Stromal Neoplasms. Primary Site. Kidney. Program. TARGET
+
+#get familiar with aggregations
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TARGET-CCSK') |> facet(c("data_type","data_format","analysis.workflow_type","file_id","file_name")) |> aggregations()
+
+
+
+q_1 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TARGET-CCSK') |> facet(c("data_type","data_format","analysis.workflow_type")) |> aggregations()
+
+idat_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |> GenomicDataCommons::filter( data_type == 'Methylation Beta Value' ) |> GenomicDataCommons::filter( analysis.workflow_type == 'SeSAMe Methylation Beta Estimation')  |> manifest()
+n<-which(idat_manifest_CCSK$access=='open')
+
+#save data to file
+write.csv(idat_manifest_CCSK[n,],file='manifest.txt',quote=FALSE,row.names=FALSE)
+
+
+###### test  single file 
+gdcdata(idat_manifest_CCSK[n[1],1]))
diff --git a/R/target_methylation_1.R b/R/target_methylation_1.R
new file mode 100644
index 0000000..2c091c4
--- /dev/null
+++ b/R/target_methylation_1.R
@@ -0,0 +1,17 @@
+library(GenomicDataCommons)
+library(dplyr)
+library(tibble)
+
+
+idat_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |> GenomicDataCommons::filter( data_type == 'Methylation Beta Value' ) |> GenomicDataCommons::filter( analysis.workflow_type == 'SeSAMe Methylation Beta Estimation')  |> manifest()
+n<-which(idat_manifest_CCSK$access=='open')
+
+##########----------#######################
+for( i in seq(1,length(n)))
+{
+#use cast
+id<-0;
+	id<-as.character(idat_manifest_CCSK[n[i],1])
+######only test with single file 
+gdcdata(id)
+}
diff --git a/R/tcga_proteome.R b/R/tcga_proteome.R
new file mode 100644
index 0000000..d4dd688
--- /dev/null
+++ b/R/tcga_proteome.R
@@ -0,0 +1,29 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+p_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_type == 'Protein Expression Quantification' & data_format == 'tsv') |> manifest()
+#locate open data
+open_access<-which(p_2$access=="open")
+#381 files
+#download select files 
+#for(i in length(open_access))
+#for(i in seq(3,5))
+#for(i in seq(20,24))
+
+for(i in seq(200,202))
+{
+uid<-0;uid<-as.character(p_2[open_access[i],1])
+gdcdata(uid)
+}
+
+#sanity check , use the filter function 
+
+
+p_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_type == 'Protein Expression Quantification' & data_format == 'tsv') |> filter(access == 'open') |> manifest()
+
+for(i in seq(20,24))
+{
+uid<-0;uid<-as.character(p_3[i,1])
+gdcdata(uid)
+}
diff --git a/R/tcga_slides.R b/R/tcga_slides.R
new file mode 100644
index 0000000..f260f3d
--- /dev/null
+++ b/R/tcga_slides.R
@@ -0,0 +1,25 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+#specify project name
+#q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-KIRC' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-BRCA' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
+#locate open data
+open_access<-which(q_2$access=="open")
+
+#select files
+#for(i in length(open_access))
+#for(i in seq(3,5))
+#for(i in seq(20,24))
+for(i in seq(200,202))
+{
+uid<-0;uid<-as.character(q_2[open_access[i],1])
+gdcdata(uid)
+}
+
+
+######alternatively, use filter 
+#both approaches should list same files
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-BRCA' & data_type == 'Slide Image' & data_format == 'svs') |> filter(access == 'open') |>  manifest()
+
diff --git a/R/tcga_slides_1.R b/R/tcga_slides_1.R
new file mode 100644
index 0000000..057547b
--- /dev/null
+++ b/R/tcga_slides_1.R
@@ -0,0 +1,27 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-COAD' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
+#locate open data
+open_access<-which(q_2$access=="open")
+
+#for(i in length(open_access))
+#for(i in seq(3,5))
+#for(i in seq(20,24))
+for(i in seq(200,202))
+{
+uid<-0;uid<-as.character(q_2[open_access[i],1])
+gdcdata(uid)
+}
+
+
+#or sanity check
+
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-COAD' & data_type == 'Slide Image' & data_format == 'svs') |> filter(access == 'open') |> manifest()
+
+for(i in seq(2,4))
+{
+uid<-0;uid<-as.character(q_3[i,1])
+gdcdata(uid)
+}

From 7e08ba780bc2fd29e5788f7e4edae57236478add Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Mon, 3 Mar 2025 10:11:50 -0500
Subject: [PATCH 02/11] Add files via upload

---
 vignettes/overviewGenomicDataCommons.Rmd | 811 +++++++++++++++++++++++
 vignettes/questions-and-answers.Rmd      |   6 +-
 vignettes/somatic_mutations.Rmd          |  10 +-
 3 files changed, 819 insertions(+), 8 deletions(-)
 create mode 100644 vignettes/overviewGenomicDataCommons.Rmd

diff --git a/vignettes/overviewGenomicDataCommons.Rmd b/vignettes/overviewGenomicDataCommons.Rmd
new file mode 100644
index 0000000..4269cda
--- /dev/null
+++ b/vignettes/overviewGenomicDataCommons.Rmd
@@ -0,0 +1,811 @@
+---
+title: "The GenomicDataCommons Package"
+author: "Sean Davis & Martin Morgan"
+date: "`r format(Sys.Date(), '%A, %B %d, %Y')`"
+always_allow_html: yes
+output:
+  BiocStyle::html_document:
+    df_print: paged
+    toc_float: true
+abstract: >
+  The National Cancer Institute (NCI) has established
+  the [Genomic Data Commons](https://gdc.nci.nih.gov/) (GDC). The GDC
+  provides the cancer research community with an open and unified
+  repository for sharing and accessing data across numerous cancer
+  studies and projects via a high-performance data transfer and query
+  infrastructure.  The *GenomicDataCommons* Bioconductor package
+  provides basic infrastructure for querying, accessing, and mining
+  genomic datasets available from the GDC. We expect that the
+  Bioconductor developer and the larger bioinformatics communities will
+  build on the *GenomicDataCommons* package to add higher-level
+  functionality and expose cancer genomics data to the plethora of
+  state-of-the-art bioinformatics methods available in Bioconductor.
+
+vignette: >
+  %\VignetteIndexEntry{Introduction to Accessing the NCI Genomic Data Commons}
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}
+---
+
+```{r init, results='hide', echo=FALSE, warning=FALSE, message=FALSE}
+library(knitr)
+opts_chunk$set(warning=FALSE, message=FALSE)
+BiocStyle::markdown()
+```
+
+
+# What is the GDC?
+
+From the [Genomic Data Commons (GDC) website](https://gdc.cancer.gov/about-gdc):
+
+> The National Cancer Institute's (NCI's) Genomic Data Commons (GDC) is
+a data sharing platform that promotes precision medicine in
+oncology. It is not just a database or a tool; it is an expandable
+knowledge network supporting the import and standardization of genomic
+and clinical data from cancer research programs.
+> The GDC contains NCI-generated data from some of the largest and most
+comprehensive cancer genomic datasets, including The Cancer Genome
+Atlas (TCGA) and Therapeutically Applicable Research to Generate
+Effective Therapies (TARGET). For the first time, these datasets have
+been harmonized using a common set of bioinformatics pipelines, so
+that the data can be directly compared.
+> As a growing knowledge system for cancer, the GDC also enables
+researchers to submit data, and harmonizes these data for import into
+the GDC. As more researchers add clinical and genomic data to the GDC,
+it will become an even more powerful tool for making discoveries about
+the molecular basis of cancer that may lead to better care for
+patients.
+
+The
+[data model for the GDC is complex](https://gdc.cancer.gov/developers/gdc-data-model/gdc-data-model-components),
+but it worth a quick overview and a graphical representation is included here. 
+
+![The data model is encoded as a
+so-called property graph. Nodes represent entities such as Projects,
+Cases, Diagnoses, Files (various kinds), and Annotations. The
+relationships between these entities are maintained as edges.  Both
+nodes and edges may have Properties that supply instance details. ](all_nodes_040318.png)
+
+ The
+GDC API exposes these nodes and edges in a somewhat simplified set
+of
+[RESTful](https://en.wikipedia.org/wiki/Representational_state_transfer) endpoints.
+
+# Quickstart
+
+This quickstart section is just meant to show basic
+functionality. More details of functionality are included further on
+in this vignette and in function-specific help.
+
+This software is available at Bioconductor.org and can be downloaded via
+`BiocManager::install`.
+
+To report bugs or problems, either
+[submit a new issue](https://github.com/Bioconductor/GenomicDataCommons/issues)
+or submit a `bug.report(package='GenomicDataCommons')` from within R (which
+will redirect you to the new issue on GitHub).
+
+## Installation
+
+Installation can be achieved via Bioconductor's `BiocManager` package.
+
+```{r install_bioc, eval=FALSE}
+if (!require("BiocManager"))
+    install.packages("BiocManager")
+BiocManager::install('GenomicDataCommons')
+```
+
+```{r libraries, message=FALSE}
+library(GenomicDataCommons)
+```
+
+## Check connectivity and status
+
+The `r Biocpkg("GenomicDataCommons")` package relies on having network
+connectivity. In addition, the NCI GDC API must also be operational
+and not under maintenance. Checking `status` can be used to check this
+connectivity and functionality.
+
+```{r statusQS}
+GenomicDataCommons::status()
+```
+
+And to check the status in code:
+
+```{r statusCheck}
+stopifnot(GenomicDataCommons::status()$status=="OK")
+```
+
+
+## Find data
+Please use a fresh R session to minimise package conflicts arising from identical function names.
+For example the functions filter(), results() are available with R packages dplyr, GenomicDataCommons . Instead consider using the R package conflicted.
+Example usage
+conflicts_prefer(dplyr::filter())
+conflicts_prefer(GenomicDataCommons::filter)
+conflicts_prefer(stats :: filter)
+
+The following code builds a `manifest` that can be used to guide the
+download of raw data. Here, filtering finds gene expression files
+quantified as raw counts using `STAR` from ovarian cancer patients.
+
+```{r manifest}
+ge_manifest <- files() |>
+    filter( cases.project.project_id == 'TCGA-OV') |> 
+    filter( type == 'gene_expression' ) |>
+    filter( analysis.workflow_type == 'STAR - Counts')  |>
+    manifest()
+head(ge_manifest)
+```
+
+## Download data
+
+After  the `r nrow(ge_manifest)` gene expression files
+specified in the query above. Using multiple processes to do the download very
+significantly speeds up the transfer in many cases.  On a standard 1Gb
+connection, the following completes in about 30 seconds. The first time the 
+data are downloaded, R will ask to create a cache directory (see `?gdc_cache`
+for details of setting and interacting with the cache). Resulting
+downloaded files will be stored in the cache directory. Future access to 
+the same files will be directly from the cache, alleviating multiple downloads.
+
+```{r downloadQS, eval=FALSE}
+fnames <- lapply(ge_manifest$id[1:20], gdcdata)
+```
+
+If the download had included controlled-access data, the download above would
+have needed to include a `token`.  Details are available in
+[the authentication section below](#authentication).
+
+## Metadata queries
+
+### Clinical data
+
+Accessing clinical data is a very common task. Given a set of `case_ids`,
+the `gdc_clinical()` function will return a list of four `tibble`s. 
+
+- demographic
+- diagnoses
+- exposures
+- main
+
+```{r gdc_clinical}
+case_ids <- cases() |> results(size=10) |> ids()
+clindat <- gdc_clinical(case_ids)
+names(clindat)
+```
+
+```{r clinData}
+head(clindat[["main"]])
+head(clindat[["diagnoses"]])
+```
+
+### General metadata queries
+
+The `r Biocpkg("GenomicDataCommons")` package can access the significant 
+clinical, demographic, biospecimen, and annotation information 
+contained in the NCI GDC. The `gdc_clinical()` function will often
+be all that is needed, but the API and `r Biocpkg("GenomicDataCommons")` package
+make much flexibility if fine-tuning is required. 
+
+```{r metadataQS}
+expands <- c("diagnoses","annotations",
+             "demographic","exposures")
+clinResults <- cases() |>
+    GenomicDataCommons::select(NULL) |>
+    GenomicDataCommons::expand(expands) |>
+    results(size=50)
+str(clinResults[[1]],list.len=6)
+# or listviewer::jsonedit(clinResults)
+```
+
+# Basic design
+
+This package design is meant to have some similarities to the "hadleyverse"
+approach of dplyr. Roughly, the functionality for finding and accessing files
+and metadata can be divided into:
+
+1. Simple query constructors based on GDC API endpoints.
+2. A set of verbs that when applied, adjust filtering, field selection, and
+faceting (fields for aggregation) and result in a new query object (an
+endomorphism)
+3. A set of verbs that take a query and return results from the GDC
+
+In addition, there are exhiliary functions for asking the GDC API for
+information about available and default fields, slicing BAM files, and
+downloading actual data files.  Here is an overview of functionality[^1].
+
+
+- Creating a query
+    - `projects()`
+    - `cases()`
+    - `files()`
+    - `annotations()`
+- Manipulating a query
+    - `filter()`
+    - `facet()`
+    - `select()`
+- Introspection on the GDC API fields
+    - `mapping()`
+    - `available_fields()`
+    - `default_fields()`
+    - `grep_fields()`
+    - `available_values()`
+    - `available_expand()`
+- Executing an API call to retrieve query results
+    - `results()`
+    - `count()`
+    - `response()`
+- Raw data file downloads
+    - `gdcdata()`
+    - `transfer()`
+    - `gdc_client()`
+- Summarizing and aggregating field values (faceting)
+    - `aggregations()`
+- Authentication
+    - `gdc_token()`
+- BAM file slicing
+    - `slicing()`
+
+[^1]: See individual function and methods documentation for specific details.
+
+
+# Usage
+
+There are two main classes of operations when working with the NCI GDC.
+
+1. [Querying metadata and finding data files](#querying-metadata) (e.g., finding
+all gene expression quantifications data files for all colon cancer patients).
+2. [Transferring raw or processed data](#datafile-access-and-download) from the
+GDC to another computer (e.g., downloading raw or processed data)
+
+Both classes of operation are reviewed in detail in the following sections.
+
+## Querying metadata
+
+Vast amounts of metadata about cases (patients, basically), files, projects, and
+so-called annotations are available via the NCI GDC API. Typically, one will
+want to query metadata to either focus in on a set of files for download or
+transfer *or* to perform so-called aggregations (pivot-tables, facets, similar
+to the R `table()` functionality).
+
+Querying metadata starts with [creating a "blank" query](#creating-a-query). One
+will often then want to [`filter`](#filtering) the query to limit results prior
+to [retrieving results](#retrieving-results). The GenomicDataCommons package has
+[helper functions for listing fields](#fields-and-values) that are available for
+filtering.
+
+In addition to fetching results, the GDC API allows
+[faceting, or aggregating,](#facets-and-aggregation), useful for compiling
+reports, generating dashboards, or building user interfaces to GDC data (see GDC
+web query interface for a non-R-based example).
+
+### Creating a query
+
+A query of the GDC starts its life in R. Queries follow the four metadata
+endpoints available at the GDC.  In particular, there are four convenience
+functions that each create `GDCQuery` objects (actually, specific subclasses of
+`GDCQuery`):
+
+- `projects()`
+- `cases()`
+- `files()`
+- `annotations()`
+
+```{r projectquery}
+pquery <- projects()
+```
+
+The `pquery` object is now an object of (S3) class, `GDCQuery` (and
+`gdc_projects` and `list`). The object contains the following elements:
+
+- fields: This is a character vector of the fields that will be returned when we
+[retrieve data](#retrieving-results). If no fields are specified to, for
+example, the `projects()` function, the default fields from the GDC are used
+(see `default_fields()`)
+- filters: This will contain results after calling the
+[`filter()` method](#filtering) and will be used to filter results on
+[retrieval](#retrieving-results).
+- facets: A character vector of field names that will be used for
+[aggregating data](#facets-and-aggregation) in a call to `aggregations()`.
+- token: A character(1) token from the GDC. See
+[the authentication section](#authentication) for details, but note that, in
+general, the token is not necessary for metadata query and retrieval, only for
+actual data download.
+
+Looking at the actual object (get used to using `str()`!), note that the query
+contains no results.
+
+```{r pquery}
+str(pquery)
+```
+### Retrieving results
+
+[[ GDC pagination documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#size-and-from)
+
+[[ GDC sorting documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#sort)
+
+With a query object available, the next step is to retrieve results from the
+GDC. The GenomicDataCommons package.  The most basic type of results we can get
+is a simple `count()` of records available that satisfy the filter criteria.
+Note that we have not set any filters, so a `count()` here will represent all
+the project records publicly available at the GDC in the "default" archive"
+
+```{r pquerycount}
+pcount <- count(pquery)
+# or
+pcount <- pquery |> count()
+pcount
+```
+
+The `results()` method will fetch actual results.
+
+```{r pqueryresults}
+presults <- pquery |> results()
+```
+These results are
+returned from the GDC in [JSON](http://www.json.org/) format and
+converted into a (potentially nested) list in R. The `str()` method is useful
+for taking a quick glimpse of the data.
+
+```{r presultsstr}
+str(presults)
+```
+
+A default of only 10 records are returned. We can use the `size` and `from`
+arguments to `results()` to either page through results or to change the number
+of results. Finally, there is a convenience method, `results_all()` that will
+simply fetch all the available results given a query. Note that `results_all()`
+may take a long time and return HUGE result sets if not used carefully. Use of a
+combination of `count()` and `results()` to get a sense of the expected data
+size is probably warranted before calling `results_all()`
+
+```{r presultsall}
+length(ids(presults))
+presults <- pquery |> results_all()
+length(ids(presults))
+# includes all records
+length(ids(presults)) == count(pquery)
+```
+
+Extracting subsets of
+results or manipulating the results into a more conventional R data
+structure is not easily generalizable.  However,
+the
+[purrr](https://github.com/hadley/purrr),
+[rlist](https://renkun.me/rlist/),
+and [data.tree](https://cran.r-project.org/web/packages/data.tree/vignettes/data.tree.html) packages
+are all potentially of interest for manipulating complex, nested list
+structures. For viewing the results in an interactive viewer, consider the
+[listviewer](https://github.com/timelyportfolio/listviewer) package.
+
+
+### Fields and Values
+
+[[ GDC `fields` documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#fields)
+
+Central to querying and retrieving data from the GDC is the ability to specify
+which fields to return, filtering by fields and values, and faceting or
+aggregating. The GenomicDataCommons package includes two simple functions,
+`available_fields()` and `default_fields()`. Each can operate on a character(1)
+endpoint name ("cases", "files", "annotations", or "projects") or a `GDCQuery`
+object.
+
+```{r defaultfields}
+default_fields('files')
+# The number of fields available for files endpoint
+length(available_fields('files'))
+# The first few fields available for files endpoint
+head(available_fields('files'))
+```
+
+The fields to be returned by a query can be specified following a similar
+paradigm to that of the dplyr package. The `select()` function is a verb that
+resets the fields slot of a `GDCQuery`; note that this is not quite analogous to
+the dplyr `select()` verb that limits from already-present fields. We
+*completely replace* the fields when using `select()` on a `GDCQuery`.
+
+```{r selectexample}
+# Default fields here
+qcases <- cases()
+qcases$fields
+# set up query to use ALL available fields
+# Note that checking of fields is done by select()
+qcases <- cases() |> GenomicDataCommons::select(available_fields('cases'))
+head(qcases$fields)
+```
+
+Finding fields of interest is such a common operation that the
+GenomicDataCommons includes the `grep_fields()` function.
+See the appropriate help pages for details.
+
+### Facets and aggregation
+
+[[ GDC `facet` documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#facets)
+
+The GDC API offers a feature known as aggregation or faceting. By
+specifying one or more fields (of appropriate type), the GDC can
+return to us a count of the number of records matching each potential
+value. This is similar to the R `table` method. Multiple fields can be
+returned at once, but the GDC API does not have a cross-tabulation
+feature; all aggregations are only on one field at a time. Results of
+`aggregation()` calls come back as a list of data.frames (actually,
+tibbles).
+
+```{r aggexample}
+# total number of files of a specific type
+res <- files() |> facet(c('type','data_type')) |> aggregations()
+res$type
+```
+
+Using `aggregations()` is an also easy way to learn the contents of individual
+fields and forms the basis for faceted search pages.
+
+### Filtering
+
+[[ GDC `filtering` documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#filters-specifying-the-query)
+
+The GenomicDataCommons package uses a form of non-standard evaluation to specify
+R-like queries that are then translated into an R list. That R list is, upon
+calling a method that fetches results from the GDC API, translated into the
+appropriate JSON string. The R expression uses the formula interface as
+suggested by Hadley Wickham in his [vignette on non-standard evaluation](https://cran.r-project.org/web/packages/dplyr/vignettes/nse.html)
+
+> It’s best to use a formula because a formula captures both the expression to
+evaluate and the environment where the evaluation occurs. This is important if
+the expression is a mixture of variables in a data frame and objects in the
+local environment [for example].
+
+For the user, these details will not be too important except to note that a
+filter expression must begin with a "~".
+
+```{r allfilesunfiltered}
+qfiles <- files()
+qfiles |> count() # all files
+```
+To limit the file type, we can refer back to the
+[section on faceting](#facets-and-aggregation) to see the possible values for
+the file field "type". For example, to filter file results to only
+"gene_expression" files, we simply specify a filter.
+
+```{r onlyGeneExpression}
+qfiles <- files() |> filter( type == 'gene_expression')
+# here is what the filter looks like after translation
+str(get_filter(qfiles))
+```
+
+What if we want to create a filter based on the project ('TCGA-OVCA', for
+example)? Well, we have a couple of possible ways to discover available fields.
+The first is based on base R functionality and some intuition.
+
+```{r filtAvailFields}
+grep('pro',available_fields('files'),value=TRUE) |> 
+    head()
+```
+
+Interestingly, the project information is "nested" inside the case. We don't
+need to know that detail other than to know that we now have a few potential
+guesses for where our information might be in the files records.  We need to
+know where because we need to construct the appropriate filter.
+
+```{r filtProgramID}
+files() |> 
+    facet('cases.project.project_id') |> 
+    aggregations() |> 
+    head()
+```
+
+We note that `cases.project.project_id` looks like it is a good fit. We also
+note that `TCGA-OV` is the correct project_id, not `TCGA-OVCA`. Note that
+*unlike with dplyr and friends, the `filter()` method here **replaces** the
+filter and does not build on any previous filters*.
+
+```{r filtfinal}
+qfiles <- files() |>
+    filter( cases.project.project_id == 'TCGA-OV' & type == 'gene_expression')
+str(get_filter(qfiles))
+qfiles |> count()
+```
+
+Asking for a `count()` of results given these new filter criteria gives `r
+qfiles |> count()` results. Filters can be chained (or nested) to 
+accomplish the same effect as multiple `&` conditionals. The `count()`
+below is equivalent to the `&` filtering done above.
+
+```{r filtChain}
+qfiles2 <- files() |>
+    filter( cases.project.project_id == 'TCGA-OV') |> 
+    filter( type == 'gene_expression') 
+qfiles2 |> count()
+(qfiles |> count()) == (qfiles2 |> count()) #TRUE
+```
+
+
+
+Generating a manifest for bulk downloads is as
+simple as asking for the manifest from the current query.
+
+```{r filtAndManifest}
+manifest_df <- qfiles |> manifest()
+head(manifest_df)
+```
+
+Note that we might still not be quite there. Looking at filenames, there are
+suspiciously named files that might include "FPKM", "FPKM-UQ", or "counts".
+Another round of `grep` and `available_fields`, looking for "type" turned up
+that the field "analysis.workflow_type" has the appropriate filter criteria.
+
+
+```{r filterForSTARCounts}
+qfiles <- files() |> filter( ~ cases.project.project_id == 'TCGA-OV' &
+                            type == 'gene_expression' &
+                            access == "open" &
+                            analysis.workflow_type == 'STAR - Counts')
+manifest_df <- qfiles |> manifest()
+nrow(manifest_df)
+```
+
+The GDC Data Transfer Tool can be used (from R, `transfer()` or from the
+command-line) to orchestrate high-performance, restartable transfers of all the
+files in the manifest. See [the bulk downloads section](bulk-downloads) for
+details.
+
+
+## Authentication
+
+[[ GDC authentication documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#facets)
+
+The GDC offers both "controlled-access" and "open" data. As of this
+writing, only data stored as files is "controlled-access"; that is,
+metadata accessible via the GDC is all "open" data and some files are
+"open" and some are "controlled-access". Controlled-access data are
+only available
+after
+[going through the process of obtaining access.](https://gdc.cancer.gov/access-data/obtaining-access-controlled-data)
+
+After controlled-access to one or more datasets has been granted,
+logging into the GDC web portal will allow you
+to
+[access a GDC authentication token](https://docs.gdc.cancer.gov/Data_Portal/Users_Guide/Authentication/#gdc-authentication-tokens),
+which can be downloaded and then used to access available
+controlled-access data via the GenomicDataCommons package.
+
+The GenomicDataCommons uses authentication tokens only for downloading
+data (see `transfer` and `gdcdata` documentation). The package
+includes a helper function, `gdc_token`, that looks for the token to
+be stored in one of three ways (resolved in this order):
+
+1. As a string stored in the environment variable, `GDC_TOKEN`
+2. As a file, stored in the file named by the environment variable,
+   `GDC_TOKEN_FILE`
+3. In a file in the user home directory, called `.gdc_token`
+
+As a concrete example:
+
+```{r authenNoRun, eval=FALSE}
+token <- gdc_token()
+transfer(...,token=token)
+# or
+transfer(...,token=get_token())
+```
+
+
+## Datafile access and download
+
+### Data downloads via the GDC API
+
+The `gdcdata` function takes a character vector of one or more file
+ids. A simple way of producing such a vector is to produce a
+`manifest` data frame and then pass in the first column, which will
+contain file ids.
+
+```{r singlefileDL}
+fnames <- gdcdata(manifest_df$id[1:2],progress=FALSE)
+
+```
+
+Note that for controlled-access data, a
+GDC [authentication token](#authentication) is required. Using the
+`BiocParallel` package may be useful for downloading in parallel,
+particularly for large numbers of smallish files.
+
+### Bulk downloads
+
+The bulk download functionality is only efficient (as of v1.2.0 of the
+GDC Data Transfer Tool) for relatively large files, so use this
+approach only when transferring BAM files or larger VCF files, for
+example. Otherwise, consider using the approach shown above, perhaps
+in parallel.
+
+```{r bulkDL, eval=FALSE}
+# Requires gcd_client command-line utility to be isntalled
+# separately. 
+fnames <- gdcdata(manifest_df$id[3:10], access_method = 'client')
+```
+
+
+### BAM slicing
+
+# Use Cases
+
+## Cases
+
+### How many cases are there per project_id?
+
+```{r casesPerProject}
+res <- cases() |> facet("project.project_id") |> aggregations()
+head(res)
+library(ggplot2)
+ggplot(res$project.project_id,aes(x = key, y = doc_count)) +
+    geom_bar(stat='identity') +
+    theme(axis.text.x = element_text(angle = 45, hjust = 1))
+```
+
+### How many cases are included in all TARGET projects?
+
+```{r casesInTCGA}
+cases() |> filter(~ project.program.name=='TARGET') |> count()
+```
+
+### How many cases are included in all TCGA projects?
+
+```{r casesInTARGET}
+cases() |> filter(~ project.program.name=='TCGA') |> count()
+```
+
+### What is the breakdown of sample types in TCGA-BRCA?
+
+```{r casesTCGABRCASampleTypes}
+# The need to do the "&" here is a requirement of the
+# current version of the GDC API. I have filed a feature
+# request to remove this requirement.
+resp <- cases() |> filter(~ project.project_id=='TCGA-BRCA' &
+                              project.project_id=='TCGA-BRCA' ) |>
+    facet('samples.sample_type') |> aggregations()
+resp$samples.sample_type
+```
+
+### Fetch all samples in TCGA-BRCA that use "Solid Tissue" as a normal.
+
+```{r casesTCGABRCASolidNormal}
+# The need to do the "&" here is a requirement of the
+# current version of the GDC API. I have filed a feature
+# request to remove this requirement.
+resp <- cases() |> filter(~ project.project_id=='TCGA-BRCA' &
+                              samples.sample_type=='Solid Tissue Normal') |>
+    GenomicDataCommons::select(c(default_fields(cases()),'samples.sample_type')) |>
+    response_all()
+count(resp)
+res <- resp |> results()
+str(res[1],list.len=6)
+head(ids(resp))
+```
+
+### Get all TCGA case ids that are female
+
+```{r casesFemaleTCGA}
+cases() |>
+  GenomicDataCommons::filter(~ project.program.name == 'TCGA' &
+    "cases.demographic.gender" %in% "female") |>
+      GenomicDataCommons::results(size = 4) |>
+        ids()
+```
+
+### Get all TCGA-COAD case ids that are NOT female
+
+```{r notFemaleTCGACOAD}
+cases() |>
+  GenomicDataCommons::filter(~ project.project_id == 'TCGA-COAD' &
+    "cases.demographic.gender" %exclude% "female") |>
+      GenomicDataCommons::results(size = 4) |>
+        ids()
+```
+
+### Get all TCGA cases that are missing gender
+
+```{r missingGenderTCGA}
+cases() |>
+  GenomicDataCommons::filter(~ project.program.name == 'TCGA' &
+    missing("cases.demographic.gender")) |>
+      GenomicDataCommons::results(size = 4) |>
+        ids()
+```
+
+### Get all TCGA cases that are NOT missing gender
+
+```{r notMissingGenderTCGA}
+cases() |>
+  GenomicDataCommons::filter(~ project.program.name == 'TCGA' &
+    !missing("cases.demographic.gender")) |>
+      GenomicDataCommons::results(size = 4) |>
+        ids()
+```
+
+
+## Files
+
+### How many of each type of file are available?
+
+```{r filesVCFCount}
+res <- files() |> facet('type') |> aggregations()
+res$type
+ggplot(res$type,aes(x = key,y = doc_count)) + geom_bar(stat='identity') +
+    theme(axis.text.x = element_text(angle = 45, hjust = 1))
+```
+
+### Find gene-level RNA-seq quantification files for GBM
+
+```{r filesRNAseqGeneGBM}
+q <- files() |>
+    GenomicDataCommons::select(available_fields('files')) |>
+    filter(~ cases.project.project_id=='TCGA-GBM' &
+               data_type=='Gene Expression Quantification')
+q |> facet('analysis.workflow_type') |> aggregations()
+# so need to add another filter
+file_ids <- q |> filter(~ cases.project.project_id=='TCGA-GBM' &
+                            data_type=='Gene Expression Quantification' &
+                            analysis.workflow_type == 'STAR - Counts') |>
+    GenomicDataCommons::select('file_id') |>
+    response_all() |>
+    ids()
+```
+
+## Slicing
+
+### Get all BAM file ids from TCGA-GBM
+
+**I need to figure out how to do slicing reproducibly in a testing environment
+and for vignette building**.
+
+```{r filesRNAseqGeneGBMforBAM}
+q <- files() |>
+    GenomicDataCommons::select(available_fields('files')) |>
+    filter(~ cases.project.project_id == 'TCGA-GBM' &
+               data_type == 'Aligned Reads' &
+               experimental_strategy == 'RNA-Seq' &
+               data_format == 'BAM')
+file_ids <- q |> response_all() |> ids()
+```
+
+
+```{r slicing10, eval=FALSE}
+bamfile <- slicing(file_ids[1],regions="chr12:6534405-6538375",token=gdc_token())
+library(GenomicAlignments)
+aligns <- readGAlignments(bamfile)
+```
+
+# Troubleshooting
+
+## SSL connection errors
+
+* Symptom: Trying to connect to the API results in:
+```
+Error in curl::curl_fetch_memory(url, handle = handle) :
+SSL connect error
+```
+* Possible solutions: The [issue
+is that the GDC supports only recent security Transport Layer Security (TLS)](http://stackoverflow.com/a/42599546/459633),
+so the only known fix is to upgrade the system `openssl` to version
+1.0.1 or later.
+    * [[Mac OS]](https://github.com/Bioconductor/GenomicDataCommons/issues/35#issuecomment-284233510),
+    * [[Ubuntu]](http://askubuntu.com/a/434245)
+    * [[Centos/RHEL]](https://www.liquidweb.com/kb/update-and-patch-openssl-for-the-ccs-injection-vulnerability/).
+    After upgrading `openssl`, reinstall the R `curl` and `httr` packages.
+
+
+# sessionInfo()
+
+```{r sessionInfo}
+sessionInfo()
+```
+
+# Developer notes
+
+- The `S3` object-oriented programming paradigm is used.
+- We have adopted a functional programming style with functions and methods that
+often take an "object" as the first argument. This style lends itself to
+pipeline-style programming.
+- The GenomicDataCommons package uses the
+[alternative request format (POST)](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#alternative-request-format)
+to allow very large request bodies.
+
diff --git a/vignettes/questions-and-answers.Rmd b/vignettes/questions-and-answers.Rmd
index 67fcf74..d8649d6 100644
--- a/vignettes/questions-and-answers.Rmd
+++ b/vignettes/questions-and-answers.Rmd
@@ -29,7 +29,7 @@ changes to lazy evaluation best practices. There is now no need to
 include the `~` in the filter expression. So:
 
 ```{r}
-q = files() |>
+q <- files() |>
   GenomicDataCommons::filter(
     cases.project.project_id == 'TCGA-COAD' &
       data_type == 'Aligned Reads' &
@@ -51,7 +51,7 @@ manifest(q)
 Your question about race and ethnicity is a good one. 
 
 ```{r}
-all_fields = available_fields(files())
+all_fields <- available_fields(files())
 ```
 
 And we can grep for `race` or `ethnic` to get potential matching fields
@@ -72,7 +72,7 @@ available_values('files',"cases.demographic.race")
 We can complete our filter expression now to limit to `white` race only.
 
 ```{r}
-q_white_only = q |>
+q_white_only <- q |>
   GenomicDataCommons::filter(cases.demographic.race=='white')
 count(q_white_only)
 manifest(q_white_only)
diff --git a/vignettes/somatic_mutations.Rmd b/vignettes/somatic_mutations.Rmd
index 4268c16..1c6c975 100644
--- a/vignettes/somatic_mutations.Rmd
+++ b/vignettes/somatic_mutations.Rmd
@@ -38,7 +38,7 @@ head(available_values('genes','symbol'))
 
 
 ```{r}
-tp53 = genes() |> 
+tp53 <- genes() |> 
   GenomicDataCommons::filter(symbol=='TP53') |> 
   results(size=10000) |> 
   as_tibble()
@@ -67,7 +67,7 @@ ssms() |>
 
 ```{r warning=FALSE,message=FALSE}
 library(VariantAnnotation)
-vars = ssms() |> 
+vars <- ssms() |> 
     GenomicDataCommons::filter(
       consequence.transcript.gene.symbol %in% c('TP53')) |> 
     GenomicDataCommons::results_all() |>
@@ -75,7 +75,7 @@ vars = ssms() |>
 ```
 
 ```{r}
-vr = VRanges(seqnames = vars$chromosome,
+vr <- VRanges(seqnames = vars$chromosome,
              ranges = IRanges(start=vars$start_position, width=1),
              ref = vars$reference_allele,
              alt = vars$tumor_allele)
@@ -89,7 +89,7 @@ ssm_occurrences() |>
 ```
 
 ```{r}
-var_samples = ssm_occurrences() |> 
+var_samples <- ssm_occurrences() |> 
     GenomicDataCommons::filter(
       ssm.consequence.transcript.gene.symbol %in% c('TP53')) |> 
     GenomicDataCommons::expand(c('case', 'ssm', 'case.project')) |>
@@ -119,7 +119,7 @@ fnames <- files() |>
 
 ```{r cache=TRUE}
 library(maftools)
-melanoma = read.maf(maf = fnames)
+melanoma <- read.maf(maf = fnames)
 ```
 
 ```{r}

From d44262888bd66273b78acb3ebbb6ab7c06a77a2b Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Mon, 3 Mar 2025 10:34:13 -0500
Subject: [PATCH 03/11] Add files via upload

---
 R/tcga_CEL.R | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 R/tcga_CEL.R

diff --git a/R/tcga_CEL.R b/R/tcga_CEL.R
new file mode 100644
index 0000000..5cceb52
--- /dev/null
+++ b/R/tcga_CEL.R
@@ -0,0 +1,28 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+#
+
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-GBM' & data_category == 'Transcriptome Profiling' & data_format == 'CEL') |> manifest()
+#OR use filter fn
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-GBM' & data_category == 'Transcriptome Profiling' & data_format == 'CEL') |> GenomicDataCommons::filter(access=='OPEN') |> manifest()
+
+for(i in seq(10,12))
+{
+uid<-0;
+uid<-as.character(q_3[i,1])
+gdcdata(uid)
+}
+
+
+#
+n<-which(q_2["access"] == 'open')
+for(j in seq(2,3))
+{
+Id<-0
+Id<-as.character(q_3[n[j],1])
+gdcdata(Id)
+}
+
+

From 18e31be38e73048f2500b4cf7c7e3c97b3a66a81 Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Mon, 3 Mar 2025 11:24:45 -0500
Subject: [PATCH 04/11] Add files via upload

---
 vignettes/target_cn.R            | 21 +++++++++++++++++++++
 vignettes/target_methylation.R   | 21 +++++++++++++++++++++
 vignettes/target_methylation_1.R | 17 +++++++++++++++++
 vignettes/tcga_CEL.R             | 28 ++++++++++++++++++++++++++++
 vignettes/tcga_proteome.R        | 29 +++++++++++++++++++++++++++++
 vignettes/tcga_slides.R          | 25 +++++++++++++++++++++++++
 vignettes/tcga_slides_1.R        | 27 +++++++++++++++++++++++++++
 7 files changed, 168 insertions(+)
 create mode 100644 vignettes/target_cn.R
 create mode 100644 vignettes/target_methylation.R
 create mode 100644 vignettes/target_methylation_1.R
 create mode 100644 vignettes/tcga_CEL.R
 create mode 100644 vignettes/tcga_proteome.R
 create mode 100644 vignettes/tcga_slides.R
 create mode 100644 vignettes/tcga_slides_1.R

diff --git a/vignettes/target_cn.R b/vignettes/target_cn.R
new file mode 100644
index 0000000..547a681
--- /dev/null
+++ b/vignettes/target_cn.R
@@ -0,0 +1,21 @@
+library(GenomicDataCommons)
+library(dplyr)
+library(tibble)
+#Clear Cell Sarcoma of the Kidney. Disease Type. Complex Mixed and Stromal Neoplasms. Primary Site. Kidney. Program. TARGET
+
+
+cn_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |>  GenomicDataCommons::filter( analysis.workflow_type == 'ASCAT2')  |> manifest()
+n<-which(cn_manifest_CCSK$access=='open')
+
+#save dat to file
+write.csv(cn_manifest_CCSK[n,],file='out.txt',quote=FALSE,row.names=FALSE)
+##########----------#######################
+#select files
+for( i in seq(1,length(n)))
+{
+#
+id<-0;
+        id<-as.character(cn_manifest_CCSK[n[i],1])
+###### 
+gdcdata(id)
+}
diff --git a/vignettes/target_methylation.R b/vignettes/target_methylation.R
new file mode 100644
index 0000000..1f54692
--- /dev/null
+++ b/vignettes/target_methylation.R
@@ -0,0 +1,21 @@
+library(GenomicDataCommons)
+library(dplyr)
+library(tibble)
+#Clear Cell Sarcoma of the Kidney. Disease Type. Complex Mixed and Stromal Neoplasms. Primary Site. Kidney. Program. TARGET
+
+#get familiar with aggregations
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TARGET-CCSK') |> facet(c("data_type","data_format","analysis.workflow_type","file_id","file_name")) |> aggregations()
+
+
+
+q_1 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TARGET-CCSK') |> facet(c("data_type","data_format","analysis.workflow_type")) |> aggregations()
+
+idat_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |> GenomicDataCommons::filter( data_type == 'Methylation Beta Value' ) |> GenomicDataCommons::filter( analysis.workflow_type == 'SeSAMe Methylation Beta Estimation')  |> manifest()
+n<-which(idat_manifest_CCSK$access=='open')
+
+#save data to file
+write.csv(idat_manifest_CCSK[n,],file='manifest.txt',quote=FALSE,row.names=FALSE)
+
+
+###### test  single file 
+gdcdata(idat_manifest_CCSK[n[1],1]))
diff --git a/vignettes/target_methylation_1.R b/vignettes/target_methylation_1.R
new file mode 100644
index 0000000..2c091c4
--- /dev/null
+++ b/vignettes/target_methylation_1.R
@@ -0,0 +1,17 @@
+library(GenomicDataCommons)
+library(dplyr)
+library(tibble)
+
+
+idat_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |> GenomicDataCommons::filter( data_type == 'Methylation Beta Value' ) |> GenomicDataCommons::filter( analysis.workflow_type == 'SeSAMe Methylation Beta Estimation')  |> manifest()
+n<-which(idat_manifest_CCSK$access=='open')
+
+##########----------#######################
+for( i in seq(1,length(n)))
+{
+#use cast
+id<-0;
+	id<-as.character(idat_manifest_CCSK[n[i],1])
+######only test with single file 
+gdcdata(id)
+}
diff --git a/vignettes/tcga_CEL.R b/vignettes/tcga_CEL.R
new file mode 100644
index 0000000..5cceb52
--- /dev/null
+++ b/vignettes/tcga_CEL.R
@@ -0,0 +1,28 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+#
+
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-GBM' & data_category == 'Transcriptome Profiling' & data_format == 'CEL') |> manifest()
+#OR use filter fn
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-GBM' & data_category == 'Transcriptome Profiling' & data_format == 'CEL') |> GenomicDataCommons::filter(access=='OPEN') |> manifest()
+
+for(i in seq(10,12))
+{
+uid<-0;
+uid<-as.character(q_3[i,1])
+gdcdata(uid)
+}
+
+
+#
+n<-which(q_2["access"] == 'open')
+for(j in seq(2,3))
+{
+Id<-0
+Id<-as.character(q_3[n[j],1])
+gdcdata(Id)
+}
+
+
diff --git a/vignettes/tcga_proteome.R b/vignettes/tcga_proteome.R
new file mode 100644
index 0000000..d4dd688
--- /dev/null
+++ b/vignettes/tcga_proteome.R
@@ -0,0 +1,29 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+p_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_type == 'Protein Expression Quantification' & data_format == 'tsv') |> manifest()
+#locate open data
+open_access<-which(p_2$access=="open")
+#381 files
+#download select files 
+#for(i in length(open_access))
+#for(i in seq(3,5))
+#for(i in seq(20,24))
+
+for(i in seq(200,202))
+{
+uid<-0;uid<-as.character(p_2[open_access[i],1])
+gdcdata(uid)
+}
+
+#sanity check , use the filter function 
+
+
+p_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_type == 'Protein Expression Quantification' & data_format == 'tsv') |> filter(access == 'open') |> manifest()
+
+for(i in seq(20,24))
+{
+uid<-0;uid<-as.character(p_3[i,1])
+gdcdata(uid)
+}
diff --git a/vignettes/tcga_slides.R b/vignettes/tcga_slides.R
new file mode 100644
index 0000000..f260f3d
--- /dev/null
+++ b/vignettes/tcga_slides.R
@@ -0,0 +1,25 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+#specify project name
+#q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-KIRC' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-BRCA' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
+#locate open data
+open_access<-which(q_2$access=="open")
+
+#select files
+#for(i in length(open_access))
+#for(i in seq(3,5))
+#for(i in seq(20,24))
+for(i in seq(200,202))
+{
+uid<-0;uid<-as.character(q_2[open_access[i],1])
+gdcdata(uid)
+}
+
+
+######alternatively, use filter 
+#both approaches should list same files
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-BRCA' & data_type == 'Slide Image' & data_format == 'svs') |> filter(access == 'open') |>  manifest()
+
diff --git a/vignettes/tcga_slides_1.R b/vignettes/tcga_slides_1.R
new file mode 100644
index 0000000..057547b
--- /dev/null
+++ b/vignettes/tcga_slides_1.R
@@ -0,0 +1,27 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-COAD' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
+#locate open data
+open_access<-which(q_2$access=="open")
+
+#for(i in length(open_access))
+#for(i in seq(3,5))
+#for(i in seq(20,24))
+for(i in seq(200,202))
+{
+uid<-0;uid<-as.character(q_2[open_access[i],1])
+gdcdata(uid)
+}
+
+
+#or sanity check
+
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-COAD' & data_type == 'Slide Image' & data_format == 'svs') |> filter(access == 'open') |> manifest()
+
+for(i in seq(2,4))
+{
+uid<-0;uid<-as.character(q_3[i,1])
+gdcdata(uid)
+}

From b5e4e2ea504387a85e7948eebcb4950dc113ee6b Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Wed, 5 Mar 2025 15:30:20 -0500
Subject: [PATCH 05/11] Add files via upload

---
 vignettes/mmrf_commpass_wgs.R | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 vignettes/mmrf_commpass_wgs.R

diff --git a/vignettes/mmrf_commpass_wgs.R b/vignettes/mmrf_commpass_wgs.R
new file mode 100644
index 0000000..8624de2
--- /dev/null
+++ b/vignettes/mmrf_commpass_wgs.R
@@ -0,0 +1,34 @@
+
+
+#building queries
+
+#get  available info for project MMRF-COMMPASS
+q_1 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> manifest()
+
+#save info to file for future use
+write.csv(q_1,file="out.txt",quote=FALE,row.names=FALSE)
+
+#list only open access entries
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open")|> manifest()
+
+# restrict data to WGS  
+
+
+q_3=files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open") |> filter(experimental_strategy == "WGS") |> manifest() 
+
+
+#restrict data to WGS Copy Number Segment
+q_4=files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open") |> filter(experimental_strategy == "WGS" & data_type == 'Copy Number Segment') |> manifest() 
+
+
+#get files less than size 32000
+
+q_5=files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open") |> filter(experimental_strategy == "WGS" & data_type == 'Copy Number Segment' & file_size < 32000) |> manifest() 
+
+#get the files
+for(i in seq(1,dim(q_5)[1]))
+{
+uid<-0;
+uid<-as.character(q_6[i,"id"])
+gdcdata(uid)
+}

From 3833ec238dd7ffc48437253ed67715b1e473e7bc Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Wed, 5 Mar 2025 16:46:28 -0500
Subject: [PATCH 06/11] Add files via upload

---
 vignettes/mmrf_commpass_wxs.R | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 vignettes/mmrf_commpass_wxs.R

diff --git a/vignettes/mmrf_commpass_wxs.R b/vignettes/mmrf_commpass_wxs.R
new file mode 100644
index 0000000..b04e128
--- /dev/null
+++ b/vignettes/mmrf_commpass_wxs.R
@@ -0,0 +1,34 @@
+
+
+#building queries
+
+#get  available info for project MMRF-COMMPASS
+q_1 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> manifest()
+
+#save info to file for future use
+write.csv(q_3,file="out.txt",quote=FALE,row.names=FALSE)
+
+#list only open access entries
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open")|> manifest()
+
+# restrict data to WXS  
+
+
+q_3=files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open") |> filter(experimental_strategy == "WXS") |> manifest() 
+
+
+#restrict data to WXS Masked Somatic Mutation
+q_4=files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open") |> filter(experimental_strategy == "WXS" & data_type == 'Masked Somatic Mutation') |> manifest() 
+
+
+#list files by timestamp
+
+q_5=files() |> GenomicDataCommons::filter(cases.project.project_id == 'MMRF-COMMPASS') |> filter(access == "open") |> filter(experimental_strategy == "WXS" & data_type == 'Masked Somatic Mutation' & created_datetime < "2022-08-22T10:48:06.705961-05:00" ) |> manifest() 
+
+#get the files
+for(i in seq(1,dim(q_5)[1]))
+{
+uid<-0;
+uid<-as.character(q_5[i,"id"])
+gdcdata(uid)
+}

From c36419132cdee2325524a967cadcc6b244ab3f3d Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Thu, 6 Mar 2025 15:23:07 -0500
Subject: [PATCH 07/11] Add files via upload

---
 vignettes/tcgaTHCA_clinical.R  | 14 ++++++++++++++
 vignettes/tcgaTHCA_pathology.R | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+)
 create mode 100644 vignettes/tcgaTHCA_clinical.R
 create mode 100644 vignettes/tcgaTHCA_pathology.R

diff --git a/vignettes/tcgaTHCA_clinical.R b/vignettes/tcgaTHCA_clinical.R
new file mode 100644
index 0000000..6a34221
--- /dev/null
+++ b/vignettes/tcgaTHCA_clinical.R
@@ -0,0 +1,14 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+#get files for project TCGA-THCA
+#build a manifest file 
+#use col names  with function calls
+p_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_category == 'Clinical' & data_type == 'Clinical Supplement' & data_format == 'BCR XML')  |> filter(access == "open") |> manifest()
+#get select data
+for(i in seq(20,24))
+{
+uid<-0;uid<-as.character(p_2[i,1])
+gdcdata(uid)
+}
diff --git a/vignettes/tcgaTHCA_pathology.R b/vignettes/tcgaTHCA_pathology.R
new file mode 100644
index 0000000..6288dd9
--- /dev/null
+++ b/vignettes/tcgaTHCA_pathology.R
@@ -0,0 +1,33 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+
+# get pathology reports
+q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_category == 'Clinical' & data_type == 'Pathology Report') |> manifest()
+
+for(i in seq(20,24))
+{
+uid<-0;uid<-as.character(q_2[i,1])
+gdcdata(uid)
+}
+
+#use updated datetime to filter data
+q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_category == 'Clinical' & data_type == 'Pathology Report' &  (updated_datetime ==  "2022-12-06T15:32:24.960627-06:00")) |> manifest()
+
+#or 
+
+q_4 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_category == 'Clinical' & data_type == 'Pathology Report' &  (updated_datetime > "2022-12-06T15:32:24.960627-06:00")) |> manifest()
+
+for(i in seq(20,24))
+{
+uid<-0;uid<-as.character(q_4[i,1])
+gdcdata(uid)
+}
+
+#use file size to filter and updated datetime
+#single hit
+q_5 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_category == 'Clinical' & data_type == 'Pathology Report' &  (updated_datetime == "2022-12-06T15:32:24.960627-06:00") & file_size < 2350000) |> manifest()
+#get one file that fits above criteria
+gdcdata(q_5[1,"id"])
+

From 630ee3d2f65ac128f253e90655821d47ad79af42 Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Wed, 12 Mar 2025 17:30:37 -0400
Subject: [PATCH 08/11] Files deleted from incorrect dir

---
 R/target_cn.R            | 21 ---------------------
 R/target_methylation.R   | 21 ---------------------
 R/target_methylation_1.R | 17 -----------------
 R/tcga_CEL.R             | 28 ----------------------------
 R/tcga_proteome.R        | 29 -----------------------------
 R/tcga_slides.R          | 25 -------------------------
 R/tcga_slides_1.R        | 27 ---------------------------
 7 files changed, 168 deletions(-)
 delete mode 100644 R/target_cn.R
 delete mode 100644 R/target_methylation.R
 delete mode 100644 R/target_methylation_1.R
 delete mode 100644 R/tcga_CEL.R
 delete mode 100644 R/tcga_proteome.R
 delete mode 100644 R/tcga_slides.R
 delete mode 100644 R/tcga_slides_1.R

diff --git a/R/target_cn.R b/R/target_cn.R
deleted file mode 100644
index 547a681..0000000
--- a/R/target_cn.R
+++ /dev/null
@@ -1,21 +0,0 @@
-library(GenomicDataCommons)
-library(dplyr)
-library(tibble)
-#Clear Cell Sarcoma of the Kidney. Disease Type. Complex Mixed and Stromal Neoplasms. Primary Site. Kidney. Program. TARGET
-
-
-cn_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |>  GenomicDataCommons::filter( analysis.workflow_type == 'ASCAT2')  |> manifest()
-n<-which(cn_manifest_CCSK$access=='open')
-
-#save dat to file
-write.csv(cn_manifest_CCSK[n,],file='out.txt',quote=FALSE,row.names=FALSE)
-##########----------#######################
-#select files
-for( i in seq(1,length(n)))
-{
-#
-id<-0;
-        id<-as.character(cn_manifest_CCSK[n[i],1])
-###### 
-gdcdata(id)
-}
diff --git a/R/target_methylation.R b/R/target_methylation.R
deleted file mode 100644
index 1f54692..0000000
--- a/R/target_methylation.R
+++ /dev/null
@@ -1,21 +0,0 @@
-library(GenomicDataCommons)
-library(dplyr)
-library(tibble)
-#Clear Cell Sarcoma of the Kidney. Disease Type. Complex Mixed and Stromal Neoplasms. Primary Site. Kidney. Program. TARGET
-
-#get familiar with aggregations
-q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TARGET-CCSK') |> facet(c("data_type","data_format","analysis.workflow_type","file_id","file_name")) |> aggregations()
-
-
-
-q_1 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TARGET-CCSK') |> facet(c("data_type","data_format","analysis.workflow_type")) |> aggregations()
-
-idat_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |> GenomicDataCommons::filter( data_type == 'Methylation Beta Value' ) |> GenomicDataCommons::filter( analysis.workflow_type == 'SeSAMe Methylation Beta Estimation')  |> manifest()
-n<-which(idat_manifest_CCSK$access=='open')
-
-#save data to file
-write.csv(idat_manifest_CCSK[n,],file='manifest.txt',quote=FALSE,row.names=FALSE)
-
-
-###### test  single file 
-gdcdata(idat_manifest_CCSK[n[1],1]))
diff --git a/R/target_methylation_1.R b/R/target_methylation_1.R
deleted file mode 100644
index 2c091c4..0000000
--- a/R/target_methylation_1.R
+++ /dev/null
@@ -1,17 +0,0 @@
-library(GenomicDataCommons)
-library(dplyr)
-library(tibble)
-
-
-idat_manifest_CCSK <- files() |> GenomicDataCommons::filter( cases.project.project_id == 'TARGET-CCSK') |> GenomicDataCommons::filter( data_type == 'Methylation Beta Value' ) |> GenomicDataCommons::filter( analysis.workflow_type == 'SeSAMe Methylation Beta Estimation')  |> manifest()
-n<-which(idat_manifest_CCSK$access=='open')
-
-##########----------#######################
-for( i in seq(1,length(n)))
-{
-#use cast
-id<-0;
-	id<-as.character(idat_manifest_CCSK[n[i],1])
-######only test with single file 
-gdcdata(id)
-}
diff --git a/R/tcga_CEL.R b/R/tcga_CEL.R
deleted file mode 100644
index 5cceb52..0000000
--- a/R/tcga_CEL.R
+++ /dev/null
@@ -1,28 +0,0 @@
-library(dplyr)
-library(tibble)
-library(GenomicDataCommons)
-
-#
-
-q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-GBM' & data_category == 'Transcriptome Profiling' & data_format == 'CEL') |> manifest()
-#OR use filter fn
-q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-GBM' & data_category == 'Transcriptome Profiling' & data_format == 'CEL') |> GenomicDataCommons::filter(access=='OPEN') |> manifest()
-
-for(i in seq(10,12))
-{
-uid<-0;
-uid<-as.character(q_3[i,1])
-gdcdata(uid)
-}
-
-
-#
-n<-which(q_2["access"] == 'open')
-for(j in seq(2,3))
-{
-Id<-0
-Id<-as.character(q_3[n[j],1])
-gdcdata(Id)
-}
-
-
diff --git a/R/tcga_proteome.R b/R/tcga_proteome.R
deleted file mode 100644
index d4dd688..0000000
--- a/R/tcga_proteome.R
+++ /dev/null
@@ -1,29 +0,0 @@
-library(dplyr)
-library(tibble)
-library(GenomicDataCommons)
-
-p_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_type == 'Protein Expression Quantification' & data_format == 'tsv') |> manifest()
-#locate open data
-open_access<-which(p_2$access=="open")
-#381 files
-#download select files 
-#for(i in length(open_access))
-#for(i in seq(3,5))
-#for(i in seq(20,24))
-
-for(i in seq(200,202))
-{
-uid<-0;uid<-as.character(p_2[open_access[i],1])
-gdcdata(uid)
-}
-
-#sanity check , use the filter function 
-
-
-p_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-THCA' & data_type == 'Protein Expression Quantification' & data_format == 'tsv') |> filter(access == 'open') |> manifest()
-
-for(i in seq(20,24))
-{
-uid<-0;uid<-as.character(p_3[i,1])
-gdcdata(uid)
-}
diff --git a/R/tcga_slides.R b/R/tcga_slides.R
deleted file mode 100644
index f260f3d..0000000
--- a/R/tcga_slides.R
+++ /dev/null
@@ -1,25 +0,0 @@
-library(dplyr)
-library(tibble)
-library(GenomicDataCommons)
-
-#specify project name
-#q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-KIRC' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
-q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-BRCA' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
-#locate open data
-open_access<-which(q_2$access=="open")
-
-#select files
-#for(i in length(open_access))
-#for(i in seq(3,5))
-#for(i in seq(20,24))
-for(i in seq(200,202))
-{
-uid<-0;uid<-as.character(q_2[open_access[i],1])
-gdcdata(uid)
-}
-
-
-######alternatively, use filter 
-#both approaches should list same files
-q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-BRCA' & data_type == 'Slide Image' & data_format == 'svs') |> filter(access == 'open') |>  manifest()
-
diff --git a/R/tcga_slides_1.R b/R/tcga_slides_1.R
deleted file mode 100644
index 057547b..0000000
--- a/R/tcga_slides_1.R
+++ /dev/null
@@ -1,27 +0,0 @@
-library(dplyr)
-library(tibble)
-library(GenomicDataCommons)
-
-q_2 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-COAD' & data_type == 'Slide Image' & data_format == 'svs') |> manifest()
-#locate open data
-open_access<-which(q_2$access=="open")
-
-#for(i in length(open_access))
-#for(i in seq(3,5))
-#for(i in seq(20,24))
-for(i in seq(200,202))
-{
-uid<-0;uid<-as.character(q_2[open_access[i],1])
-gdcdata(uid)
-}
-
-
-#or sanity check
-
-q_3 = files() |> GenomicDataCommons::filter(cases.project.project_id == 'TCGA-COAD' & data_type == 'Slide Image' & data_format == 'svs') |> filter(access == 'open') |> manifest()
-
-for(i in seq(2,4))
-{
-uid<-0;uid<-as.character(q_3[i,1])
-gdcdata(uid)
-}

From 34b4fa814436ed19adc36812548d3142269cec3c Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Wed, 12 Mar 2025 17:43:18 -0400
Subject: [PATCH 09/11] update overview.Rmd

---
 vignettes/overview.Rmd                   |  72 +-
 vignettes/overviewGenomicDataCommons.Rmd | 811 -----------------------
 2 files changed, 39 insertions(+), 844 deletions(-)
 delete mode 100644 vignettes/overviewGenomicDataCommons.Rmd

diff --git a/vignettes/overview.Rmd b/vignettes/overview.Rmd
index 17a1114..4269cda 100644
--- a/vignettes/overview.Rmd
+++ b/vignettes/overview.Rmd
@@ -118,6 +118,12 @@ stopifnot(GenomicDataCommons::status()$status=="OK")
 
 
 ## Find data
+Please use a fresh R session to minimise package conflicts arising from identical function names.
+For example the functions filter(), results() are available with R packages dplyr, GenomicDataCommons . Instead consider using the R package conflicted.
+Example usage
+conflicts_prefer(dplyr::filter())
+conflicts_prefer(GenomicDataCommons::filter)
+conflicts_prefer(stats :: filter)
 
 The following code builds a `manifest` that can be used to guide the
 download of raw data. Here, filtering finds gene expression files
@@ -164,8 +170,8 @@ the `gdc_clinical()` function will return a list of four `tibble`s.
 - main
 
 ```{r gdc_clinical}
-case_ids = cases() |> results(size=10) |> ids()
-clindat = gdc_clinical(case_ids)
+case_ids <- cases() |> results(size=10) |> ids()
+clindat <- gdc_clinical(case_ids)
 names(clindat)
 ```
 
@@ -183,9 +189,9 @@ be all that is needed, but the API and `r Biocpkg("GenomicDataCommons")` package
 make much flexibility if fine-tuning is required. 
 
 ```{r metadataQS}
-expands = c("diagnoses","annotations",
+expands <- c("diagnoses","annotations",
              "demographic","exposures")
-clinResults = cases() |>
+clinResults <- cases() |>
     GenomicDataCommons::select(NULL) |>
     GenomicDataCommons::expand(expands) |>
     results(size=50)
@@ -287,7 +293,7 @@ functions that each create `GDCQuery` objects (actually, specific subclasses of
 - `annotations()`
 
 ```{r projectquery}
-pquery = projects()
+pquery <- projects()
 ```
 
 The `pquery` object is now an object of (S3) class, `GDCQuery` (and
@@ -326,16 +332,16 @@ Note that we have not set any filters, so a `count()` here will represent all
 the project records publicly available at the GDC in the "default" archive"
 
 ```{r pquerycount}
-pcount = count(pquery)
+pcount <- count(pquery)
 # or
-pcount = pquery |> count()
+pcount <- pquery |> count()
 pcount
 ```
 
 The `results()` method will fetch actual results.
 
 ```{r pqueryresults}
-presults = pquery |> results()
+presults <- pquery |> results()
 ```
 These results are
 returned from the GDC in [JSON](http://www.json.org/) format and
@@ -356,7 +362,7 @@ size is probably warranted before calling `results_all()`
 
 ```{r presultsall}
 length(ids(presults))
-presults = pquery |> results_all()
+presults <- pquery |> results_all()
 length(ids(presults))
 # includes all records
 length(ids(presults)) == count(pquery)
@@ -401,11 +407,11 @@ the dplyr `select()` verb that limits from already-present fields. We
 
 ```{r selectexample}
 # Default fields here
-qcases = cases()
+qcases <- cases()
 qcases$fields
 # set up query to use ALL available fields
 # Note that checking of fields is done by select()
-qcases = cases() |> GenomicDataCommons::select(available_fields('cases'))
+qcases <- cases() |> GenomicDataCommons::select(available_fields('cases'))
 head(qcases$fields)
 ```
 
@@ -428,7 +434,7 @@ tibbles).
 
 ```{r aggexample}
 # total number of files of a specific type
-res = files() |> facet(c('type','data_type')) |> aggregations()
+res <- files() |> facet(c('type','data_type')) |> aggregations()
 res$type
 ```
 
@@ -454,7 +460,7 @@ For the user, these details will not be too important except to note that a
 filter expression must begin with a "~".
 
 ```{r allfilesunfiltered}
-qfiles = files()
+qfiles <- files()
 qfiles |> count() # all files
 ```
 To limit the file type, we can refer back to the
@@ -463,7 +469,7 @@ the file field "type". For example, to filter file results to only
 "gene_expression" files, we simply specify a filter.
 
 ```{r onlyGeneExpression}
-qfiles = files() |> filter( type == 'gene_expression')
+qfiles <- files() |> filter( type == 'gene_expression')
 # here is what the filter looks like after translation
 str(get_filter(qfiles))
 ```
@@ -495,7 +501,7 @@ note that `TCGA-OV` is the correct project_id, not `TCGA-OVCA`. Note that
 filter and does not build on any previous filters*.
 
 ```{r filtfinal}
-qfiles = files() |>
+qfiles <- files() |>
     filter( cases.project.project_id == 'TCGA-OV' & type == 'gene_expression')
 str(get_filter(qfiles))
 qfiles |> count()
@@ -507,7 +513,7 @@ accomplish the same effect as multiple `&` conditionals. The `count()`
 below is equivalent to the `&` filtering done above.
 
 ```{r filtChain}
-qfiles2 = files() |>
+qfiles2 <- files() |>
     filter( cases.project.project_id == 'TCGA-OV') |> 
     filter( type == 'gene_expression') 
 qfiles2 |> count()
@@ -520,7 +526,7 @@ Generating a manifest for bulk downloads is as
 simple as asking for the manifest from the current query.
 
 ```{r filtAndManifest}
-manifest_df = qfiles |> manifest()
+manifest_df <- qfiles |> manifest()
 head(manifest_df)
 ```
 
@@ -531,11 +537,11 @@ that the field "analysis.workflow_type" has the appropriate filter criteria.
 
 
 ```{r filterForSTARCounts}
-qfiles = files() |> filter( ~ cases.project.project_id == 'TCGA-OV' &
+qfiles <- files() |> filter( ~ cases.project.project_id == 'TCGA-OV' &
                             type == 'gene_expression' &
                             access == "open" &
                             analysis.workflow_type == 'STAR - Counts')
-manifest_df = qfiles |> manifest()
+manifest_df <- qfiles |> manifest()
 nrow(manifest_df)
 ```
 
@@ -577,7 +583,7 @@ be stored in one of three ways (resolved in this order):
 As a concrete example:
 
 ```{r authenNoRun, eval=FALSE}
-token = gdc_token()
+token <- gdc_token()
 transfer(...,token=token)
 # or
 transfer(...,token=get_token())
@@ -594,7 +600,7 @@ ids. A simple way of producing such a vector is to produce a
 contain file ids.
 
 ```{r singlefileDL}
-fnames = gdcdata(manifest_df$id[1:2],progress=FALSE)
+fnames <- gdcdata(manifest_df$id[1:2],progress=FALSE)
 
 ```
 
@@ -614,7 +620,7 @@ in parallel.
 ```{r bulkDL, eval=FALSE}
 # Requires gcd_client command-line utility to be isntalled
 # separately. 
-fnames = gdcdata(manifest_df$id[3:10], access_method = 'client')
+fnames <- gdcdata(manifest_df$id[3:10], access_method = 'client')
 ```
 
 
@@ -627,7 +633,7 @@ fnames = gdcdata(manifest_df$id[3:10], access_method = 'client')
 ### How many cases are there per project_id?
 
 ```{r casesPerProject}
-res = cases() |> facet("project.project_id") |> aggregations()
+res <- cases() |> facet("project.project_id") |> aggregations()
 head(res)
 library(ggplot2)
 ggplot(res$project.project_id,aes(x = key, y = doc_count)) +
@@ -653,7 +659,7 @@ cases() |> filter(~ project.program.name=='TCGA') |> count()
 # The need to do the "&" here is a requirement of the
 # current version of the GDC API. I have filed a feature
 # request to remove this requirement.
-resp = cases() |> filter(~ project.project_id=='TCGA-BRCA' &
+resp <- cases() |> filter(~ project.project_id=='TCGA-BRCA' &
                               project.project_id=='TCGA-BRCA' ) |>
     facet('samples.sample_type') |> aggregations()
 resp$samples.sample_type
@@ -665,12 +671,12 @@ resp$samples.sample_type
 # The need to do the "&" here is a requirement of the
 # current version of the GDC API. I have filed a feature
 # request to remove this requirement.
-resp = cases() |> filter(~ project.project_id=='TCGA-BRCA' &
+resp <- cases() |> filter(~ project.project_id=='TCGA-BRCA' &
                               samples.sample_type=='Solid Tissue Normal') |>
     GenomicDataCommons::select(c(default_fields(cases()),'samples.sample_type')) |>
     response_all()
 count(resp)
-res = resp |> results()
+res <- resp |> results()
 str(res[1],list.len=6)
 head(ids(resp))
 ```
@@ -721,7 +727,7 @@ cases() |>
 ### How many of each type of file are available?
 
 ```{r filesVCFCount}
-res = files() |> facet('type') |> aggregations()
+res <- files() |> facet('type') |> aggregations()
 res$type
 ggplot(res$type,aes(x = key,y = doc_count)) + geom_bar(stat='identity') +
     theme(axis.text.x = element_text(angle = 45, hjust = 1))
@@ -730,13 +736,13 @@ ggplot(res$type,aes(x = key,y = doc_count)) + geom_bar(stat='identity') +
 ### Find gene-level RNA-seq quantification files for GBM
 
 ```{r filesRNAseqGeneGBM}
-q = files() |>
+q <- files() |>
     GenomicDataCommons::select(available_fields('files')) |>
     filter(~ cases.project.project_id=='TCGA-GBM' &
                data_type=='Gene Expression Quantification')
 q |> facet('analysis.workflow_type') |> aggregations()
 # so need to add another filter
-file_ids = q |> filter(~ cases.project.project_id=='TCGA-GBM' &
+file_ids <- q |> filter(~ cases.project.project_id=='TCGA-GBM' &
                             data_type=='Gene Expression Quantification' &
                             analysis.workflow_type == 'STAR - Counts') |>
     GenomicDataCommons::select('file_id') |>
@@ -752,20 +758,20 @@ file_ids = q |> filter(~ cases.project.project_id=='TCGA-GBM' &
 and for vignette building**.
 
 ```{r filesRNAseqGeneGBMforBAM}
-q = files() |>
+q <- files() |>
     GenomicDataCommons::select(available_fields('files')) |>
     filter(~ cases.project.project_id == 'TCGA-GBM' &
                data_type == 'Aligned Reads' &
                experimental_strategy == 'RNA-Seq' &
                data_format == 'BAM')
-file_ids = q |> response_all() |> ids()
+file_ids <- q |> response_all() |> ids()
 ```
 
 
 ```{r slicing10, eval=FALSE}
-bamfile = slicing(file_ids[1],regions="chr12:6534405-6538375",token=gdc_token())
+bamfile <- slicing(file_ids[1],regions="chr12:6534405-6538375",token=gdc_token())
 library(GenomicAlignments)
-aligns = readGAlignments(bamfile)
+aligns <- readGAlignments(bamfile)
 ```
 
 # Troubleshooting
diff --git a/vignettes/overviewGenomicDataCommons.Rmd b/vignettes/overviewGenomicDataCommons.Rmd
deleted file mode 100644
index 4269cda..0000000
--- a/vignettes/overviewGenomicDataCommons.Rmd
+++ /dev/null
@@ -1,811 +0,0 @@
----
-title: "The GenomicDataCommons Package"
-author: "Sean Davis & Martin Morgan"
-date: "`r format(Sys.Date(), '%A, %B %d, %Y')`"
-always_allow_html: yes
-output:
-  BiocStyle::html_document:
-    df_print: paged
-    toc_float: true
-abstract: >
-  The National Cancer Institute (NCI) has established
-  the [Genomic Data Commons](https://gdc.nci.nih.gov/) (GDC). The GDC
-  provides the cancer research community with an open and unified
-  repository for sharing and accessing data across numerous cancer
-  studies and projects via a high-performance data transfer and query
-  infrastructure.  The *GenomicDataCommons* Bioconductor package
-  provides basic infrastructure for querying, accessing, and mining
-  genomic datasets available from the GDC. We expect that the
-  Bioconductor developer and the larger bioinformatics communities will
-  build on the *GenomicDataCommons* package to add higher-level
-  functionality and expose cancer genomics data to the plethora of
-  state-of-the-art bioinformatics methods available in Bioconductor.
-
-vignette: >
-  %\VignetteIndexEntry{Introduction to Accessing the NCI Genomic Data Commons}
-  %\VignetteEngine{knitr::rmarkdown}
-  %\VignetteEncoding{UTF-8}
----
-
-```{r init, results='hide', echo=FALSE, warning=FALSE, message=FALSE}
-library(knitr)
-opts_chunk$set(warning=FALSE, message=FALSE)
-BiocStyle::markdown()
-```
-
-
-# What is the GDC?
-
-From the [Genomic Data Commons (GDC) website](https://gdc.cancer.gov/about-gdc):
-
-> The National Cancer Institute's (NCI's) Genomic Data Commons (GDC) is
-a data sharing platform that promotes precision medicine in
-oncology. It is not just a database or a tool; it is an expandable
-knowledge network supporting the import and standardization of genomic
-and clinical data from cancer research programs.
-> The GDC contains NCI-generated data from some of the largest and most
-comprehensive cancer genomic datasets, including The Cancer Genome
-Atlas (TCGA) and Therapeutically Applicable Research to Generate
-Effective Therapies (TARGET). For the first time, these datasets have
-been harmonized using a common set of bioinformatics pipelines, so
-that the data can be directly compared.
-> As a growing knowledge system for cancer, the GDC also enables
-researchers to submit data, and harmonizes these data for import into
-the GDC. As more researchers add clinical and genomic data to the GDC,
-it will become an even more powerful tool for making discoveries about
-the molecular basis of cancer that may lead to better care for
-patients.
-
-The
-[data model for the GDC is complex](https://gdc.cancer.gov/developers/gdc-data-model/gdc-data-model-components),
-but it worth a quick overview and a graphical representation is included here. 
-
-![The data model is encoded as a
-so-called property graph. Nodes represent entities such as Projects,
-Cases, Diagnoses, Files (various kinds), and Annotations. The
-relationships between these entities are maintained as edges.  Both
-nodes and edges may have Properties that supply instance details. ](all_nodes_040318.png)
-
- The
-GDC API exposes these nodes and edges in a somewhat simplified set
-of
-[RESTful](https://en.wikipedia.org/wiki/Representational_state_transfer) endpoints.
-
-# Quickstart
-
-This quickstart section is just meant to show basic
-functionality. More details of functionality are included further on
-in this vignette and in function-specific help.
-
-This software is available at Bioconductor.org and can be downloaded via
-`BiocManager::install`.
-
-To report bugs or problems, either
-[submit a new issue](https://github.com/Bioconductor/GenomicDataCommons/issues)
-or submit a `bug.report(package='GenomicDataCommons')` from within R (which
-will redirect you to the new issue on GitHub).
-
-## Installation
-
-Installation can be achieved via Bioconductor's `BiocManager` package.
-
-```{r install_bioc, eval=FALSE}
-if (!require("BiocManager"))
-    install.packages("BiocManager")
-BiocManager::install('GenomicDataCommons')
-```
-
-```{r libraries, message=FALSE}
-library(GenomicDataCommons)
-```
-
-## Check connectivity and status
-
-The `r Biocpkg("GenomicDataCommons")` package relies on having network
-connectivity. In addition, the NCI GDC API must also be operational
-and not under maintenance. Checking `status` can be used to check this
-connectivity and functionality.
-
-```{r statusQS}
-GenomicDataCommons::status()
-```
-
-And to check the status in code:
-
-```{r statusCheck}
-stopifnot(GenomicDataCommons::status()$status=="OK")
-```
-
-
-## Find data
-Please use a fresh R session to minimise package conflicts arising from identical function names.
-For example the functions filter(), results() are available with R packages dplyr, GenomicDataCommons . Instead consider using the R package conflicted.
-Example usage
-conflicts_prefer(dplyr::filter())
-conflicts_prefer(GenomicDataCommons::filter)
-conflicts_prefer(stats :: filter)
-
-The following code builds a `manifest` that can be used to guide the
-download of raw data. Here, filtering finds gene expression files
-quantified as raw counts using `STAR` from ovarian cancer patients.
-
-```{r manifest}
-ge_manifest <- files() |>
-    filter( cases.project.project_id == 'TCGA-OV') |> 
-    filter( type == 'gene_expression' ) |>
-    filter( analysis.workflow_type == 'STAR - Counts')  |>
-    manifest()
-head(ge_manifest)
-```
-
-## Download data
-
-After  the `r nrow(ge_manifest)` gene expression files
-specified in the query above. Using multiple processes to do the download very
-significantly speeds up the transfer in many cases.  On a standard 1Gb
-connection, the following completes in about 30 seconds. The first time the 
-data are downloaded, R will ask to create a cache directory (see `?gdc_cache`
-for details of setting and interacting with the cache). Resulting
-downloaded files will be stored in the cache directory. Future access to 
-the same files will be directly from the cache, alleviating multiple downloads.
-
-```{r downloadQS, eval=FALSE}
-fnames <- lapply(ge_manifest$id[1:20], gdcdata)
-```
-
-If the download had included controlled-access data, the download above would
-have needed to include a `token`.  Details are available in
-[the authentication section below](#authentication).
-
-## Metadata queries
-
-### Clinical data
-
-Accessing clinical data is a very common task. Given a set of `case_ids`,
-the `gdc_clinical()` function will return a list of four `tibble`s. 
-
-- demographic
-- diagnoses
-- exposures
-- main
-
-```{r gdc_clinical}
-case_ids <- cases() |> results(size=10) |> ids()
-clindat <- gdc_clinical(case_ids)
-names(clindat)
-```
-
-```{r clinData}
-head(clindat[["main"]])
-head(clindat[["diagnoses"]])
-```
-
-### General metadata queries
-
-The `r Biocpkg("GenomicDataCommons")` package can access the significant 
-clinical, demographic, biospecimen, and annotation information 
-contained in the NCI GDC. The `gdc_clinical()` function will often
-be all that is needed, but the API and `r Biocpkg("GenomicDataCommons")` package
-make much flexibility if fine-tuning is required. 
-
-```{r metadataQS}
-expands <- c("diagnoses","annotations",
-             "demographic","exposures")
-clinResults <- cases() |>
-    GenomicDataCommons::select(NULL) |>
-    GenomicDataCommons::expand(expands) |>
-    results(size=50)
-str(clinResults[[1]],list.len=6)
-# or listviewer::jsonedit(clinResults)
-```
-
-# Basic design
-
-This package design is meant to have some similarities to the "hadleyverse"
-approach of dplyr. Roughly, the functionality for finding and accessing files
-and metadata can be divided into:
-
-1. Simple query constructors based on GDC API endpoints.
-2. A set of verbs that when applied, adjust filtering, field selection, and
-faceting (fields for aggregation) and result in a new query object (an
-endomorphism)
-3. A set of verbs that take a query and return results from the GDC
-
-In addition, there are exhiliary functions for asking the GDC API for
-information about available and default fields, slicing BAM files, and
-downloading actual data files.  Here is an overview of functionality[^1].
-
-
-- Creating a query
-    - `projects()`
-    - `cases()`
-    - `files()`
-    - `annotations()`
-- Manipulating a query
-    - `filter()`
-    - `facet()`
-    - `select()`
-- Introspection on the GDC API fields
-    - `mapping()`
-    - `available_fields()`
-    - `default_fields()`
-    - `grep_fields()`
-    - `available_values()`
-    - `available_expand()`
-- Executing an API call to retrieve query results
-    - `results()`
-    - `count()`
-    - `response()`
-- Raw data file downloads
-    - `gdcdata()`
-    - `transfer()`
-    - `gdc_client()`
-- Summarizing and aggregating field values (faceting)
-    - `aggregations()`
-- Authentication
-    - `gdc_token()`
-- BAM file slicing
-    - `slicing()`
-
-[^1]: See individual function and methods documentation for specific details.
-
-
-# Usage
-
-There are two main classes of operations when working with the NCI GDC.
-
-1. [Querying metadata and finding data files](#querying-metadata) (e.g., finding
-all gene expression quantifications data files for all colon cancer patients).
-2. [Transferring raw or processed data](#datafile-access-and-download) from the
-GDC to another computer (e.g., downloading raw or processed data)
-
-Both classes of operation are reviewed in detail in the following sections.
-
-## Querying metadata
-
-Vast amounts of metadata about cases (patients, basically), files, projects, and
-so-called annotations are available via the NCI GDC API. Typically, one will
-want to query metadata to either focus in on a set of files for download or
-transfer *or* to perform so-called aggregations (pivot-tables, facets, similar
-to the R `table()` functionality).
-
-Querying metadata starts with [creating a "blank" query](#creating-a-query). One
-will often then want to [`filter`](#filtering) the query to limit results prior
-to [retrieving results](#retrieving-results). The GenomicDataCommons package has
-[helper functions for listing fields](#fields-and-values) that are available for
-filtering.
-
-In addition to fetching results, the GDC API allows
-[faceting, or aggregating,](#facets-and-aggregation), useful for compiling
-reports, generating dashboards, or building user interfaces to GDC data (see GDC
-web query interface for a non-R-based example).
-
-### Creating a query
-
-A query of the GDC starts its life in R. Queries follow the four metadata
-endpoints available at the GDC.  In particular, there are four convenience
-functions that each create `GDCQuery` objects (actually, specific subclasses of
-`GDCQuery`):
-
-- `projects()`
-- `cases()`
-- `files()`
-- `annotations()`
-
-```{r projectquery}
-pquery <- projects()
-```
-
-The `pquery` object is now an object of (S3) class, `GDCQuery` (and
-`gdc_projects` and `list`). The object contains the following elements:
-
-- fields: This is a character vector of the fields that will be returned when we
-[retrieve data](#retrieving-results). If no fields are specified to, for
-example, the `projects()` function, the default fields from the GDC are used
-(see `default_fields()`)
-- filters: This will contain results after calling the
-[`filter()` method](#filtering) and will be used to filter results on
-[retrieval](#retrieving-results).
-- facets: A character vector of field names that will be used for
-[aggregating data](#facets-and-aggregation) in a call to `aggregations()`.
-- token: A character(1) token from the GDC. See
-[the authentication section](#authentication) for details, but note that, in
-general, the token is not necessary for metadata query and retrieval, only for
-actual data download.
-
-Looking at the actual object (get used to using `str()`!), note that the query
-contains no results.
-
-```{r pquery}
-str(pquery)
-```
-### Retrieving results
-
-[[ GDC pagination documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#size-and-from)
-
-[[ GDC sorting documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#sort)
-
-With a query object available, the next step is to retrieve results from the
-GDC. The GenomicDataCommons package.  The most basic type of results we can get
-is a simple `count()` of records available that satisfy the filter criteria.
-Note that we have not set any filters, so a `count()` here will represent all
-the project records publicly available at the GDC in the "default" archive"
-
-```{r pquerycount}
-pcount <- count(pquery)
-# or
-pcount <- pquery |> count()
-pcount
-```
-
-The `results()` method will fetch actual results.
-
-```{r pqueryresults}
-presults <- pquery |> results()
-```
-These results are
-returned from the GDC in [JSON](http://www.json.org/) format and
-converted into a (potentially nested) list in R. The `str()` method is useful
-for taking a quick glimpse of the data.
-
-```{r presultsstr}
-str(presults)
-```
-
-A default of only 10 records are returned. We can use the `size` and `from`
-arguments to `results()` to either page through results or to change the number
-of results. Finally, there is a convenience method, `results_all()` that will
-simply fetch all the available results given a query. Note that `results_all()`
-may take a long time and return HUGE result sets if not used carefully. Use of a
-combination of `count()` and `results()` to get a sense of the expected data
-size is probably warranted before calling `results_all()`
-
-```{r presultsall}
-length(ids(presults))
-presults <- pquery |> results_all()
-length(ids(presults))
-# includes all records
-length(ids(presults)) == count(pquery)
-```
-
-Extracting subsets of
-results or manipulating the results into a more conventional R data
-structure is not easily generalizable.  However,
-the
-[purrr](https://github.com/hadley/purrr),
-[rlist](https://renkun.me/rlist/),
-and [data.tree](https://cran.r-project.org/web/packages/data.tree/vignettes/data.tree.html) packages
-are all potentially of interest for manipulating complex, nested list
-structures. For viewing the results in an interactive viewer, consider the
-[listviewer](https://github.com/timelyportfolio/listviewer) package.
-
-
-### Fields and Values
-
-[[ GDC `fields` documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#fields)
-
-Central to querying and retrieving data from the GDC is the ability to specify
-which fields to return, filtering by fields and values, and faceting or
-aggregating. The GenomicDataCommons package includes two simple functions,
-`available_fields()` and `default_fields()`. Each can operate on a character(1)
-endpoint name ("cases", "files", "annotations", or "projects") or a `GDCQuery`
-object.
-
-```{r defaultfields}
-default_fields('files')
-# The number of fields available for files endpoint
-length(available_fields('files'))
-# The first few fields available for files endpoint
-head(available_fields('files'))
-```
-
-The fields to be returned by a query can be specified following a similar
-paradigm to that of the dplyr package. The `select()` function is a verb that
-resets the fields slot of a `GDCQuery`; note that this is not quite analogous to
-the dplyr `select()` verb that limits from already-present fields. We
-*completely replace* the fields when using `select()` on a `GDCQuery`.
-
-```{r selectexample}
-# Default fields here
-qcases <- cases()
-qcases$fields
-# set up query to use ALL available fields
-# Note that checking of fields is done by select()
-qcases <- cases() |> GenomicDataCommons::select(available_fields('cases'))
-head(qcases$fields)
-```
-
-Finding fields of interest is such a common operation that the
-GenomicDataCommons includes the `grep_fields()` function.
-See the appropriate help pages for details.
-
-### Facets and aggregation
-
-[[ GDC `facet` documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#facets)
-
-The GDC API offers a feature known as aggregation or faceting. By
-specifying one or more fields (of appropriate type), the GDC can
-return to us a count of the number of records matching each potential
-value. This is similar to the R `table` method. Multiple fields can be
-returned at once, but the GDC API does not have a cross-tabulation
-feature; all aggregations are only on one field at a time. Results of
-`aggregation()` calls come back as a list of data.frames (actually,
-tibbles).
-
-```{r aggexample}
-# total number of files of a specific type
-res <- files() |> facet(c('type','data_type')) |> aggregations()
-res$type
-```
-
-Using `aggregations()` is an also easy way to learn the contents of individual
-fields and forms the basis for faceted search pages.
-
-### Filtering
-
-[[ GDC `filtering` documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#filters-specifying-the-query)
-
-The GenomicDataCommons package uses a form of non-standard evaluation to specify
-R-like queries that are then translated into an R list. That R list is, upon
-calling a method that fetches results from the GDC API, translated into the
-appropriate JSON string. The R expression uses the formula interface as
-suggested by Hadley Wickham in his [vignette on non-standard evaluation](https://cran.r-project.org/web/packages/dplyr/vignettes/nse.html)
-
-> It’s best to use a formula because a formula captures both the expression to
-evaluate and the environment where the evaluation occurs. This is important if
-the expression is a mixture of variables in a data frame and objects in the
-local environment [for example].
-
-For the user, these details will not be too important except to note that a
-filter expression must begin with a "~".
-
-```{r allfilesunfiltered}
-qfiles <- files()
-qfiles |> count() # all files
-```
-To limit the file type, we can refer back to the
-[section on faceting](#facets-and-aggregation) to see the possible values for
-the file field "type". For example, to filter file results to only
-"gene_expression" files, we simply specify a filter.
-
-```{r onlyGeneExpression}
-qfiles <- files() |> filter( type == 'gene_expression')
-# here is what the filter looks like after translation
-str(get_filter(qfiles))
-```
-
-What if we want to create a filter based on the project ('TCGA-OVCA', for
-example)? Well, we have a couple of possible ways to discover available fields.
-The first is based on base R functionality and some intuition.
-
-```{r filtAvailFields}
-grep('pro',available_fields('files'),value=TRUE) |> 
-    head()
-```
-
-Interestingly, the project information is "nested" inside the case. We don't
-need to know that detail other than to know that we now have a few potential
-guesses for where our information might be in the files records.  We need to
-know where because we need to construct the appropriate filter.
-
-```{r filtProgramID}
-files() |> 
-    facet('cases.project.project_id') |> 
-    aggregations() |> 
-    head()
-```
-
-We note that `cases.project.project_id` looks like it is a good fit. We also
-note that `TCGA-OV` is the correct project_id, not `TCGA-OVCA`. Note that
-*unlike with dplyr and friends, the `filter()` method here **replaces** the
-filter and does not build on any previous filters*.
-
-```{r filtfinal}
-qfiles <- files() |>
-    filter( cases.project.project_id == 'TCGA-OV' & type == 'gene_expression')
-str(get_filter(qfiles))
-qfiles |> count()
-```
-
-Asking for a `count()` of results given these new filter criteria gives `r
-qfiles |> count()` results. Filters can be chained (or nested) to 
-accomplish the same effect as multiple `&` conditionals. The `count()`
-below is equivalent to the `&` filtering done above.
-
-```{r filtChain}
-qfiles2 <- files() |>
-    filter( cases.project.project_id == 'TCGA-OV') |> 
-    filter( type == 'gene_expression') 
-qfiles2 |> count()
-(qfiles |> count()) == (qfiles2 |> count()) #TRUE
-```
-
-
-
-Generating a manifest for bulk downloads is as
-simple as asking for the manifest from the current query.
-
-```{r filtAndManifest}
-manifest_df <- qfiles |> manifest()
-head(manifest_df)
-```
-
-Note that we might still not be quite there. Looking at filenames, there are
-suspiciously named files that might include "FPKM", "FPKM-UQ", or "counts".
-Another round of `grep` and `available_fields`, looking for "type" turned up
-that the field "analysis.workflow_type" has the appropriate filter criteria.
-
-
-```{r filterForSTARCounts}
-qfiles <- files() |> filter( ~ cases.project.project_id == 'TCGA-OV' &
-                            type == 'gene_expression' &
-                            access == "open" &
-                            analysis.workflow_type == 'STAR - Counts')
-manifest_df <- qfiles |> manifest()
-nrow(manifest_df)
-```
-
-The GDC Data Transfer Tool can be used (from R, `transfer()` or from the
-command-line) to orchestrate high-performance, restartable transfers of all the
-files in the manifest. See [the bulk downloads section](bulk-downloads) for
-details.
-
-
-## Authentication
-
-[[ GDC authentication documentation ]](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#facets)
-
-The GDC offers both "controlled-access" and "open" data. As of this
-writing, only data stored as files is "controlled-access"; that is,
-metadata accessible via the GDC is all "open" data and some files are
-"open" and some are "controlled-access". Controlled-access data are
-only available
-after
-[going through the process of obtaining access.](https://gdc.cancer.gov/access-data/obtaining-access-controlled-data)
-
-After controlled-access to one or more datasets has been granted,
-logging into the GDC web portal will allow you
-to
-[access a GDC authentication token](https://docs.gdc.cancer.gov/Data_Portal/Users_Guide/Authentication/#gdc-authentication-tokens),
-which can be downloaded and then used to access available
-controlled-access data via the GenomicDataCommons package.
-
-The GenomicDataCommons uses authentication tokens only for downloading
-data (see `transfer` and `gdcdata` documentation). The package
-includes a helper function, `gdc_token`, that looks for the token to
-be stored in one of three ways (resolved in this order):
-
-1. As a string stored in the environment variable, `GDC_TOKEN`
-2. As a file, stored in the file named by the environment variable,
-   `GDC_TOKEN_FILE`
-3. In a file in the user home directory, called `.gdc_token`
-
-As a concrete example:
-
-```{r authenNoRun, eval=FALSE}
-token <- gdc_token()
-transfer(...,token=token)
-# or
-transfer(...,token=get_token())
-```
-
-
-## Datafile access and download
-
-### Data downloads via the GDC API
-
-The `gdcdata` function takes a character vector of one or more file
-ids. A simple way of producing such a vector is to produce a
-`manifest` data frame and then pass in the first column, which will
-contain file ids.
-
-```{r singlefileDL}
-fnames <- gdcdata(manifest_df$id[1:2],progress=FALSE)
-
-```
-
-Note that for controlled-access data, a
-GDC [authentication token](#authentication) is required. Using the
-`BiocParallel` package may be useful for downloading in parallel,
-particularly for large numbers of smallish files.
-
-### Bulk downloads
-
-The bulk download functionality is only efficient (as of v1.2.0 of the
-GDC Data Transfer Tool) for relatively large files, so use this
-approach only when transferring BAM files or larger VCF files, for
-example. Otherwise, consider using the approach shown above, perhaps
-in parallel.
-
-```{r bulkDL, eval=FALSE}
-# Requires gcd_client command-line utility to be isntalled
-# separately. 
-fnames <- gdcdata(manifest_df$id[3:10], access_method = 'client')
-```
-
-
-### BAM slicing
-
-# Use Cases
-
-## Cases
-
-### How many cases are there per project_id?
-
-```{r casesPerProject}
-res <- cases() |> facet("project.project_id") |> aggregations()
-head(res)
-library(ggplot2)
-ggplot(res$project.project_id,aes(x = key, y = doc_count)) +
-    geom_bar(stat='identity') +
-    theme(axis.text.x = element_text(angle = 45, hjust = 1))
-```
-
-### How many cases are included in all TARGET projects?
-
-```{r casesInTCGA}
-cases() |> filter(~ project.program.name=='TARGET') |> count()
-```
-
-### How many cases are included in all TCGA projects?
-
-```{r casesInTARGET}
-cases() |> filter(~ project.program.name=='TCGA') |> count()
-```
-
-### What is the breakdown of sample types in TCGA-BRCA?
-
-```{r casesTCGABRCASampleTypes}
-# The need to do the "&" here is a requirement of the
-# current version of the GDC API. I have filed a feature
-# request to remove this requirement.
-resp <- cases() |> filter(~ project.project_id=='TCGA-BRCA' &
-                              project.project_id=='TCGA-BRCA' ) |>
-    facet('samples.sample_type') |> aggregations()
-resp$samples.sample_type
-```
-
-### Fetch all samples in TCGA-BRCA that use "Solid Tissue" as a normal.
-
-```{r casesTCGABRCASolidNormal}
-# The need to do the "&" here is a requirement of the
-# current version of the GDC API. I have filed a feature
-# request to remove this requirement.
-resp <- cases() |> filter(~ project.project_id=='TCGA-BRCA' &
-                              samples.sample_type=='Solid Tissue Normal') |>
-    GenomicDataCommons::select(c(default_fields(cases()),'samples.sample_type')) |>
-    response_all()
-count(resp)
-res <- resp |> results()
-str(res[1],list.len=6)
-head(ids(resp))
-```
-
-### Get all TCGA case ids that are female
-
-```{r casesFemaleTCGA}
-cases() |>
-  GenomicDataCommons::filter(~ project.program.name == 'TCGA' &
-    "cases.demographic.gender" %in% "female") |>
-      GenomicDataCommons::results(size = 4) |>
-        ids()
-```
-
-### Get all TCGA-COAD case ids that are NOT female
-
-```{r notFemaleTCGACOAD}
-cases() |>
-  GenomicDataCommons::filter(~ project.project_id == 'TCGA-COAD' &
-    "cases.demographic.gender" %exclude% "female") |>
-      GenomicDataCommons::results(size = 4) |>
-        ids()
-```
-
-### Get all TCGA cases that are missing gender
-
-```{r missingGenderTCGA}
-cases() |>
-  GenomicDataCommons::filter(~ project.program.name == 'TCGA' &
-    missing("cases.demographic.gender")) |>
-      GenomicDataCommons::results(size = 4) |>
-        ids()
-```
-
-### Get all TCGA cases that are NOT missing gender
-
-```{r notMissingGenderTCGA}
-cases() |>
-  GenomicDataCommons::filter(~ project.program.name == 'TCGA' &
-    !missing("cases.demographic.gender")) |>
-      GenomicDataCommons::results(size = 4) |>
-        ids()
-```
-
-
-## Files
-
-### How many of each type of file are available?
-
-```{r filesVCFCount}
-res <- files() |> facet('type') |> aggregations()
-res$type
-ggplot(res$type,aes(x = key,y = doc_count)) + geom_bar(stat='identity') +
-    theme(axis.text.x = element_text(angle = 45, hjust = 1))
-```
-
-### Find gene-level RNA-seq quantification files for GBM
-
-```{r filesRNAseqGeneGBM}
-q <- files() |>
-    GenomicDataCommons::select(available_fields('files')) |>
-    filter(~ cases.project.project_id=='TCGA-GBM' &
-               data_type=='Gene Expression Quantification')
-q |> facet('analysis.workflow_type') |> aggregations()
-# so need to add another filter
-file_ids <- q |> filter(~ cases.project.project_id=='TCGA-GBM' &
-                            data_type=='Gene Expression Quantification' &
-                            analysis.workflow_type == 'STAR - Counts') |>
-    GenomicDataCommons::select('file_id') |>
-    response_all() |>
-    ids()
-```
-
-## Slicing
-
-### Get all BAM file ids from TCGA-GBM
-
-**I need to figure out how to do slicing reproducibly in a testing environment
-and for vignette building**.
-
-```{r filesRNAseqGeneGBMforBAM}
-q <- files() |>
-    GenomicDataCommons::select(available_fields('files')) |>
-    filter(~ cases.project.project_id == 'TCGA-GBM' &
-               data_type == 'Aligned Reads' &
-               experimental_strategy == 'RNA-Seq' &
-               data_format == 'BAM')
-file_ids <- q |> response_all() |> ids()
-```
-
-
-```{r slicing10, eval=FALSE}
-bamfile <- slicing(file_ids[1],regions="chr12:6534405-6538375",token=gdc_token())
-library(GenomicAlignments)
-aligns <- readGAlignments(bamfile)
-```
-
-# Troubleshooting
-
-## SSL connection errors
-
-* Symptom: Trying to connect to the API results in:
-```
-Error in curl::curl_fetch_memory(url, handle = handle) :
-SSL connect error
-```
-* Possible solutions: The [issue
-is that the GDC supports only recent security Transport Layer Security (TLS)](http://stackoverflow.com/a/42599546/459633),
-so the only known fix is to upgrade the system `openssl` to version
-1.0.1 or later.
-    * [[Mac OS]](https://github.com/Bioconductor/GenomicDataCommons/issues/35#issuecomment-284233510),
-    * [[Ubuntu]](http://askubuntu.com/a/434245)
-    * [[Centos/RHEL]](https://www.liquidweb.com/kb/update-and-patch-openssl-for-the-ccs-injection-vulnerability/).
-    After upgrading `openssl`, reinstall the R `curl` and `httr` packages.
-
-
-# sessionInfo()
-
-```{r sessionInfo}
-sessionInfo()
-```
-
-# Developer notes
-
-- The `S3` object-oriented programming paradigm is used.
-- We have adopted a functional programming style with functions and methods that
-often take an "object" as the first argument. This style lends itself to
-pipeline-style programming.
-- The GenomicDataCommons package uses the
-[alternative request format (POST)](https://docs.gdc.cancer.gov/API/Users_Guide/Search_and_Retrieval/#alternative-request-format)
-to allow very large request bodies.
-

From e205d62f455aab4e8b736d3db791168a22c35eb3 Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Wed, 19 Mar 2025 14:39:16 -0400
Subject: [PATCH 10/11] Add files via upload

---
 vignettes/get_projects.R | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 vignettes/get_projects.R

diff --git a/vignettes/get_projects.R b/vignettes/get_projects.R
new file mode 100644
index 0000000..d2cf7f4
--- /dev/null
+++ b/vignettes/get_projects.R
@@ -0,0 +1,39 @@
+library(GenomicDataCommons)
+
+
+#more than one possibility to get availble projects on the gdc portal
+#perhaps useful for anyone searching for gdc data to combine with existing laboratory samples
+gdc_proj<-projects()
+
+#get available keys to build queries
+#available_fields(gdc_proj)
+#facet(gdc_proj)
+
+####get available gdc projects
+res_1<-(gdc_proj |> facet('project_id') |> aggregations() )
+#save to file
+write.csv(res$project_id$key,file="project_id.txt",quote=FALSE,row.names=FALSE)
+
+#get gdc project names
+res_2<-(gdc_proj |> facet('program.name') |> aggregations() )
+#Save to file
+write.csv(res$program.name$key,file=='program.name.txt',quote=FALSE,row.names=FALSE)
+
+#addtional exp details
+res_3<-(gdc_proj |> facet('name') |> aggregations() )
+#get list components
+#names(res)
+write.csv(res$name["key"],file=='project_name.txt',quote=FALSE,row.names=FALSE)
+
+#get biospecimen, tissue site 
+res_4<-(gdc_proj |> facet('primary_site') |> aggregations() )
+
+write.csv(res$primary_site['key'],file=='primary_site.txt',quote=FALSE,row.names=FALSE)
+
+####use multiple fields
+res_5<-(gdc_proj |> facet(gdc_proj$fields[c(4:5,7)]) |> aggregations() )
+
+x<-list(N=res$name["key"],P=res$project_id["key"],T=res$primary_site["key"])
+
+#save to file , not a 1-1 map
+#cat(capture.output(print(x), file="test.txt"))

From 2531b93f320c3ef2ca0c633116093e533a766f1e Mon Sep 17 00:00:00 2001
From: bd4everyone <p1romita@yahoo.co.in>
Date: Thu, 27 Mar 2025 11:47:01 -0400
Subject: [PATCH 11/11] Add files via upload

---
 vignettes/ssm_examples.R | 51 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 vignettes/ssm_examples.R

diff --git a/vignettes/ssm_examples.R b/vignettes/ssm_examples.R
new file mode 100644
index 0000000..0d6f225
--- /dev/null
+++ b/vignettes/ssm_examples.R
@@ -0,0 +1,51 @@
+library(dplyr)
+library(tibble)
+library(GenomicDataCommons)
+
+#build queries to get simple somatic mutations
+q_primsite_1 = ssm_occurrences() |> GenomicDataCommons::filter(case.primary_site== 'Esophagus') |> GenomicDataCommons::expand(c('ssm','case')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+#add search criteria
+q_primsite_2 = ssm_occurrences() |> GenomicDataCommons::filter(case.primary_site== 'Esophagus' & case.lost_to_followup == 'No' ) |> GenomicDataCommons::expand(c('ssm','case')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+################
+q_consent = ssm_occurrences() |> GenomicDataCommons::filter(case.consent_type== 'Consent by Death') |> GenomicDataCommons::expand(c('ssm','case')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_consent,file="ssm_consentbyDeath.txt",row.names=FALSE,quote=FALSE)
+
+q_del = ssm_occurrences() |> GenomicDataCommons::filter(ssm.mutation_subtype == 'Small deletion') |> GenomicDataCommons::expand(c('ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_del,file="ssm_subtypeDeletions.txt",row.names=FALSE,quote=FALSE)
+
+#get simple somatic mutations on chr one
+q_chrone = ssm_occurrences() |> GenomicDataCommons::filter(ssm.chromosome == 'chr1') |> GenomicDataCommons::expand(c('ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_chrone,file="simplesomaticmutschr1.txt",row.names=FALSE,quote=FALSE)
+
+######################------------------------------################################
+####get all simple somatic mutations on chr 17
+q_1 = ssm_occurrences() |> GenomicDataCommons::filter(ssm.chromosome == 'chr17') |> GenomicDataCommons::expand(c('ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_1,file="simplesomaticmutschr17.txt",row.names=FALSE,quote=FALSE)
+
+
+#pull  mutations on chr17 for TP53
+
+q_2 = ssm_occurrences() |> GenomicDataCommons::filter(ssm.consequence.transcript.gene.symbol == 'TP53' & ssm.chromosome == 'chr17') |> GenomicDataCommons::expand(c('case','ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_2,file="TP53var_samples17.txt",row.names=FALSE,quote=FALSE)
+#sanity check: TP53 gene located on chr17 , so same results
+q_3 = ssm_occurrences() |> GenomicDataCommons::filter(ssm.consequence.transcript.gene.symbol == 'TP53') |> GenomicDataCommons::expand(c('case','ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_3,file="TP53var_samples.txt",row.names=FALSE,quote=FALSE)
+
+
+#pull  mutations on chr17 for NF1
+q_4 = ssm_occurrences() |> GenomicDataCommons::filter(ssm.consequence.transcript.gene.symbol == 'NF1' & ssm.chromosome == 'chr17') |> GenomicDataCommons::expand(c('case','ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+
+write.csv(q_4,file="NF1var_samples17.txt",row.names=FALSE,quote=FALSE)
+
+#sanity check : NF1 gene located on chr17, so same results
+q_5 = ssm_occurrences() |> GenomicDataCommons::filter(ssm.consequence.transcript.gene.symbol == 'NF1') |> GenomicDataCommons::expand(c('case','ssm')) |> GenomicDataCommons::results_all() |> as_tibble()
+write.csv(q_5,file="NF1var_samples.txt",row.names=FALSE,quote=FALSE)
+