@@ -1,7 +1,7 @@

 Package: TCGAbiolinks

 Type: Package

 Title: TCGAbiolinks: An R/Bioconductor package for integrative analysis with GDC data

-Version: 2.29.0

+Version: 2.29.1

 Date: 2022-17-08

 Author: Antonio Colaprico,

     Tiago Chedraoui Silva,

@@ -1,3 +1,8 @@

+CHANGES IN VERSION 2.29.1

+-------------------------

+

+* Removing support to legacy archive since it will be shutdown by GDC soon.

+

 CHANGES IN VERSION 2.21.1

 -------------------------

@@ -344,13 +344,16 @@ GDCquery_clinic <- function(

                             } else {

                                 # HTMCP-03-06-02061 has two diagnosis

                                 x$submitter_id <- gsub("_diagnosis.*","",x$submitter_id)

+                                # If there are two rows for the same submitter_id

+                                # we will collapse them into one single row

+                                # concatanating all columns using ;

                                 aux <- x %>% dplyr::group_by(submitter_id) %>%

-                                    dplyr::summarise_each(funs(paste(unique(.), collapse = ";")))

+                                    summarise(across(everything(),~ paste(unique(.), collapse = ";")))

                                 aux$treatments <- list(dplyr::bind_rows(x$treatments))

                                 aux

                             }

                         }

-                    ),fill = T

+                    ), fill = TRUE

                 )

                 #df$submitter_id <- gsub("^d|_diagnosis|diag-|-DX|-DIAG|-diagnosis","", df$submitter_id)

                 # ^d ORGANOID-PANCREATIC

@@ -500,7 +503,7 @@ GDCprepare_clinic <- function(

     }

     # Get all the clincal xml files

-    source <- ifelse(query$legacy,"legacy","harmonized")

+    source <- "harmonized"

     files <- file.path(

         query$results[[1]]$project, source,

         gsub(" ","_",query$results[[1]]$data_category),

@@ -16,15 +16,6 @@

 #' @importFrom methods is

 #' @export

 #' @examples

-#' query <- GDCquery(

-#'   project = "TCGA-ACC",

-#'   data.category =  "Copy number variation",

-#'   legacy = TRUE,

-#'   file.type = "hg19.seg",

-#'   barcode = c("TCGA-OR-A5LR-01A-11D-A29H-01", "TCGA-OR-A5LJ-10A-01D-A29K-01")

-#'  )

-#' # data will be saved in  GDCdata/TCGA-ACC/legacy/Copy_number_variation/Copy_number_segmentation

-#' GDCdownload(query, method = "api")

 #' \dontrun{

 #'     # Download clinical data from XML

 #'     query <- GDCquery(project = "TCGA-COAD", data.category = "Clinical")

@@ -39,14 +30,14 @@

 #'     # data will be saved in:

 #'     # example_data_dir/TARGET-AML/harmonized/Transcriptome_Profiling/miRNA_Expression_Quantification

 #'     GDCdownload(query, method = "client", directory = "example_data_dir")

-#'     acc.gbm <- GDCquery(

+#'     query_acc_gbm <- GDCquery(

 #'         project =  c("TCGA-ACC","TCGA-GBM"),

 #'         data.category = "Transcriptome Profiling",

 #'         data.type = "Gene Expression Quantification",

 #'         workflow.type = "STAR - Counts"

 #'     )

 #'     GDCdownload(

-#'        query = acc.gbm,

+#'        query = query_acc_gbm,

 #'        method = "api",

 #'        directory = "example",

 #'        files.per.chunk = 50

@@ -73,7 +64,7 @@ GDCdownload <- function(

         stop("We can only download one data type. Please use data.type argument in GDCquery to filter results.")

     }

-    source <- ifelse(query$legacy,"legacy","harmonized")

+    source <- "harmonized"

     dir.create(directory, showWarnings = FALSE, recursive = TRUE)

     for(proj in unique(unlist(query$project))){

@@ -152,11 +143,7 @@ GDCdownload <- function(

                 )

             }

-            server <- ifelse(

-                query$legacy,

-                "https://api.gdc.cancer.gov/legacy/data/",

-                "https://api.gdc.cancer.gov/data/"

-            )

+            server <- "https://api.gdc.cancer.gov/data/"

             if (is.null(files.per.chunk) & sum(as.numeric(manifest$size)) > 10^9) {

                 message("The total size of files is big. We will download files in chunks")

@@ -67,107 +67,52 @@ checkProjectInput <- function(project){

     }

 }

-checkLegacyPlatform <- function(project,data.category, legacy = FALSE){

-    project.summary <- getProjectSummary(project, legacy)

-    if(missing(data.category)) {

-        print(knitr::kable(project.summary$data_categories))

-        stop("Please set a data.category argument from the column data_category above")

-    }

-    if(!(data.category %in% project.summary$data_categories$data_category)) {

-        print(knitr::kable(project.summary$data_categories))

-        stop("Please set a valid data.category argument from the column data_category above")

-    }

-}

+checkDataTypeInput <- function(data.type){

+

+    harmonized.data.type <- c(

+        "Aggregated Somatic Mutation",

+        "Aligned Reads",

+        "Gene Expression Quantification",

+        "Raw CGI Variant",

+        "Methylation Beta Value",

+        "Differential Gene Expression",

+        "Splice Junction Quantification",

+        "Protein Expression Quantification",

+        "Annotated Somatic Mutation",

+        "Raw Simple Somatic Mutation",

+        "Masked Somatic Mutation",

+        "Copy Number Segment",

+        "Masked Intensities",

+        "Allele-specific Copy Number Segment",

+        "Masked Copy Number Segment",

+        "Isoform Expression Quantification",

+        "miRNA Expression Quantification",

+        "Gene Level Copy Number",

+        "Biospecimen Supplement",

+        "Gene Level Copy Number Scores",

+        "Protein Expression Quantification",

+        "Clinical Supplement",

+        "Single Cell Analysis",

+        "Masked Somatic Mutation",

+        "Slide Image"

+    )

-checkDataTypeInput <- function(legacy, data.type){

-    if(legacy){

-        legacy.data.type <- c("Copy number segmentation",

-                              "Raw intensities",

-                              "Aligned reads",

-                              "Copy number estimate",

-                              "Simple nucleotide variation",

-                              "Gene expression quantification",

-                              "Coverage WIG",

-                              "miRNA gene quantification",

-                              "Genotypes",

-                              "miRNA isoform quantification",

-                              "Normalized copy numbers",

-                              "Isoform expression quantification",

-                              "Normalized intensities",

-                              "Tissue slide image",

-                              "Exon quantification",

-                              "Exon junction quantification",

-                              "Methylation beta value",

-                              "Unaligned reads",

-                              "Diagnostic image",

-                              "CGH array QC",

-                              "Biospecimen Supplement",

-                              "Pathology report",

-                              "Clinical Supplement",

-                              "Intensities",

-                              "Protein expression quantification",

-                              "Microsatellite instability",

-                              "Structural variation",

-                              "Auxiliary test",

-                              "Copy number QC metrics",

-                              "Intensities Log2Ratio",

-                              "Methylation array QC metrics",

-                              "Clinical data",

-                              "Copy number variation",

-                              "ABI sequence trace",

-                              "Protein Expression Quantification",

-                              "Biospecimen data",

-                              "Simple somatic mutation",

-                              "Bisulfite sequence alignment",

-                              "Methylation percentage",

-                              "Sequencing tag",

-                              "Sequencing tag counts",

-                              "LOH")

-        if(!data.type %in% legacy.data.type) {

-            print(knitr::kable(as.data.frame(sort(legacy.data.type))))

-            stop("Please set a data.type argument from the column legacy.data.type above")

-        }

-    } else {

-        harmonized.data.type <- c(

-            "Aggregated Somatic Mutation",

-            "Aligned Reads",

-            "Gene Expression Quantification",

-            "Raw CGI Variant",

-            "Methylation Beta Value",

-            "Differential Gene Expression",

-            "Splice Junction Quantification",

-            "Protein Expression Quantification",

-            "Annotated Somatic Mutation",

-            "Raw Simple Somatic Mutation",

-            "Masked Somatic Mutation",

-            "Copy Number Segment",

-            "Masked Intensities",

-            "Allele-specific Copy Number Segment",

-            "Masked Copy Number Segment",

-            "Isoform Expression Quantification",

-            "miRNA Expression Quantification",

-            "Gene Level Copy Number",

-            "Biospecimen Supplement",

-            "Gene Level Copy Number Scores",

-            "Protein Expression Quantification",

-            "Clinical Supplement",

-            "Single Cell Analysis",

-            "Masked Somatic Mutation",

-            "Slide Image")

-        if(!data.type %in% harmonized.data.type) {

-            print(knitr::kable(as.data.frame(sort(harmonized.data.type))))

-            stop("Please set a data.type argument from the column harmonized.data.type above")

-        }

+    if (!data.type %in% harmonized.data.type) {

+        print(knitr::kable(as.data.frame(sort(harmonized.data.type))))

+        stop("Please set a data.type argument from the column harmonized.data.type above")

     }

 }

-checkDataCategoriesInput <- function(project,data.category, legacy = FALSE){

+checkDataCategoriesInput <- function(project,data.category){

+

     for(proj in project){

-        project.summary <- getProjectSummary(proj, legacy)

+

+        project.summary <- getProjectSummary(proj)

         if(missing(data.category)) {

             print(knitr::kable(project.summary$data_categories))

             stop("Please set a data.category argument from the column data_category above")

         }

+

         if(!(data.category %in% project.summary$data_categories$data_category)) {

             print(knitr::kable(project.summary$data_categories))

             stop("Please set a valid data.category argument from the column data_category above. We could not validade the data.category for project ", proj)

@@ -618,13 +563,10 @@ get.mutation <- function(

     if(missing(genes)) stop("Argument genes is missing")

     # Get mutation annotation file

-    library(maftools)

-    library(dplyr)

     query <- GDCquery(

         project = project,

         data.category = "Simple Nucleotide Variation",

         access = "open",

-        legacy = FALSE,

         data.type = "Masked Somatic Mutation",

         workflow.type = "Aliquot Ensemble Somatic Variant Merging and Masking"

     )

@@ -638,8 +580,9 @@ get.mutation <- function(

         unlist(

             sapply(

                 mutant_variant_classification,

-                function(x) grep(x,maf$Variant_Classification,

-                                 ignore.case = TRUE)

+                function(x) {

+                    grep(x,maf$Variant_Classification,ignore.case = TRUE)

+                }

             )

         )

     )

@@ -648,8 +591,10 @@ get.mutation <- function(

     mut <- NULL

     for(i in genes) {

         if(!i %in% maf$Hugo_Symbol) next

-        aux <- data.frame(patient = substr(unique(maf[i == maf$Hugo_Symbol,]$Tumor_Sample_Barcode),1,15),

-                          mut = TRUE)

+        aux <- data.frame(

+            patient = substr(unique(maf[i == maf$Hugo_Symbol,]$Tumor_Sample_Barcode),1,15),

+            mut = TRUE

+        )

         colnames(aux)[2] <- paste0("mut_hg38_",i)

         if(is.null(mut)) {

             mut <- aux

@@ -668,6 +613,7 @@ get.mutation <- function(

     return(mut)

 }

+

 get.mut.gistc <- function(

         project,

         genes,

@@ -694,6 +640,7 @@ get.mut.gistc <- function(

     } else if(is.null(mut) & !is.null(cnv)) {

         return(cnv)

     }

+

     return(NULL)

 }

 get.mut.gistc.information <- function(

@@ -91,7 +91,7 @@ GDCprepare <- function(

         stop("To remove the files, please set save to TRUE. Otherwise, the data will be lost")

     }

     # We save the files in project/source/data.category/data.type/file_id/file_name

-    source <- ifelse(query$legacy,"legacy","harmonized")

+    source <- "harmonized"

     files <- file.path(

         query$results[[1]]$project, source,

         gsub(" ","_",query$results[[1]]$data_category),

@@ -174,8 +174,7 @@ GDCprepare <- function(

             files = files,

             cases = cases,

             summarizedExperiment = summarizedExperiment,

-            platform =  unique(query$results[[1]]$platform),

-            legacy = query$legacy

+            platform =  unique(query$results[[1]]$platform)

         )

     }  else if (grepl("Raw intensities|Masked Intensities",query$data.type, ignore.case = TRUE)) {

         # preparing IDAT files

@@ -183,8 +182,7 @@ GDCprepare <- function(

             files = files,

             barcode = cases,

             summarizedExperiment = summarizedExperiment,

-            platform =  unique(query$results[[1]]$platform),

-            legacy = query$legacy

+            platform =  unique(query$results[[1]]$platform)

         )

     }  else if (grepl("Proteome Profiling",query$data.category,ignore.case = TRUE)) {

@@ -199,7 +197,7 @@ GDCprepare <- function(

     }  else if (grepl("Simple Nucleotide Variation",query$data.category,ignore.case = TRUE)) {

-        if(grepl("Masked Somatic Mutation",query$results[[1]]$data_type[1],ignore.case = TRUE) | source == "legacy"){

+        if(grepl("Masked Somatic Mutation",query$results[[1]]$data_type[1],ignore.case = TRUE)){

             data <- readSimpleNucleotideVariationMaf(files)

         }

@@ -212,7 +210,7 @@ GDCprepare <- function(

                 files = files,

                 cases = cases,

                 summarizedExperiment = summarizedExperiment,

-                genome = ifelse(query$legacy,"hg19","hg38"),

+                genome = "hg38",

                 experimental.strategy = unique(query$results[[1]]$experimental_strategy)

             )

@@ -221,7 +219,7 @@ GDCprepare <- function(

                 files = files,

                 cases = cases,

                 summarizedExperiment = FALSE,

-                genome = ifelse(query$legacy,"hg19","hg38"),

+                genome = "hg38",

                 experimental.strategy = unique(query$results[[1]]$experimental_strategy)

             )

@@ -713,14 +711,13 @@ readIDATDNAmethylation <- function(

         files,

         barcode,

         summarizedExperiment,

-        platform,

-        legacy

+        platform

 ) {

     check_package("sesame")

     # Check if moved files would be moved outside of scope folder, if so, path doesn't change

-    moved.files <- sapply(files,USE.NAMES=FALSE,function(x){

+    moved.files <- sapply(files,USE.NAMES = FALSE,function(x){

         if (grepl("Raw_intensities|Masked_Intensities",dirname(dirname(x)))) {

             return(file.path(dirname(dirname(x)), basename(x)))

         }

@@ -753,7 +750,7 @@ readIDATDNAmethylation <- function(

         betas <- makeSEFromDNAMethylationMatrix(

             betas = betas,

-            genome = ifelse(legacy,"hg19","hg38"),

+            genome ="hg38",

             met.platform = platform

         )

         colData(betas) <- DataFrame(colDataPrepare(colnames(betas)))

@@ -774,8 +771,7 @@ readDNAmethylation <- function(

         files,

         cases,

         summarizedExperiment = TRUE,

-        platform,

-        legacy

+        platform

 ){

     if(length(platform) > 1){

@@ -847,7 +843,7 @@ readDNAmethylation <- function(

             df <- makeSEFromDNAMethylationMatrix(

                 betas = df,

-                genome = ifelse(legacy,"hg19","hg38"),

+                genome = "hg38",

                 met.platform = platform

             )

         }

@@ -1056,31 +1052,37 @@ colDataPrepareTCGA <- function(barcode){

     # For the moment this will work only for TCGA Data

     # We should search what TARGET data means

-    code <- c('01','02','03','04','05','06','07','08','09','10','11',

-              '12','13','14','20','40','50','60','61')

-    shortLetterCode <- c("TP","TR","TB","TRBM","TAP","TM","TAM","THOC",

-                         "TBM","NB","NT","NBC","NEBV","NBM","CELLC","TRB",

-                         "CELL","XP","XCL")

-

-    definition <- c("Primary solid Tumor", # 01

-                    "Recurrent Solid Tumor", # 02

-                    "Primary Blood Derived Cancer - Peripheral Blood", # 03

-                    "Recurrent Blood Derived Cancer - Bone Marrow", # 04

-                    "Additional - New Primary", # 05

-                    "Metastatic", # 06

-                    "Additional Metastatic", # 07

-                    "Human Tumor Original Cells", # 08

-                    "Primary Blood Derived Cancer - Bone Marrow", # 09

-                    "Blood Derived Normal", # 10

-                    "Solid Tissue Normal",  # 11

-                    "Buccal Cell Normal",   # 12

-                    "EBV Immortalized Normal", # 13

-                    "Bone Marrow Normal", # 14

-                    "Control Analyte", # 20

-                    "Recurrent Blood Derived Cancer - Peripheral Blood", # 40

-                    "Cell Lines", # 50

-                    "Primary Xenograft Tissue", # 60

-                    "Cell Line Derived Xenograft Tissue") # 61

+    code <- c(

+        '01','02','03','04','05','06','07','08','09','10','11',

+        '12','13','14','20','40','50','60','61'

+    )

+    shortLetterCode <- c(

+        "TP","TR","TB","TRBM","TAP","TM","TAM","THOC",

+        "TBM","NB","NT","NBC","NEBV","NBM","CELLC","TRB",

+        "CELL","XP","XCL"

+    )

+

+    definition <- c(

+        "Primary solid Tumor", # 01

+        "Recurrent Solid Tumor", # 02

+        "Primary Blood Derived Cancer - Peripheral Blood", # 03

+        "Recurrent Blood Derived Cancer - Bone Marrow", # 04

+        "Additional - New Primary", # 05

+        "Metastatic", # 06

+        "Additional Metastatic", # 07

+        "Human Tumor Original Cells", # 08

+        "Primary Blood Derived Cancer - Bone Marrow", # 09

+        "Blood Derived Normal", # 10

+        "Solid Tissue Normal",  # 11

+        "Buccal Cell Normal",   # 12

+        "EBV Immortalized Normal", # 13

+        "Bone Marrow Normal", # 14

+        "Control Analyte", # 20

+        "Recurrent Blood Derived Cancer - Peripheral Blood", # 40

+        "Cell Lines", # 50

+        "Primary Xenograft Tissue", # 60

+        "Cell Line Derived Xenograft Tissue"

+    ) # 61

     aux <- DataFrame(code = code,shortLetterCode,definition)

     # in case multiple equal barcode

@@ -1088,10 +1090,12 @@ colDataPrepareTCGA <- function(barcode){

                     "-[:alnum:]{3}-[:alnum:]{3}-[:alnum:]{4}-[:alnum:]{2}")

     samples <- str_match(barcode,regex)[,1]

-    ret <- DataFrame(barcode = barcode,

-                     patient = substr(barcode, 1, 12),

-                     sample = substr(barcode, 1, 16),

-                     code = substr(barcode, 14, 15))

+    ret <- DataFrame(

+        barcode = barcode,

+        patient = substr(barcode, 1, 12),

+        sample = substr(barcode, 1, 16),

+        code = substr(barcode, 14, 15)

+    )

     ret <- merge(ret,aux, by = "code", sort = FALSE)

     ret <- ret[match(barcode,ret$barcode),]

     rownames(ret) <- gsub("\\.","-",make.names(ret$barcode,unique=TRUE))

@@ -3,7 +3,6 @@

 #'   Uses GDC API to search for search, it searches for both controlled and

 #'   open-access data.

 #'   For GDC data arguments project, data.category, data.type and workflow.type should be used

-#'   For the legacy data arguments project, data.category, platform and/or file.extension should be used.

 #'   Please, see the vignette for a table with the possibilities.

 #' @param project A list of valid project (see list with TCGAbiolinks:::getGDCprojects()$project_id)]

 #' \itemize{

@@ -75,33 +74,15 @@

 #' \item{ Simple Nucleotide Variation }

 #' \item{ Transcriptome Profiling }

 #' }

-#' List for legacy archive

-#' \itemize{

-#' \item{ Biospecimen }

-#' \item{ Clinical }

-#' \item{ Copy number variation }

-#' \item{ DNA methylation }

-#' \item{ Gene expression }

-#' \item{ Protein expression }

-#' \item{ Raw microarray data }

-#' \item{ Raw sequencing data }

-#' \item{ Simple nucleotide variation }

-#' }

 #' @param data.type A data type to filter the files to download

 #' For the complete list please check the vignette.

 #' @param sample.type A sample type to filter the files to download

 #' @param barcode A list of barcodes to filter the files to download

-#' @param legacy Search in the legacy repository

 #' @param data.format Data format filter ("VCF", "TXT", "BAM","SVS","BCR XML","BCR SSF XML",

 #' "TSV", "BCR Auxiliary XML", "BCR OMF XML", "BCR Biotab", "MAF", "BCR PPS XML", "XLSX")

-#' @param file.type To be used in the legacy database for some platforms,

-#' to define which file types to be used.

 #' @param workflow.type GDC workflow type

-#' @param experimental.strategy Filter to experimental strategy. Harmonized: WXS, RNA-Seq, miRNA-Seq, Genotyping Array.

-#' Legacy:  WXS, RNA-Seq, miRNA-Seq, Genotyping Array,

-#' DNA-Seq, Methylation array, Protein expression array, WXS,CGH array, VALIDATION, Gene expression array,WGS,

-#' MSI-Mono-Dinucleotide Assay, miRNA expression array, Mixed strategies, AMPLICON, Exon array,

-#' Total RNA-Seq, Capillary sequencing, Bisulfite-Seq

+#' @param experimental.strategy Filter to experimental strategy.

+#' Harmonized: WXS, RNA-Seq, miRNA-Seq, Genotyping Array.

 #' @param access Filter by access type. Possible values: controlled, open

 #' @param platform Example:

 #' \tabular{ll}{

@@ -157,19 +138,6 @@

 #'    data.type = "Masked Copy Number Segment",

 #'    sample.type = c("Primary Tumor")

 #' )

-#' query.met <- GDCquery(

-#'    project = c("TCGA-GBM","TCGA-LGG"),

-#'    legacy = TRUE,

-#'    data.category = "DNA methylation",

-#'    platform = "Illumina Human Methylation 450"

-#' )

-#' query <- GDCquery(

-#'    project = "TCGA-ACC",

-#'    data.category =  "Copy number variation",

-#'    legacy = TRUE,

-#'    file.type = "hg19.seg",

-#'    barcode = c("TCGA-OR-A5LR-01A-11D-A29H-01")

-#' )

 #' }

 #' @return A data frame with the results and the parameters used

 #' @importFrom jsonlite fromJSON

@@ -183,7 +151,6 @@ GDCquery <- function(

         data.category,

         data.type,

         workflow.type,

-        legacy = FALSE,

         access,

         platform,

         file.type,

@@ -243,11 +210,11 @@ GDCquery <- function(

         }

     })

     print.header("GDCquery: Searching in GDC database","section")

-    message("Genome of reference: ",ifelse(legacy,"hg19","hg38"))

+    message("Genome of reference: hg38")

     # Check arguments

     checkProjectInput(project)

-    checkDataCategoriesInput(project, data.category, legacy)

-    if(!is.na(data.type)) checkDataTypeInput(legacy = legacy, data.type = data.type)

+    checkDataCategoriesInput(project, data.category)

+    if(!is.na(data.type)) checkDataTypeInput(data.type = data.type)

     if(!any(is.na(sample.type))) checkBarcodeDefinition(sample.type)

     results <- NULL

@@ -257,7 +224,6 @@ GDCquery <- function(

             project = proj,

             data.category = data.category,

             data.type = data.type,

-            legacy = legacy,

             workflow.type = workflow.type,

             platform = platform,

             file.type = file.type,

@@ -279,7 +245,6 @@ GDCquery <- function(

                 project = proj,

                 data.category = data.category,

                 data.type = data.type,

-                legacy = legacy,

                 workflow.type = NA,

                 platform = NA,

                 file.type = file.type,

@@ -621,17 +586,6 @@ GDCquery <- function(

         message("ooo By sample.type")

         results <- results[tolower(results$sample_type) %in% tolower(sample.type),]

     }

-    # some how there are duplicated files in GDC we should remove them

-    # Example of problematic query

-    # query.exp <- GDCquery(project = "TCGA-BRCA",

-    #                  legacy = TRUE,

-    #                  data.category = "Gene expression",

-    #                  data.type = "Gene expression quantification",

-    #                  platform = "Illumina HiSeq",

-    #                  file.type = "results",

-    #                  experimental_strategy = "RNA-Seq",

-    #                  sample.type = c("Primary solid Tumor","Solid Tissue Normal"))

-    #

     print.header("Checking data","subsection")

     message("ooo Checking if there are duplicated cases")

@@ -665,7 +619,6 @@ GDCquery <- function(

         project = I(list(project)),

         data.category = data.category,

         data.type = data.type,

-        legacy = legacy,

         access = I(list(access)),

         experimental.strategy =  I(list(experimental.strategy)),

         file.type = file.type,

@@ -677,37 +630,41 @@ GDCquery <- function(

     return(ret)

 }

-getGDCquery <- function(project, data.category, data.type, legacy, workflow.type,platform,file.type,files.access,sample.type,experimental.strategy){

+getGDCquery <- function(

+        project,

+        data.category,

+        data.type,

+        workflow.type,

+        platform,

+        file.type,

+        files.access,

+        sample.type,

+        experimental.strategy

+){

     # Get manifest using the API

-    baseURL <- ifelse(legacy,"https://api.gdc.cancer.gov/legacy/files/?","https://api.gdc.cancer.gov/files/?")

+    baseURL <- "https://api.gdc.cancer.gov/files/?"

     options.pretty <- "pretty=true"

-    if(data.category == "Protein expression" & legacy) {

-        options.expand <- "fields=archive.revision,archive.file_name,md5sum,state,data_category,file_id,platform,file_name,file_size,md5sum,submitter_id,data_type&expand=cases.samples.portions,cases.project,center,analysis"

-    } else if(data.category %in% c("Clinical","Biospecimen")) {

+    if(data.category %in% c("Clinical","Biospecimen")) {

         options.expand <- "expand=cases,cases.project,center,analysis"

     } else {

         options.expand <- "expand=cases,cases.samples.portions.analytes.aliquots,cases.project,center,analysis,cases.samples"

     }

-    option.size <- paste0("size=",getNbFiles(project,data.category,legacy))

+    option.size <- paste0("size=",getNbFiles(project,data.category))

     option.format <- paste0("format=JSON")

-    options.filter <- paste0("filters=",

-                             URLencode('{"op":"and","content":['),  # Start json request

-                             URLencode('{"op":"in","content":{"field":"cases.project.project_id","value":["'),

-                             project,

-                             URLencode('"]}}'))

+    options.filter <- paste0(

+        "filters=",

+        URLencode('{"op":"and","content":['),  # Start json request

+        URLencode('{"op":"in","content":{"field":"cases.project.project_id","value":["'),

+        project,

+        URLencode('"]}}')

+    )

-    if(!is.na(experimental.strategy))  options.filter <- paste0(options.filter,addFilter("files.experimental_strategy", experimental.strategy))

+    if(!is.na(experimental.strategy)) options.filter <- paste0(options.filter,addFilter("files.experimental_strategy", experimental.strategy))

     if(!is.na(data.category))  options.filter <- paste0(options.filter,addFilter("files.data_category", data.category))

     if(!is.na(data.type))  options.filter <- paste0(options.filter,addFilter("files.data_type", data.type))

     if(!is.na(workflow.type))  options.filter <- paste0(options.filter,addFilter("files.analysis.workflow_type", workflow.type))

     if(!any(is.na(platform))) options.filter <- paste0(options.filter,addFilter("files.platform", platform))

-    if(!any(is.na(file.type))) {

-        if(file.type == "results" & legacy) options.filter <- paste0(options.filter,addFilter("files.tags", "unnormalized"))

-        if(file.type == "normalized_results" & legacy) options.filter <- paste0(options.filter,addFilter("files.tags", "normalized"))

-        if(file.type == "nocnv_hg19.seg" & legacy) options.filter <- paste0(options.filter,addFilter("files.tags", "nocnv"))

-        if(file.type == "hg19.isoform" & legacy) options.filter <- paste0(options.filter,addFilter("files.tags", "hg19"))

-    }

     if(!any(is.na(files.access))) {

         options.filter <- paste0(options.filter,addFilter("files.access", files.access))

     }

@@ -1028,12 +985,11 @@ GDCquery_ATAC_seq <- function(

     results$data_category <- "ATAC-seq"

     results$project <- "ATAC-seq"

     ret <- data.frame(

-        results=I(list(results)),

+        results = I(list(results)),

         tumor = I(list(tumor)),

         project = I(list("ATAC-seq")),

         data.type = I(list("ATAC-seq")),

-        data.category = I(list("ATAC-seq")),

-        legacy = I(list(FALSE))

+        data.category = I(list("ATAC-seq"))

     )

     return(ret)

@@ -871,7 +871,6 @@ unlistlabels <- function(lab) {

 #' @importFrom data.table dcast setDT setDF :=

 #' @examples

 #' \dontrun{

-#' library(maftools)

 #' library(dplyr)

 #' query <- GDCquery(

 #'    project = "TCGA-CHOL",

@@ -929,7 +928,6 @@ TCGAvisualize_oncoprint <- function(

         annotation.legend.side = "bottom"

 ){

-

     check_package("ComplexHeatmap")

     check_package("circlize")

     check_package("grid")

@@ -34,15 +34,6 @@ Uses GDC API or GDC transfer tool to download gdc data

   The data from query will be save in a folder: project/data.category

 }

 \examples{

-query <- GDCquery(

-  project = "TCGA-ACC",

-  data.category =  "Copy number variation",

-  legacy = TRUE,

-  file.type = "hg19.seg",

-  barcode = c("TCGA-OR-A5LR-01A-11D-A29H-01", "TCGA-OR-A5LJ-10A-01D-A29K-01")

- )

-# data will be saved in  GDCdata/TCGA-ACC/legacy/Copy_number_variation/Copy_number_segmentation

-GDCdownload(query, method = "api")

 \dontrun{

     # Download clinical data from XML

     query <- GDCquery(project = "TCGA-COAD", data.category = "Clinical")

@@ -57,14 +48,14 @@ GDCdownload(query, method = "api")

     # data will be saved in:

     # example_data_dir/TARGET-AML/harmonized/Transcriptome_Profiling/miRNA_Expression_Quantification

     GDCdownload(query, method = "client", directory = "example_data_dir")

-    acc.gbm <- GDCquery(

+    query_acc_gbm <- GDCquery(

         project =  c("TCGA-ACC","TCGA-GBM"),

         data.category = "Transcriptome Profiling",

         data.type = "Gene Expression Quantification",

         workflow.type = "STAR - Counts"

     )

     GDCdownload(

-       query = acc.gbm,

+       query = query_acc_gbm,

        method = "api",

        directory = "example",

        files.per.chunk = 50

@@ -9,7 +9,6 @@ GDCquery(

   data.category,

   data.type,

   workflow.type,

-  legacy = FALSE,

   access,

   platform,

   file.type,

@@ -90,18 +89,6 @@ List for harmonized database:

 \item{ Sequencing Reads }

 \item{ Simple Nucleotide Variation }

 \item{ Transcriptome Profiling }

-}

-List for legacy archive

-\itemize{

-\item{ Biospecimen }

-\item{ Clinical }

-\item{ Copy number variation }

-\item{ DNA methylation }

-\item{ Gene expression }

-\item{ Protein expression }

-\item{ Raw microarray data }

-\item{ Raw sequencing data }

-\item{ Simple nucleotide variation }

 }}

 \item{data.type}{A data type to filter the files to download

@@ -109,8 +96,6 @@ For the complete list please check the vignette.}

 \item{workflow.type}{GDC workflow type}

-\item{legacy}{Search in the legacy repository}

-

 \item{access}{Filter by access type. Possible values: controlled, open}

 \item{platform}{Example:

@@ -140,19 +125,13 @@ HumanMethylation27                \tab Mixed_DNASeq_Cont_curated      \cr

 IlluminaHiSeq_RNASeqV2            \tab Mixed_DNASeq_Cont

 }}

-\item{file.type}{To be used in the legacy database for some platforms,

-to define which file types to be used.}

-

 \item{barcode}{A list of barcodes to filter the files to download}

 \item{data.format}{Data format filter ("VCF", "TXT", "BAM","SVS","BCR XML","BCR SSF XML",

 "TSV", "BCR Auxiliary XML", "BCR OMF XML", "BCR Biotab", "MAF", "BCR PPS XML", "XLSX")}

-\item{experimental.strategy}{Filter to experimental strategy. Harmonized: WXS, RNA-Seq, miRNA-Seq, Genotyping Array.

-Legacy:  WXS, RNA-Seq, miRNA-Seq, Genotyping Array,

-DNA-Seq, Methylation array, Protein expression array, WXS,CGH array, VALIDATION, Gene expression array,WGS,

-MSI-Mono-Dinucleotide Assay, miRNA expression array, Mixed strategies, AMPLICON, Exon array,

-Total RNA-Seq, Capillary sequencing, Bisulfite-Seq}

+\item{experimental.strategy}{Filter to experimental strategy.

+Harmonized: WXS, RNA-Seq, miRNA-Seq, Genotyping Array.}

 \item{sample.type}{A sample type to filter the files to download}

 }

@@ -163,7 +142,6 @@ A data frame with the results and the parameters used

 Uses GDC API to search for search, it searches for both controlled and

   open-access data.

   For GDC data arguments project, data.category, data.type and workflow.type should be used

-  For the legacy data arguments project, data.category, platform and/or file.extension should be used.

   Please, see the vignette for a table with the possibilities.

 }

 \examples{

@@ -193,19 +171,6 @@ query <- GDCquery(

    data.type = "Masked Copy Number Segment",

    sample.type = c("Primary Tumor")

 )

-query.met <- GDCquery(

-   project = c("TCGA-GBM","TCGA-LGG"),

-   legacy = TRUE,

-   data.category = "DNA methylation",

-   platform = "Illumina Human Methylation 450"

-)

-query <- GDCquery(

-   project = "TCGA-ACC",

-   data.category =  "Copy number variation",

-   legacy = TRUE,

-   file.type = "hg19.seg",

-   barcode = c("TCGA-OR-A5LR-01A-11D-A29H-01")

-)

 }

 }

 \author{

@@ -87,7 +87,6 @@ Creating a oncoprint

 }

 \examples{

 \dontrun{

-library(maftools)

 library(dplyr)

 query <- GDCquery(

    project = "TCGA-CHOL",

@@ -1,17 +1,16 @@

-context("Download AND PREPARE")

-

-

+context("Download and prepare")

 test_that("GDCdownload API method is working ", {

     skip_on_bioc()

     skip_if_offline()

-    cases <-  c(

+    cases <- c(

         "TCGA-PA-A5YG-01A-11R-A29S-07",

         "TCGA-OR-A5JX-01A-11R-A29S-07",

         "TCGA-PK-A5HA-01A-11R-A29S-07",

         "TCGA-OR-A5KY-01A-11R-A29S-07"

     )

+

     acc <- GDCquery(

         project =  c("TCGA-ACC"),

         data.category = "Transcriptome Profiling",

@@ -20,8 +19,8 @@ test_that("GDCdownload API method is working ", {

         barcode = substr(cases,1,12)

     )

     GDCdownload(acc, method = "api", directory = "ex")

-

     obj <- GDCprepare(acc,  directory = "ex",summarizedExperiment = TRUE)

+

     expect_true(all(substr(colnames(obj),1,12) == substr(cases,1,12)))

     expect_true(all(obj$barcode == cases))

@@ -46,9 +45,6 @@ test_that("GDCdownload API method is working ", {

     expect_true(all(query$results[[1]]$sample.submitter_id == data$sample_submitter_id))

 })

-

-

-

 test_that("getBarcodeInfo works", {

     skip_on_bioc()

     skip_if_offline()

@@ -61,11 +57,14 @@ test_that("getBarcodeInfo works", {

     x <- getBarcodeInfo(c("TARGET-20-PARUDL-03A"))

     expect_true(all(cols %in% colnames(x)))

-    samples <- c("HCM-CSHL-0063-C18-85A",

-                 "HCM-CSHL-0065-C20-06A",

-                 "HCM-CSHL-0065-C20-85A",

-                 "HCM-CSHL-0063-C18-01A")

+    samples <- c(

+        "HCM-CSHL-0063-C18-85A",

+        "HCM-CSHL-0065-C20-06A",

+        "HCM-CSHL-0065-C20-85A",

+        "HCM-CSHL-0063-C18-01A"

+    )

     x <- colDataPrepare(samples)