0

我正在研究这样定义的 Drake 工作流程：

projectName <- c("lake_2018_CER_lib_norm_log2", "lake_2018_CER_lib_norm", "lake_2018_CER_raw_counts")
normalize <- c(TRUE, TRUE, FALSE)
logTransform <- c(TRUE, FALSE, FALSE)

normalize_fxn <- function(datExpr) {
  
  datExpr <- sweep(datExpr, 2, colSums(datExpr), FUN = "/")
  return(datExpr)
  
}

plan <- drake_plan(
  
  datExpr = target(fread(file_in(filePath), sep = "\t") %>% select(-1), transform = map(filePath = !!filePath, .id = FALSE)),
  datExprNorm = target(if(normalize == TRUE) {normalize_fxn(datExpr)*1e6 + 1} else {datExpr}, transform = map(datExpr, normalize = !!normalize)),
  datExprLog = target(if(logTransform == TRUE) {log2(datExprNorm*1e6 + 1)} else {datExprNorm}, transform = map(datExprNorm, logTransform = !!logTransform)),
  filterGenesMinCells = target(if(is.numeric(percentCells)) {round(ncol(datExprLog)*percentCells)} else {NULL}, transform = cross(datExprLog, percentCells = !!percentCells)),
  makePlots = target(realVsPermCor(datExpr = datExprLog,
                                   projectName = projectName,
                                   featureType = featureType,
                                   nPerms = 100,
                                   subsampleReal = NULL,
                                   resampleReal = NULL,
                                   subsamplePerm,
                                   filterGenesMinCells = filterGenesMinCells,
                                   filterCellsMinGenes = NULL,
                                   fdrSubsample,
                                   futureThreads = NULL,
                                   openBlasThreads = 10,
                                   outDir),
                     transform = cross(filterGenesMinCells, featureType = !!featureType, .id = c(featureType, percentCells)))
)

目标输出如下所示：

> plan$target
 [1] "datExpr"                                                              "datExprLog_TRUE_datExprNorm_TRUE_datExpr"                            
 [3] "datExprLog_FALSE_datExprNorm_TRUE_datExpr_2"                          "datExprLog_FALSE_datExprNorm_FALSE_datExpr"                          
 [5] "datExprNorm_TRUE_datExpr"                                             "datExprNorm_TRUE_datExpr_2"                                          
 [7] "datExprNorm_FALSE_datExpr"                                            "filterGenesMinCells_NULL_datExprLog_TRUE_datExprNorm_TRUE_datExpr"   
 [9] "filterGenesMinCells_0.01_datExprLog_TRUE_datExprNorm_TRUE_datExpr"    "filterGenesMinCells_0.02_datExprLog_TRUE_datExprNorm_TRUE_datExpr"   
[11] "filterGenesMinCells_NULL_datExprLog_FALSE_datExprNorm_TRUE_datExpr_2" "filterGenesMinCells_0.01_datExprLog_FALSE_datExprNorm_TRUE_datExpr_2"
[13] "filterGenesMinCells_0.02_datExprLog_FALSE_datExprNorm_TRUE_datExpr_2" "filterGenesMinCells_NULL_datExprLog_FALSE_datExprNorm_FALSE_datExpr" 
[15] "filterGenesMinCells_0.01_datExprLog_FALSE_datExprNorm_FALSE_datExpr"  "filterGenesMinCells_0.02_datExprLog_FALSE_datExprNorm_FALSE_datExpr" 
[17] "makePlots_gene_NULL"                                                  "makePlots_cell_NULL"                                                 
[19] "makePlots_gene_0.01"                                                  "makePlots_cell_0.01"                                                 
[21] "makePlots_gene_0.02"                                                  "makePlots_cell_0.02"                                                 
[23] "makePlots_gene_NULL_2"                                                "makePlots_cell_NULL_2"                                               
[25] "makePlots_gene_0.01_2"                                                "makePlots_cell_0.01_2"                                               
[27] "makePlots_gene_0.02_2"                                                "makePlots_cell_0.02_2"                                               
[29] "makePlots_gene_NULL_3"                                                "makePlots_cell_NULL_3"                                               
[31] "makePlots_gene_0.01_3"                                                "makePlots_cell_0.01_3"                                               
[33] "makePlots_gene_0.02_3"                                                "makePlots_cell_0.02_3"

这与我想要的非常接近，但我坚持的是projectName：我希望将三个项目名称之一用于最终目标，具体取决于前面步骤中产生的输入是否被规范化和/或对数转换.

目前，我生成了 18 个目标，因此我希望每个项目名称都映射到 6 个目标。

有什么办法可以做到这一点吗？

4

1 回答 1

1

似乎您可以编写一个函数来接受规范化和记录转换设置并输出项目的名称。草图如下。

静态分支drake很难。在drake的继任者中targets，我尝试使这两种分支更容易。（尽管在项目中期进行切换可能不可行。）

library(drake)

filePath <- "file_path.txt"
normalize <- c(TRUE, TRUE, FALSE)
logTransform <- c(TRUE, FALSE, FALSE)
percentCells <- "percent_cells"
featureType <- "feature_type"
normalize_fxn <- function(datExpr) {
  datExpr <- sweep(datExpr, 2, colSums(datExpr), FUN = "/")
  return(datExpr)
}

name_project <- function(normalize, log_transform) {
  switch(
    paste0(normalize, "_", log_transform),
    TRUE_TRUE = "lake_2018_CER_lib_norm_log2",
    TRUE_FALSE = "lake_2018_CER_lib_norm",
    FALSE_FALSE = "lake_2018_CER_raw_counts"
  )
}

plan <- drake_plan(
  datExpr = target(fread(file_in(filePath), sep = "\t") %>% select(-1), transform = map(filePath = !!filePath, .id = FALSE)),
  datExprNorm = target(if(normalize == TRUE) {normalize_fxn(datExpr)*1e6 + 1} else {datExpr}, transform = map(datExpr, normalize = !!normalize)),
  datExprLog = target(if(logTransform == TRUE) {log2(datExprNorm*1e6 + 1)} else {datExprNorm}, transform = map(datExprNorm, logTransform = !!logTransform)),
  filterGenesMinCells = target(if(is.numeric(percentCells)) {round(ncol(datExprLog)*percentCells)} else {NULL}, transform = cross(datExprLog, percentCells = !!percentCells)),
  makePlots = target(
    realVsPermCor(
      datExpr = datExprLog,
      # The project name is a function of normalization and log transform.
      projectName = !!name_project(deparse(substitute(normalize)), deparse(substitute(logTransform))),
      featureType = featureType,
      nPerms = 100,
      subsampleReal = NULL,
      resampleReal = NULL,
      subsamplePerm,
      filterGenesMinCells = filterGenesMinCells,
      filterCellsMinGenes = NULL,
      fdrSubsample,
      futureThreads = NULL,
      openBlasThreads = 10,
      outDir
    ),
    transform = cross(filterGenesMinCells, featureType = !!featureType, .id = c(featureType, percentCells))
  )
)

dplyr::filter(plan, grepl("makePlots", target))$command
#> [[1]]
#> realVsPermCor(datExpr = datExprLog_TRUE_datExprNorm_TRUE_datExpr, 
#>     projectName = "lake_2018_CER_lib_norm_log2", featureType = "feature_type", 
#>     nPerms = 100, subsampleReal = NULL, resampleReal = NULL, 
#>     subsamplePerm, filterGenesMinCells = filterGenesMinCells_percent_cells_datExprLog_TRUE_datExprNorm_TRUE_datExpr, 
#>     filterCellsMinGenes = NULL, fdrSubsample, futureThreads = NULL, 
#>     openBlasThreads = 10, outDir)
#> 
#> [[2]]
#> realVsPermCor(datExpr = datExprLog_FALSE_datExprNorm_TRUE_datExpr_2, 
#>     projectName = "lake_2018_CER_lib_norm", featureType = "feature_type", 
#>     nPerms = 100, subsampleReal = NULL, resampleReal = NULL, 
#>     subsamplePerm, filterGenesMinCells = filterGenesMinCells_percent_cells_datExprLog_FALSE_datExprNorm_TRUE_datExpr_2, 
#>     filterCellsMinGenes = NULL, fdrSubsample, futureThreads = NULL, 
#>     openBlasThreads = 10, outDir)
#> 
#> [[3]]
#> realVsPermCor(datExpr = datExprLog_FALSE_datExprNorm_FALSE_datExpr, 
#>     projectName = "lake_2018_CER_raw_counts", featureType = "feature_type", 
#>     nPerms = 100, subsampleReal = NULL, resampleReal = NULL, 
#>     subsamplePerm, filterGenesMinCells = filterGenesMinCells_percent_cells_datExprLog_FALSE_datExprNorm_FALSE_datExpr, 
#>     filterCellsMinGenes = NULL, fdrSubsample, futureThreads = NULL, 
#>     openBlasThreads = 10, outDir)

由reprex 包于 2021-01-12 创建(v0.3.0)

于 2021-01-13T00:47:35.043 回答