cellMarkerToGmt: A function to convert the CellMarker data to GMT files.

In rikenbit/scTGIF: Cell type annotation for unannotated single-cell RNA-Seq data

A function to convert the CellMarker data to GMT files.

Description

The GMT (Gene Matrix Transposed file format : *.gmt) file is formatted by the Broad Institute (https://software.broadinstitute.org/cancer/software/gsea/wiki/index.php/Data_formats#GMT:_Gene_Matrix_Transposed_file_format_.28.2A.gmt.29). The data can be downloaded from the website of CellMarker (http://biocc.hrbmu.edu.cn/CellMarker).

Usage

cellMarkerToGmt(infile, outfile,
  uniq.column=c("tissueType", "cellName"),
  geneid.type=c("geneID", "geneSymbol"))

Arguments

infile	The input file downloaded from CellMarker website
outfile	The output GMT file converted from the CellMarker data
uniq.column	The duplicated terms in the specified column are aggrgated as a row of GMT file (Default: geneID)
geneid.type	Output gene identifier. (Default: geneID)

Value

output

A GMT file is generated.

Author(s)

NA

Examples

  library("GSEABase")

  tmp <- tempdir()
  infile1 = paste0(tmp, "/Human_cell_markers.txt")
  outfile1_1 = paste0(tmp, "/Human_cell_markers_1.gmt")
  outfile1_2 = paste0(tmp, "/Human_cell_markers_2.gmt")
  outfile1_3 = paste0(tmp, "/Human_cell_markers_3.gmt")
  outfile1_4 = paste0(tmp, "/Human_cell_markers_4.gmt")

  sink(infile1)
  cat("speciesType\ttissueType\tUberonOntologyID\tcancerType\tcellType\tcellName\tCellOntologyID\tcellMarker\tgeneSymbol\tgeneID\tproteinName\tproteinID\tmarkerResource\tPMID\tCompany\n")
  cat("Human\tKidney\tUBERON_0002113\tNormal\tNormal cell\tProximal tubular cell\tNA\tIntestinal Alkaline Phosphatase\tALPI\t248\tPPBI\tP09923\tExperiment\t9263997\tNA\n")
  cat("Human\tLiver\tUBERON_0002107\tNormal\tNormal cell\tIto cell (hepatic stellate cell)\tCL_0000632\tSynaptophysin\tSYP\t6855\tSYPH\tP08247\tExperiment\t10595912\tNA\n")
  cat("Human\tEndometrium\tUBERON_0001295\tNormal\tNormal cell\tTrophoblast cell\tCL_0000351\tCEACAM1\tCEACAM1\t634\tCEAM1\tP13688\tExperiment\t10751340\tNA\n")
  cat("Human\tGerm\tUBERON_0000923\tNormal\tNormal cell\tPrimordial germ cell\tCL_0000670\tVASA\tDDX4\t54514\tDDX4\tQ9NQI0\tExperiment\t10920202\tNA\n")
  cat("Human\tCorneal epithelium\tUBERON_0001772\tNormal\tNormal cell\tEpithelial cell\tCL_0000066\tKLF6\tKLF6\t1316\tKLF6\tQ99612\tExperiment\t12407152\tNA\n")
  cat("Human\tPlacenta\tUBERON_0001987\tNormal\tNormal cell\tCytotrophoblast\tCL_0000351\tFGF10\tFGF10\t2255\tFGF10\tO15520\tExperiment\t15950061\tNA\n")
  cat("Human\tPeriosteum\tUBERON_0002515\tNormal\tNormal cell\tPeriosteum-derived progenitor cell\tNA\tCD166, CD45, CD9, CD90\tALCAM, PTPRC, CD9, THY1\t214, 5788, 928, 7070\tCD166, PTPRC, CD9, THY1\tQ13740, P08575, P21926, P04216\tExperiment\t15977065\tNA\n")
  cat("Human\tAmniotic membrane\tUBERON_0009742\tNormal\tNormal cell\tAmnion epithelial cell\tCL_0002536\tNANOG, OCT3/4\tNANOG, POU5F1\t79923, 5460\tNANOG, PO5F1\tQ9H9S0, Q01860\tExperiment\t16081662\tNA\n")
  cat("Human\tPrimitive streak\tUBERON_0004341\tNormal\tNormal cell\tPrimitive streak cell\tNA\tLHX1, MIXL1\tLHX1, MIXL1\t3975, 83881\tLHX1, MIXL1\tP48742, Q9H2W2\tExperiment\t16258519\tNA\n")
  sink()

  cellMarkerToGmt(infile1, outfile1_1, uniq.column=c("tissueType"),
    geneid.type=c("geneID"))
  cellMarkerToGmt(infile1, outfile1_2, uniq.column=c("tissueType"),
    geneid.type=c("geneSymbol"))
  cellMarkerToGmt(infile1, outfile1_3, uniq.column=c("cellName"),
    geneid.type=c("geneID"))
  cellMarkerToGmt(infile1, outfile1_4, uniq.column=c("cellName"),
    geneid.type=c("geneSymbol"))

  gmt1_1 <- getGmt(outfile1_1)
  gmt1_2 <- getGmt(outfile1_2)
  gmt1_3 <- getGmt(outfile1_3)
  gmt1_4 <- getGmt(outfile1_4)

rikenbit/scTGIF documentation built on Jan. 14, 2023, 4:18 a.m.