run_bionano_filter_SE_solo: Getting the data from annotated smaps to extract SV...

In VilainLab/Nanotator: Next generation structural variant annotation and classification

Description

Getting the data from annotated smaps to extract SV information based on type of variants.

Usage

run_bionano_filter_SE_solo(
  input_fmt_geneList = c("Text", "dataFrame"),
  input_fmt_SV = c("Text", "dataFrame"),
  EnzymeType = c("SE", "SVMerge"),
  smap = NULL,
  svData,
  dat_geneList,
  fileName,
  outpath,
  outputFilename = "",
  RZIPpath,
  primaryGenesPresent = TRUE,
  outputType = c("Excel", "csv"),
  directoryName,
  fileprefix
)

Arguments

input_fmt_geneList	character. Choice of gene list input Text or Dataframe.
input_fmt_SV	character. Choice of gene list input Text or Dataframe.
EnzymeType	Character. Enzyme type used. Options SVMerge or SE.
smap	character. SV file name.
svData	Dataframe Input data containing SV data.
dat_geneList	Dataframe Input data containing geneList data.
fileName	Character Name of file containing Gene List data.
outpath	Character Directory to the output file.
outputFilename	Character Output filename.
RZIPpath	Character Path for the Rtools Zip package.
primaryGenesPresent	boolean Checks whether the primary gene List is present or not.
outputType	Character. Variants in excel tabs or in different csv files. Options Excel or csv.
directoryName	Character. Directory name where individual SV files will be stored.
fileprefix	Character. fileprefix to use for each of the files in the directory.

Value

Excel file containing the annotated SV map, tabs divided based on type of SVs.

Examples

smapName <- "NA12878_DLE1_VAP_solo5.smap"
outputFilename <- "NA12878_DLE1_VAP_solo5_out"
smappath <- system.file("extdata", smapName, package = "nanotatoR")
outpath <- system.file("extdata", smapName, package = "nanotatoR")
RZIPpath <- system.file("extdata", "zip.exe", package = "nanotatoR")
smap = system.file("extdata", smapName, package="nanotatoR")
bedFile <- system.file("extdata", "HomoSapienGRCH19_lift37.bed", package="nanotatoR")
outpath <- system.file("extdata", package="nanotatoR")
datcomp<-overlapnearestgeneSearch(smap = smap, 
    bed=bedFile, inputfmtBed = "bed", outpath, 
    n = 3, returnMethod_bedcomp = c("dataFrame"), 
    input_fmt_SV = "Text",
    EnzymeType = "SE", 
    bperrorindel = 3000, bperrorinvtrans = 50000)
hgpath=system.file("extdata", "GRCh37_hg19_variants_2016-05-15.txt", package="nanotatoR")
datDGV <- DGVfrequency (hgpath = hgpath, 
    smap_data = datcomp,
    win_indel_DGV = 10000, 
    input_fmt_SV = "dataFrame", EnzymeType = "SE",
    perc_similarity_DGV = 0.5,returnMethod="dataFrame")
    indelconf = 0.5; invconf = 0.01;transconf = 0.1;
datInf <- internalFrequency_solo(smapdata = datDGV, 
    buildSVInternalDB=TRUE, win_indel=10000, 
    win_inv_trans=50000, 
    labelType = c("SE"), EnzymeType = "SE",
    SE_path = system.file("extdata", "SoloFile/", package="nanotatoR"),
    SE_pattern = "*_DLE1_*", perc_similarity_parents =0.9,
    Samplecodes = system.file("extdata", "nanotatoR_sample_codes.csv", package="nanotatoR"),
    mergeKey = system.file("extdata", "nanotatoR_control_sample_codes.csv", package="nanotatoR"),
    mergedKeyoutpath = system.file("extdata", package="nanotatoR"), 
    mergedKeyFname = "Sample_index.csv",
    indexfile = system.file("extdata", mergedKeyFname, package="nanotatoR"),
    perc_similarity = 0.5, indelconf = 0.5, invconf = 0.01, 
    transconf = 0.1, limsize = 1000, win_indel_parents = 5000,
    win_inv_trans_parents=40000,
    returnMethod="dataFrame", input_fmt_SV = "dataFrame")
path <- system.file("extdata", "Bionano_config/", package = "nanotatoR")
pattern <- "*_hg19_*"
directoryName <- system.file("extdata", package="nanotatoR")
datBNDB <- BNDBfrequency(smapdata = datInf, 
    buildBNInternalDB=TRUE, 
    input_fmt_SV = "dataFrame",
    dbOutput="dataframe",
    BNDBpath = path, 
    BNDBpattern = pattern, 
    fname, outpath, 
    win_indel = 10000,
    win_inv_trans = 50000, 
    perc_similarity = 0.5, 
    indelconf = 0.5, 
    invconf = 0.01, 
    limsize = 1000,
    transconf = 0.1,
    returnMethod=c("dataFrame"), 
    EnzymeType = c("SE"))
decipherpath = system.file("extdata", "population_cnv.txt", package="nanotatoR")
datdecipher <- Decipherfrequency (decipherpath = decipherpath, 
    smap_data = datBNDB, win_indel = 10000, 
    perc_similarity = 0.5,returnMethod="dataFrame", 
    input_fmt_SV = "dataFrame", EnzymeType = c("SE"))
run_bionano_filter_SE_solo (input_fmt_geneList = c("Text"),
    input_fmt_SV = c("dataFrame"),
    svData = datdecipher, 
    dat_geneList = dat_geneList,
    RZIPpath = RZIPpath, EnzymeType = c("SE"),
    outputType = c("csv"),
    primaryGenesPresent = FALSE, 
    directoryName = directoryName,
    fileprefix = "AnnotatedSamplesNA12878_DLE")

VilainLab/Nanotator documentation built on Oct. 9, 2021, 8:59 p.m.