nanotatoR_main_Duo_SE {nanotatoR} | R Documentation |
Annotation and visualisation of Bionano SV, of Single enzyme Duo samples.
nanotatoR_main_Duo_SE( smap, bed, inputfmtBed = c("bed", "BNBed"), n = 3, buildBNInternalDB = TRUE, mergedFiles, smappath, buildSVInternalDB = FALSE, path, pattern, win_indel_INF = 10000, win_inv_trans_INF = 50000, perc_similarity_INF = 0.5, indelconf = 0.5, invconf = 0.01, transconf = 0.1, perc_similarity_INF_parents = 0.9, hgpath, win_indel_DGV = 10000, win_inv_trans_DGV = 50000, perc_similarity_DGV = 0.5, method_entrez = c("Single", "Multiple", "Text"), termPath, term, thresh = 5, limsize = 1000, EnzymeType = c("SVmerge", "SE"), labelType = c("SVMerge", "SE", "Both"), SVMerge_path, SVMerge_pattern, SE_path, SE_pattern, Samplecodes, mergeKey, mergedKeyoutpath, mergedKeyFname, RNAseqcombo = TRUE, RNASeqDir, returnMethod = "dataFrame", RNASeqData, RNASeqPATH, pattern_Proband = NA, pattern_Mother = NA, pattern_Father = NA, outpath, outputFilename = "", termListPresent = TRUE, internalBNDB, clinvar, InternaldatabasePresent = TRUE, RNASeqDatasetPresent = TRUE, geneListPresent = TRUE, omim, gtr, removeClinvar = FALSE, removeGTR = FALSE, downloadClinvar = FALSE, downloadGTR = FALSE, url_gtr, omimID, RZIPpath, directoryName, fileprefix, datGeneListPath, decipherpath, indexfile, primaryGenesPresent = TRUE, outputType = c("Excel", "csv") )
smap |
character. File name for the smap |
bed |
Text Bionano Bed file. |
inputfmtBed |
character Whether the bed input is UCSC bed or Bionano bed. |
n |
numeric Number of genes to report which are nearest to the breakpoint. Default is 3. |
buildBNInternalDB |
boolean. Checking whether the merged BNDB file database exist. |
mergedFiles |
character. Path to the merged SV files. |
smappath |
character. Path and file name for textfile. |
buildSVInternalDB |
boolean. Checking whether the merged solo file database exist. |
path |
character. Path to the solo file database. |
pattern |
character. pattern of the file names to merge. |
win_indel_INF |
Numeric. Insertion and deletion error window. |
win_inv_trans_INF |
Numeric. Inversion and translocation error window. |
perc_similarity_INF |
Numeric . ThresholdPercentage similarity of the query SV and reference SV. |
indelconf |
Numeric. Threshold for insertion and deletion confidence. |
invconf |
Numeric. Threshold for inversion confidence. |
transconf |
Numeric. Threshold for translocation confidence. |
perc_similarity_INF_parents |
Numeric . ThresholdPercentage similarity for parent zygosity calculation. Default threshold 0.9. |
hgpath |
character. Path to Database of Genomic Variants (DGV) Text file. |
win_indel_DGV |
Numeric. Insertion and deletion error window for DGV. |
win_inv_trans_DGV |
Numeric. Inversion and translocation error window for DGV. |
perc_similarity_DGV |
Numeric . ThresholdPercentage similarity of the query SV and reference SV, for DGV.. |
method_entrez |
character. Input Method for terms. Choices are "Single","Multiple" and "Text". |
termPath |
character. Path and file name for textfile. |
term |
character. Single or Multiple Terms. |
thresh |
integer. Threshold for the number of terms sent to entrez. Note if large lists are sent to ncbi, it might fail to get processed. Default is 5. |
limsize |
Numeric. Minimum size for SV. Default 1000. |
EnzymeType |
Character. Type of enzyme. Options Dual and DLE. |
labelType |
character. Type of labels used for mapping. Choices are Dual, DLE and Both. |
SVMerge_path |
character. Path for the Dual labelled cmap |
SVMerge_pattern |
character. pattern of the dual files. |
SE_path |
character. Path for the Dual labelled cmap |
SE_pattern |
character. pattern of the dual files. |
Samplecodes |
character. File containing relations and IDs associated to them. |
mergeKey |
character. File containing sample ID and relation. |
mergedKeyoutpath |
character. File path storing sample name and nanoID key information. |
mergedKeyFname |
character. File name storing sample name and nanoID key information. |
RNAseqcombo |
boolean whether RNASeq datasets are combined or not. |
RNASeqDir |
boolean Directory for RNASeq. |
returnMethod |
character. Choice between text or data frame as the output. |
RNASeqData |
dataFrame. RNAseq data with gene names. |
RNASeqPATH |
character. RNAseq dataset path . |
pattern_Proband |
character. Pattern for proband. |
pattern_Mother |
character. Pattern to identify the mother reads. |
pattern_Father |
character. Pattern to identify the father reads. |
outpath |
Character Directory to the output file. |
outputFilename |
Character Output filename. |
termListPresent |
logical Checks whether term list is provided by the user. |
internalBNDB |
character. internak Bionano merged databse. |
clinvar |
character. clinvar file name and location. |
InternaldatabasePresent |
boolean. Checking whether internal DB present. |
RNASeqDatasetPresent |
boolean. Checking whether RNASeq database present or not. |
geneListPresent |
logical Checks whether gene list is provided by the user. |
omim |
character. omim2gene file name and location. |
gtr |
character. gtr file name and location. |
removeClinvar |
logical. Deletes the Clinvar database if TRUE. |
removeGTR |
logical. Deletes the GTR database if TRUE. |
downloadClinvar |
logical. Downloads the Clinvar database if TRUE. |
downloadGTR |
logical. Downloads the GTR database if TRUE. |
url_gtr |
character. url for GTR. |
omimID |
character. Omim ID. |
RZIPpath |
character. Path to RZippath. |
directoryName |
Directory name where individual SV files will be stored. |
fileprefix |
character Prefix to use for each of the files in the directory. |
datGeneListPath |
Character Path for genelist. |
decipherpath |
character. Decipher database path. |
indexfile |
character. indexfile containing nano ID and sample relation. |
primaryGenesPresent |
logical Checks whether primarygene list is provided by the user. |
outputType |
Variants in excel tabs or in different csv files. Options Excel or csv. |
Excel file containing the annotated SV map, tabs divided based on type of SVs.
Text files containg gene list and terms associated with them are stored as text files.
## Not run: terms="Muscle Weakness" smapName="NA12878_DLE1_VAP_solo5.smap" smap = system.file("extdata", smapName, package="nanotatoR") bedFile <- system.file("extdata", "HomoSapienGRCH19_lift37.bed", package="nanotatoR") hgpath=system.file("extdata", "GRCh37_hg19_variants_2016-05-15.txt", package="nanotatoR") decipherpath = system.file("extdata", "population_cnv.txt", package="nanotatoR") omim = system.file("extdata", "mim2gene.txt", package="nanotatoR") clinvar = system.file("extdata", "localPDB/", package="nanotatoR") gtr = system.file("extdata", "gtrDatabase.txt", package="nanotatoR") labelType = c("SE") SE_path = system.file("extdata", "SoloFile/", package="nanotatoR") SE_pattern = "*_DLE1_*" 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" RNASeqDir = system.file("extdata", "NA12878_P_Blood_S1.genes.results", package="nanotatoR") path = system.file("extdata", "Bionano_config/", package = "nanotatoR") pattern = "_hg19.txt" outputFilename <- "GM24385_DLE-1_P_trio_hg19_out" outpath <- system.file("extdata", smapName, package = "nanotatoR") RZIPpath <- system.file("extdata", "zip.exe", package = "nanotatoR") nanotatoR_main_Duo_SE( smap = smap, bed = bedFile, inputfmtBed = c("bed"), limsize = 1000, n=3,EnzymeType = c("SE"), buildBNInternalDB=TRUE, path = path , pattern = pattern, buildSVInternalDB = TRUE, labelType = c("SE"), SE_path = SE_path, SE_pattern = SE_pattern, win_indel_INF = 10000, win_inv_trans_INF = 50000, perc_similarity_INF= 0.5, indelconf = 0.5, invconf = 0.01, transconf = 0.1, perc_similarity_INF_parents = 0.9, hgpath = hgpath, win_indel_DGV = 10000, win_inv_trans_DGV = 50000, perc_similarity_DGV = 0.5, method_entrez=c("Single"), term = "Liver cirrhosis", omim = omim, clinvar = clinvar, gtr = gtr, removeClinvar = TRUE, removeGTR = TRUE, downloadClinvar = FALSE, downloadGTR = FALSE, RNASeqDatasetPresent = FALSE, RNAseqcombo = TRUE, RNASeqDir = RNASeqDir, returnMethod = "dataFrame", pattern_Proband = "*_P_*", outpath = outpath, outputFilename = outputFilename, termListPresent = FALSE, primaryGenesPresent = FALSE, InternaldatabasePresent = TRUE, outputType = c("Excel")) ## End(Not run)