Run Nanostringnorm
setwd("J:/PM/GenEnv/Kalpana/LI analysis")
data<-read.table("comp-dataset.txt", header=T, sep="\t")
data$Code.Class<-as.character(data$Code.Class)
data$Name<-as.character(data$Name)
data$Accession<-as.character(data$Accession)
require('NanoStringNorm')
## Loading required package: NanoStringNorm
## Loading required package: gdata
## gdata: Unable to locate valid perl interpreter
## gdata:
## gdata: read.xls() will be unable to read Excel XLS and XLSX files
## gdata: unless the 'perl=' argument is used to specify the location
## gdata: of a valid perl intrpreter.
## gdata:
## gdata: (To avoid display of this message in the future, please
## gdata: ensure perl is installed and available on the executable
## gdata: search path.)
## gdata: Unable to load perl libaries needed by read.xls()
## gdata: to support 'XLX' (Excel 97-2004) files.
##
## gdata: Unable to load perl libaries needed by read.xls()
## gdata: to support 'XLSX' (Excel 2007+) files.
##
## gdata: Run the function 'installXLSXsupport()'
## gdata: to automatically download and install the perl
## gdata: libaries needed to support Excel XLS and XLSX formats.
##
## Attaching package: 'gdata'
## The following object is masked from 'package:stats':
##
## nobs
## The following object is masked from 'package:utils':
##
## object.size
## Loading required package: vsn
## Loading required package: Biobase
## Loading required package: BiocGenerics
## Loading required package: parallel
##
## Attaching package: 'BiocGenerics'
## The following objects are masked from 'package:parallel':
##
## clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
## clusterExport, clusterMap, parApply, parCapply, parLapply,
## parLapplyLB, parRapply, parSapply, parSapplyLB
## The following object is masked from 'package:gdata':
##
## combine
## The following objects are masked from 'package:stats':
##
## IQR, mad, xtabs
## The following objects are masked from 'package:base':
##
## anyDuplicated, append, as.data.frame, as.vector, cbind,
## colnames, do.call, duplicated, eval, evalq, Filter, Find, get,
## grep, grepl, intersect, is.unsorted, lapply, lengths, Map,
## mapply, match, mget, order, paste, pmax, pmax.int, pmin,
## pmin.int, Position, rank, rbind, Reduce, rownames, sapply,
## setdiff, sort, table, tapply, union, unique, unlist, unsplit
## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.
data_norm <- NanoStringNorm(
x = data,
anno = NA,
CodeCount = 'geo.mean', #pos control normalis
Background = 'mean.2sd', #neg control normalis
SampleContent = 'housekeeping.geo.mean', #
round.values = FALSE,
take.log = TRUE,
return.matrix.of.endogenous.probes = T ### needs to be FALSE to generate plots
);
##
## ##############################
## ### NanoStringNorm v1.1.21 ###
## ##############################
##
## There are 1056 samples and 414 Endogenous genes
##
## CodeCount: The following samples have positive normalization factors outside the
## recommended range of (0.3 to 3). Consider removing them.
##
## pos.norm.factor
## X11234NT 92.10
## X11234T 83.90
## r15030NT 93.40
## r15030T 74.60
## X29021NT 76.80
## X32275NT 75.40
## X32275T 95.40
## X40248NT 391.00
## X40248T 209.00
## X37371T 4.23
## X51847NT 73.50
## X51847T 3.19
##
## Background: The following samples have an estimated background greater than
## 3 standard deviations from the mean.
##
## background.zscore
## X11234NT 10.60
## X11234T 16.10
## r15030NT 14.30
## r15030T 6.90
## X29021NT 8.64
## X32275NT 5.49
## X32275T 8.96
## X40248NT 7.25
## X40248T 12.60
## X51847NT 3.89
##
## Background: After correction 1014 samples and 397
## Endogenous genes have less than 90% missing.
##
## proportion.missing
## X11234NT 0.906
## X13850NT 0.981
## r13850NT 0.915
## X20480NT 0.952
## r20480NT 0.957
## X24013T 0.901
## X26727NT 0.993
## r26727NT 0.995
## X26727T 0.964
## X27657NT 0.990
## r27657NT 0.978
## X28529NT 0.986
## r28529NT 0.932
## X28529T 1.000
## r28529T 0.961
## X28587NT 0.981
## r28587NT 0.998
## r30335NT 1.000
## X30335T 0.952
## r30335T 0.940
## X31988NT 0.911
## blank 0.981
## X35263T 0.976
## X40987T 0.978
## r40987T 0.966
## X43619NT 0.949
## r43619NT 0.964
## r43736NT 0.913
## X43736T 0.990
## X13850T 0.925
## r43736T 0.973
## r45206NT 0.940
## X46716NT 0.995
## rr46716T 0.932
## X49145T 0.940
## r49435NT 0.983
## X49435T 0.937
## X52352T 0.947
## X55438NT 0.908
## X55571NT 0.932
## r56536NT 0.918
## r56536T 0.940
##
## SampleContent: The following samples have sample/rna content greater than
## 3 standard deviations from the mean.
##
## rna.zscore
## X11590T 3.72
## X51179T 4.17
## X39681T 5.78
## X27598T 11.60
## X20339T 8.77
## X40219T 19.90
## X26769T 4.08
##
## log: Setting values less than 1 to 1 in order to calculate the log in positive space.
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.