batchcorrection: Normalisation

annotate Normalisation_QCpool.r @ 2:57edfd3943ab draft

planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit a619f606894efd016387a0b6f6bf0d5addc38bc9-dirty

author	ethevenot
date	Mon, 01 May 2017 08:06:08 -0400
parents	78cb1efd7606
children

rev	line source
0 78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	1 # Author: jfmartin
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	2 # Modified by : mpetera
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	3 ###############################################################################
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	4 # Correction of analytical effects inter and intra batch on intensities using quality control pooled samples (QC-pools)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	5 # according to the algorithm mentioned by Van der Kloet (J Prot Res 2009).
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	6 # Parameters : a dataframe of Ions intensities and an other of samples? metadata which must contains at least the three following columns :
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	7 # "batch" to identify the batches of analyses ; need at least 3 QC-pools for linear adjustment and 8 for lo(w)ess adjustment
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	8 # "injectionOrder" integer defining the injection order of all samples : QC-pools and analysed samples
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	9 # "sampleType" indicates if defining a sample with "sample" or a QC-pool with "pool"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	10 # NO MISSING DATA are allowed
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	11 # Version 0.91 insertion of ok_norm function to assess correction feasibility
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	12 # Version 0.92 insertion of slope test in ok_norm
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	13 # Version 0.93 name of log file define as a parameter of the correction function
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	14 # Version 0.94 Within a batch, test if all QCpools or samples values = 0. Definition of an error code in ok_norm function (see function for details)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	15 # Version 0.99 include non linear lowess correction.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	16 # Version 1.00 the corrected result matrix is return transposed in Galaxy
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	17 # Version 1.01 standard deviation=0 instead of sum of value=0 is used to assess constant data in ok_norm function. Negative values in corrected matrix are converted to 0.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	18 # Version 1.02 plotsituation create a result file with the error code of non execution of correction set by function ok_norm
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	19 # Version 1.03 fix bug in plot with "reg" option. suppression of ok_norm=4 condition if ok_norm function
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	20 # Version 2.00 Addition of loess function, correction indicator, plots ; modification of returned objects' format, some plots' displays and ok_norm ifelse format
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	21 # Version 2.01 Correction for pools negative values earlier in norm_QCpool
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	22 # Version 2.10 Script refreshing ; vocabulary adjustment ; span in parameters for lo(w)ess regression ; conditionning for third line ACP display ; order in loess display
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	23 # Version 2.11 ok1 and ok2 permutation (ok_norm) ; conditional display of regression (plotsituation) ; grouping of linked lignes + conditioning (normX) ; conditioning for CVplot
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	24 # Version 2.20 acplight function added from previous toolBox.R [# Version 1.01 "NA"-coding possibility added in acplight function]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	25 # Version 2.30 addition of suppressWarnings() for known and controlled warnings ; suppression of one useless "cat" message ; change in Rdata names ; 'batch(es)' in cat
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	26 # Version 2.90 change in handling of generated negative and Inf values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	27 # Version 2.91 Plot improvement
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	28
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	29 ok_norm=function(qcp,qci,spl,spi,method) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	30 # Function used for one ion within one batch to determine whether or not batch correction is possible
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	31 # ok_norm values :
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	32 # 0 : no preliminary-condition problem
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	33 # 1 : standard deviation of QC-pools or samples = 0
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	34 # 2 : insufficient number of QC-pools within a batch (n=3 for linear, n=8 for lowess or loess)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	35 # 3 : significant difference between QC-pools' and samples' means
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	36 # 4 : denominator =0 when on 1 pool per batch <> 0
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	37 # 5 : (linear regression only) the slopes ratio ?QC-pools/samples? is lower than -0.2
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	38
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	39 ok=0
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	40 if (method=="linear") {minQC=3} else {minQC=8}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	41 if (length(qcp)<minQC) { ok=2
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	42 } else {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	43 if (sd(qcp)==0 \| sd(spl)==0) { ok=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	44 } else {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	45 cvp= sd(qcp)/mean(qcp); cvs=sd(spl)/mean(spl)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	46 rttest=t.test(qcp,y=spl)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	47 reslsfit=lsfit(qci, qcp)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	48 reslsfitSample=lsfit(spl, spi)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	49 ordori=reslsfit$coefficients[1]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	50 penteB=reslsfit$coefficients[2]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	51 penteS=reslsfitSample$coefficients[2]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	52 # Significant difference between samples and pools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	53 if (rttest$p.value < 0.01) { ok=3
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	54 } else {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	55 # to avoid denominator =0 when on 1 pool per batch <> 0
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	56 if (method=="linear" & length(which(((penteB*qci)+ordori)==0))>0 ){ ok=6
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	57 } else {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	58 # different sloop between samples and pools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	59 if (method=="linear" & penteB/penteS < -0.20) { ok=5 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	60 }}}}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	61 ok_norm=ok
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	62 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	63
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	64 plotsituation <- function (x, nbid,outfic="plot_regression.pdf", outres="PreNormSummary.txt",fact="batch",span="none") {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	65 # Check for all ions in every batch if linear or lo(w)ess correction is possible.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	66 # Use ok_norm function and create a file (PreNormSummary.txt) with the error code.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	67 # Also create a pdf file with plots of linear and lo(w)ess regression lines.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	68 # x: dataframe with ions in columns and samples in rows ; x is the result of concatenation of sample metadata file and ions file
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	69 # nbid: number of samples description columns (id and factors) with at least : "batch","injectionOrder","sampleType"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	70 # outfic: name of regression plots pdf file
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	71 # fact: factor to be used as categorical variable for plots and PCA.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	72 indfact =which(dimnames(x)[[2]]==fact)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	73 indtypsamp =which(dimnames(x)[[2]]=="sampleType")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	74 indbatch =which(dimnames(x)[[2]]=="batch")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	75 indinject =which(dimnames(x)[[2]]=="injectionOrder")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	76 lastIon=dim(x)[2]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	77 nbi=lastIon-nbid # Number of ions = total number of columns - number of identifying columns
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	78 nbb=length(levels(x$batch)) # Number of batch = number of levels of "batch" comlumn (factor)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	79 nbs=length(x$sampleType[x$sampleType=="sample"])# Number of samples = number of rows with "sample" value in sampleType
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	80 pdf(outfic,width=27,height=7*ceiling((nbb+2)/3))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	81 cat(nbi," ions ",nbb," batch(es) \n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	82 cv=data.frame(matrix(0,nrow=nbi,ncol=2))# initialisation de la dataset qui contiendra les CV
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	83 pre_bilan=matrix(0,nrow=nbi,ncol=3*nbb) # dataset of ok_norm function results
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	84 for (p in 1:nbi) {# for each ion
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	85 par (mfrow=c(ceiling((nbb+2)/3),3),ask=F,cex=1.2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	86 labion=dimnames(x)[[2]][p+nbid]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	87 indpool=which(x$sampleType=="pool") # QCpools subscripts in x
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	88 pools1=x[indpool,p+nbid]; cv[p,1]=sd(pools1)/mean(pools1)# CV before correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	89 for (b in 1:nbb) {# for each batch...
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	90 xb=data.frame(x[(x$batch==levels(x$batch)[b]),c(indtypsamp,indinject,p+nbid)])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	91 indpb = which(xb$sampleType=="pool")# QCpools subscripts in the current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	92 indsp = which(xb$sampleType=="sample")# samples subscripts in the current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	93 indbt = which(xb$sampleType=="sample" \| xb$sampleType=="pool")# indices de tous les samples d'un batch pools+samples
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	94 normLinearTest=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="linear")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	95 normLoessTest=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="loess")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	96 normLowessTest=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="lowess")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	97 #cat(dimnames(x)[[2]][p+nbid]," batch ",b," loess ",normLoessTest," linear ",normLinearTest,"\n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	98 pre_bilan[ p,3*b-2]=normLinearTest
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	99 pre_bilan[ p,3*b-1]=normLoessTest
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	100 pre_bilan[ p,3*b]=normLowessTest
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	101 if(length(indpb)>1){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	102 if(span=="none"){span1<-1 ; span2<-2*length(indpool)/nbs}else{span1<-span ; span2<-span}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	103 resloess=loess(xb[indpb,3]~xb[indpb,2],span=span1,degree=2,family="gaussian",iterations=4,surface="direct")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	104 resloessSample=loess(xb[indsp,3]~xb[indsp,2],span=2*length(indpool)/nbs,degree=2,family="gaussian",iterations=4,surface="direct")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	105 reslowess=lowess(xb[indpb,2],xb[indpb,3],f=span2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	106 reslowessSample=lowess(xb[indsp,2],xb[indsp,3])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	107 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	108 plot(xb[indsp,2],xb[indsp,3],pch=16, main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	109 points(xb[indpb,2], xb[indpb,3],pch=5)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	110 points(cbind(resloess$x,resloess$fitted)[order(resloess$x),],type="l",col="green3")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	111 points(cbind(resloessSample$x,resloessSample$fitted)[order(resloessSample$x),],type="l",col="green3",lty=2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	112 points(reslowess,type="l",col="red"); points(reslowessSample,type="l",col="red",lty=2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	113 abline(lsfit(xb[indpb,2],xb[indpb,3]),col="blue")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	114 abline(lsfit(xb[indsp,2],xb[indsp,3]),lty=2,col="blue")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	115 legend("topleft",c("pools","samples"),lty=c(1,2),bty="n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	116 legend("topright",c("linear","lowess","loess"),lty=1,col=c("blue","red","green3"),bty="n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	117 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	118 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	119 # series de plot avant et apres correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	120 minval=min(x[p+nbid]);maxval=max(x[p+nbid])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	121 plot( x$injectionOrder, x[,p+nbid],col=x$batch,ylim=c(minval,maxval),ylab=labion,
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	122 main=paste0("before correction (CV for pools = ",round(cv[p,1],2),")"))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	123 suppressWarnings(plot.design( x[c(indtypsamp,indbatch,indfact,p+nbid)],main="factors effect before correction"))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	124 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	125 dev.off()
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	126 pre_bilan=data.frame(pre_bilan)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	127 labion=dimnames(x)[[2]][nbid+1:nbi]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	128 for (i in 1:nbb) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	129 dimnames(pre_bilan)[[2]][3*i-2]=paste("batch",i,"linear")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	130 dimnames(pre_bilan)[[2]][3*i-1]=paste("batch",i,"loess")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	131 dimnames(pre_bilan)[[2]][3*i]=paste("batch",i,"lowess")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	132 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	133 bilan=data.frame(labion,pre_bilan)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	134 write.table(bilan,file=outres,sep="\t",row.names=F,quote=F)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	135 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	136
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	137
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	138 normlowess=function (xb,detail="no",vref=1,b,span=NULL) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	139 # Correction function applied to 1 ion in 1 batch. Use a lowess regression computed on QC-pools in order to correct samples intensity values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	140 # xb : dataframe for 1 ion in columns and samples in rows.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	141 # vref : reference value (average of ion)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	142 # b : batch subscript
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	143 # nbid: number of samples description columns (id and factors) with at least : "batch","injectionOrder","sampleType"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	144 indpb = which(xb$sampleType=="pool") # pools subscripts of current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	145 indsp = which(xb$sampleType=="sample") # samples of current batch subscripts
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	146 indbt = which(xb$sampleType=="sample" \| xb$sampleType=="pool");# batch subscripts of all samples and QC-pools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	147 labion=dimnames(xb)[[2]][3]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	148 newval=xb[[3]] # initialisation of corrected values = intial values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	149 ind <- 0 # initialisation of correction indicator
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	150 normTodo=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="lowess")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	151 #cat("batch:",b," dim xb=",dim(xb)," ok=",normTodo,"\n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	152 if (normTodo==0) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	153 if(length(span)==0){span2<-2*length(indpb)/length(indsp)}else{span2<-span}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	154 reslowess=lowess(xb[indpb,2],xb[indpb,3],f=span2) # lowess regression with QC-pools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	155 px=xb[indsp,2]; # vector of injectionOrder values only for samples
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	156 for(j in 1:length(indbt)) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	157 if (xb$sampleType[j]=="pool") {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	158 if (reslowess$y[which(indpb==j)]==0) reslowess$y[which(indpb==j)] <- 1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	159 newval[j]=(vref*xb[j,3]) / (reslowess$y[which(indpb==j)])}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	160 else { # for samples, the correction value cor correspond to the nearest QCpools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	161 cor= reslowess$y[which(abs(reslowess$x-px[which(indsp==j)])==min(abs(reslowess$x - px[which(indsp==j)])))]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	162 if (length(cor)>1) {cor=cor[1]}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	163 if (cor <= 0) {cor=vref} # no modification of initial value
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	164 newval[j]=(vref*xb[j,3]) / cor
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	165 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	166 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	167 if (detail=="reg") {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	168 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	169 plot(xb[indsp,2],xb[indsp,3],pch=16,main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	170 points(xb[indpb,2], xb[indpb,3],pch=5)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	171 points(reslowess,type="l",col="red")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	172 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	173 ind <- 1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	174 } else {# if ok_norm <> 0 , we perform a correction based on batch samples average
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	175 moySample=mean(xb[indsp,3]);if (moySample==0) moySample=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	176 newval[indsp] = (vref*xb[indsp,3])/moySample
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	177 if(length(indpb)>0){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	178 moypool=mean(xb[indpb,3]) ; if (moypool==0) moypool=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	179 newval[indpb] = (vref*xb[indpb,3])/moypool
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	180 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	181 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	182 newval <- list(norm.ion=newval,norm.ind=ind)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	183 return(newval)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	184 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	185
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	186 normlinear <- function (xb,detail="no",vref=1,b,valneg=0) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	187 # Correction function applied to 1 ion in 1 batch.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	188 # Use a linear regression computed on QC-pools in order to correct samples intensity values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	189 # xb: dataframe with ions in columns and samples in rows; x is a result of concatenation of sample metadata file and ion file
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	190 # nbid: number of sample description columns (id and factors) with at least "batch", "injectionOrder" and "sampleType"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	191 # b: which batch it is
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	192 # valneg: to determine what to do with generated negative and Inf values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	193 indpb = which(xb$sampleType=="pool")# pools subscripts of current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	194 indsp = which(xb$sampleType=="sample")# samples of current batch subscripts
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	195 indbt = which(xb$sampleType=="sample" \| xb$sampleType=="pool") # QCpools and samples of current batch subscripts
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	196 labion=dimnames(xb)[[2]][3]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	197 newval=xb[[3]] # initialisation of corrected values = intial values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	198 ind <- 0 # initialisation of correction indicator
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	199 normTodo=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="linear")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	200 if (normTodo==0) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	201 ind <- 1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	202 reslsfit=lsfit(xb[indpb,2],xb[indpb,3]) # linear regression for QCpools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	203 reslsfitSample=lsfit(xb[indsp,2],xb[indsp,3]) # linear regression for samples
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	204 ordori=reslsfit$coefficients[1]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	205 pente=reslsfit$coefficients[2]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	206 if (detail=="reg") {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	207 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	208 plot(xb[indsp,2],xb[indsp,3],pch=16,
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	209 main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	210 points(xb[indpb,2], xb[indpb,3],pch=5)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	211 abline(reslsfit)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	212 abline(reslsfitSample,lty=2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	213 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	214 # correction with rescaling of ion global intensity (vref)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	215 newval = (vrefxb[indbt,3]) / (pente (xb[indbt,2]) + ordori)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	216 newval[which((pente * (xb[indbt,2]) + ordori)<1)] <- -1 # to handle cases where 0<denominator<1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	217 # handling if any negative values (or null denominators)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	218 if(length(which((newval==Inf)\|(newval<0)))!=0){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	219 toajust <- which((newval==Inf)\|(newval<0))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	220 if(valneg=="NA"){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	221 newval[toajust] <- NA
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	222 } else {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	223 newval[toajust] <- vref * (xb[indbt,3][toajust]) / mean(xb[indbt,3])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	224 ### Other possibility
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	225 ## if(pente>0){ # slope orientation
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	226 ## newval[toajust]<-(vref(xb[indbt,3][toajust]))/(penteceiling(-ordori/pente+1.00001)+ordori)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	227 ## }else{
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	228 ## newval[toajust]<-(vref(xb[indbt,3][toajust]))/(pentefloor(-ordori/pente-1.00001)+ordori)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	229 ## }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	230 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	231 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	232 } else {# if ok_norm!=0 , we perform a correction based on batch samples average.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	233 moySample=mean(xb[indsp,3]); if (moySample==0) moySample=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	234 newval[indsp] = (vref*xb[indsp,3])/moySample
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	235 if(length(indpb)>0){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	236 moypool=mean(xb[indpb,3]) ; if (moypool==0) moypool=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	237 newval[indpb] = (vref*xb[indpb,3])/moypool
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	238 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	239 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	240 newval <- list(norm.ion=newval,norm.ind=ind)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	241 return(newval)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	242 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	243
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	244
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	245 normloess <- function (xb,detail="no",vref=1,b,span=NULL) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	246 # Correction function applied to 1 ion in 1 batch.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	247 # Use a loess regression computed on QC-pools in order to correct samples intensity values.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	248 # xb : dataframe for 1 ion in columns and samples in rows.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	249 # detail : level of detail in the outlog file.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	250 # vref : reference value (average of ion)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	251 # b : batch subscript
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	252 indpb = which(xb$sampleType=="pool") # pools subscripts of current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	253 indsp = which(xb$sampleType=="sample") # samples of current batch subscripts
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	254 indbt = which(xb$sampleType=="sample" \| xb$sampleType=="pool");# batch subscripts of all samples and QCpools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	255 labion=dimnames(xb)[[2]][3]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	256 newval=xb[[3]] # initialisation of corrected values = intial values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	257 ind <- 0 # initialisation of correction indicator
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	258 normTodo=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="loess")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	259 #cat("batch:",b," dim xb=",dim(xb)," ok=",normTodo,"\n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	260 if (normTodo==0) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	261 if(length(span)==0){span1<-1}else{span1<-span}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	262 resloess=loess(xb[indpb,3]~xb[indpb,2],span=span1,degree=2,family="gaussian",iterations=4,surface="direct") # loess regression with QCpools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	263 cor=predict(resloess,newdata=xb[,2])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	264 cor[cor<=1] <- 1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	265 newval=(vref*xb[,3]) / cor
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	266 if(length(which(newval>3*(quantile(newval)[4])))>0){ # in this case no modification of initial value
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	267 newval <- xb[,3]} else {ind <- 1} # confirmation of correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	268 if ((detail=="reg")&(ind==1)) { # plot
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	269 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	270 plot(xb[indsp,2],xb[indsp,3],pch=16,main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	271 points(xb[indpb,2], xb[indpb,3],pch=5)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	272 points(cbind(resloess$x,resloess$fitted)[order(resloess$x),],type="l",col="red")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	273 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	274 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	275 if (ind==0) {# if ok_norm != 0 or if correction creates outliers, we perform a correction based on batch samples average
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	276 moySample=mean(xb[indsp,3]);if (moySample==0) moySample=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	277 newval[indsp] = (vref*xb[indsp,3])/moySample
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	278 if(length(indpb)>0){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	279 moypool=mean(xb[indpb,3]) ; if (moypool==0) moypool=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	280 newval[indpb] = (vref*xb[indpb,3])/moypool
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	281 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	282 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	283 newval <- list(norm.ion=newval,norm.ind=ind)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	284 return(newval)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	285 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	286
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	287
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	288
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	289 norm_QCpool <- function (x, nbid, outlog, fact, metaion, detail="no", NormMoyPool=F, NormInt=F, method="linear",span="none",valNull="0")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	290 {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	291 ### Correction applying linear or lo(w)ess correction function on all ions for every batch of a dataframe.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	292 # x: dataframe with ions in column and samples' metadata
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	293 # nbid: number of sample description columns (id and factors) with at least "batch", "injectionOrder", "sampleType"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	294 # outlog: name of regression plots and PCA pdf file
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	295 # fact: factor to be used as categorical variable for plots
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	296 # metaion: dataframe of ions' metadata
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	297 # detail: level of detail in the outlog file. detail="no" ACP + boxplot of CV before and after correction.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	298 # detail="plot" with plot for all batch before and after correction.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	299 # detail="reg" with added plots with regression lines for all batches.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	300 # NormMoyPool: not used
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	301 # NormInt: not used
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	302 # method: regression method to be used to correct : "linear" or "lowess" or "loess"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	303 # valNull: to determine what to do with negatively estimated intensities
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	304 indfact =which(dimnames(x)[[2]]==fact)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	305 indtypsamp=which(dimnames(x)[[2]]=="sampleType")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	306 indbatch =which(dimnames(x)[[2]]=="batch")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	307 indinject =which(dimnames(x)[[2]]=="injectionOrder")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	308 lastIon=dim(x)[2]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	309 valref=apply(as.matrix(x[,(nbid+1):(lastIon)]),2,mean) # reference value for each ion used to still have the same rought size of values
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	310 nbi=lastIon-nbid # number of ions
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	311 nbb=length(levels(x$batch)) # Number of batch(es) = number of levels of factor "batch" (can be =1)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	312 nbs=length(x$sampleType[x$sampleType=="sample"])# Number of samples
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	313 nbp=length(x$sampleType[x$sampleType=="pool"])# Number of QCpools
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	314 Xn=data.frame(x[,c(1:nbid)],matrix(0,nrow=nbp+nbs,ncol=nbi))# initialisation of the corrected dataframe (=initial dataframe)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	315 dimnames(Xn)=dimnames(x)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	316 cv=data.frame(matrix(0,nrow=nbi,ncol=2))# initialisation of dataframe containing CV before and after correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	317 dimnames(cv)[[2]]=c("avant","apres")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	318 if (detail!="reg" && detail!="plot" && detail!="no") {detail="no"}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	319 pdf(outlog,width=27,height=20)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	320 cat(nbi," ions ",nbb," batch(es) \n")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	321 if (detail=="plot") {if(nbb<6){par(mfrow=c(3,3),ask=F,cex=1.5)}else{par(mfrow=c(4,4),ask=F,cex=1.5)}}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	322 res.ind <- matrix(NA,ncol=nbb,nrow=nbi,dimnames=list(dimnames(x)[[2]][-c(1:nbid)],paste("norm.b",1:nbb,sep="")))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	323 for (p in 1:nbi) {# for each ion
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	324 labion=dimnames(x)[[2]][p+nbid]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	325 if (detail == "reg") {if(nbb<6){par(mfrow=c(3,3),ask=F,cex=1.5)}else{par(mfrow=c(4,4),ask=F,cex=1.5)}}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	326 indpool=which(x$sampleType=="pool")# QCpools subscripts in all batches
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	327 pools1=x[indpool,p+nbid]; cv[p,1]=sd(pools1)/mean(pools1)# CV before correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	328 for (b in 1:nbb) {# for every batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	329 indpb = which(x$batch==levels(x$batch)[b] & x$sampleType=="pool")# QCpools subscripts of the current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	330 indsp = which(x$batch==levels(x$batch)[b] & x$sampleType=="sample")# samples subscripts of the current batch
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	331 indbt = which(x$batch==levels(x$batch)[b] & (x$sampleType=="pool" \| x$sampleType=="sample")) # subscripts of all samples
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	332 # cat(dimnames(x)[[2]][p+nbid]," indsp:",length(indsp)," indpb=",length(indpb)," indbt=",length(indbt)," ")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	333 sub=data.frame(x[(x$batch==levels(x$batch)[b]),c(indtypsamp,indinject,p+nbid)])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	334 if (method=="linear") { res.norm = normlinear(sub,detail,valref[p],b,valNull)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	335 } else { if (method=="loess"){ res.norm <- normloess(sub,detail,valref[p],b,span)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	336 } else { if (method=="lowess"){ res.norm <- normlowess(sub,detail,valref[p],b,span)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	337 } else {stop("\n--\nNo valid 'method' argument supplied.\nMust be 'linear','loess' or 'lowess'.\n--\n")}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	338 }}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	339 Xn[indbt,p+nbid] = res.norm[[1]]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	340 res.ind[p,b] <- res.norm[[2]]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	341 # CV batch test : if after normaliszation, CV before < CV after initial values are kept
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	342 # moypoolRaw=mean(x[indpb,p+nbid]) ; if (moypoolRaw==0) moypoolRaw=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	343 # moySampleRaw=mean(x[indsp,p+nbid]); if (moySampleRaw==0) moySampleRaw=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	344 # moypool=mean(Xn[indpb,p+nbid]) ; if (moypool==0) moypool=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	345 # #moySample=mean(Xn[indsp,p+nbid]); if (moySample==0) moySample=1
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	346 # if (sd( Xn[indpb,p+nbid])/moypool>sd(x[indpb,p+nbid])/moypoolRaw) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	347 # Xn[indpb,p+nbid] = (valref[p]*x[indpb,p+nbid])/moypoolRaw
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	348 # Xn[indsp,p+nbid] = (valref[p]*x[indsp,p+nbid])/moySampleRaw
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	349 # }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	350 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	351 Xn[indpool,p+nbid][Xn[indpool,p+nbid]<0] <- 0
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	352 pools2=Xn[indpool,p+nbid]; cv[p,2]=sd(pools2,na.rm=TRUE)/mean(pools2,na.rm=TRUE)# CV apres correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	353 if (detail=="reg" \|\| detail=="plot" ) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	354 # plot before and after correction
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	355 minval=min(cbind(x[p+nbid],Xn[p+nbid]),na.rm=TRUE);maxval=max(cbind(x[p+nbid],Xn[p+nbid]),na.rm=TRUE)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	356 plot( x$injectionOrder, x[,p+nbid],col=x$batch,ylab=labion,ylim=c(minval,maxval),
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	357 main=paste0("before correction (CV for pools = ",round(cv[p,1],2),")"))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	358 points(x$injectionOrder[indpool],x[indpool,p+nbid],col="maroon",pch=".",cex=2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	359 plot(Xn$injectionOrder,Xn[,p+nbid],col=x$batch,ylab="",ylim=c(minval,maxval),
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	360 main=paste0("after correction (CV for pools = ",round(cv[p,2],2),")"))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	361 points(Xn$injectionOrder[indpool],Xn[indpool,p+nbid],col="maroon",pch=".",cex=2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	362 suppressWarnings(plot.design( x[c(indtypsamp,indbatch,indfact,p+nbid)],main="factors effect before correction"))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	363 suppressWarnings(plot.design(Xn[c(indtypsamp,indbatch,indfact,p+nbid)],main="factors effect after correction"))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	364 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	365 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	366 ### Replacement of post correction negative values by chosen value
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	367 Xnn=Xn
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	368 for (i in c((nbid+1):dim(Xn)[2])) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	369 cneg=which(Xn[[i]]<0)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	370 Xnn[[i]]=replace(Xn[[i]],cneg,as.numeric(valNull))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	371 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	372 Xn=Xnn
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	373
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	374 if (detail=="reg" \|\| detail=="plot" \|\| detail=="no") {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	375 if (nbi > 3) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	376 par(mfrow=c(3,4),ask=F,cex=1.2) # PCA Plot before/after, normed only and ions plot
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	377 acplight(x[,c(indtypsamp,indbatch,indtypsamp,indfact,(nbid+1):lastIon)],"uv",TRUE)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	378 norm.ion <- which(colnames(Xn)%in%(rownames(res.ind)[which(rowSums(res.ind)>=1)]))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	379 acplight(Xn[,c(indtypsamp,indbatch,indtypsamp,indfact,(nbid+1):lastIon)],"uv",TRUE,norm.ion)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	380 if(length(norm.ion)>0){acplight(Xn[,c(indtypsamp,indbatch,indtypsamp,indfact,norm.ion)],"uv",TRUE)}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	381 par(mfrow=c(1,2),ask=F,cex=1.2) # Before/after boxplot
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	382 cvplot=cv[!is.na(cv[[1]])&!is.na(cv[[2]]),]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	383 if(nrow(cvplot)>0){
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	384 boxplot(cvplot[[1]],ylim=c(min(cvplot),max(cvplot)),main="CV before correction")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	385 boxplot(cvplot[[2]],ylim=c(min(cvplot),max(cvplot)),main="CV after correction")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	386 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	387 dev.off()
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	388 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	389 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	390 if (nbi<=3) {dev.off()}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	391 # transposed matrix is return (format of the initial matrix with ions in rows)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	392 Xr=Xn[,-c(1:nbid)]; dimnames(Xr)[[1]]=Xn[[1]]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	393 Xr=t(Xr) ; Xr <- data.frame(ions=rownames(Xr),Xr)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	394
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	395 res.norm[[1]] <- Xr ; res.norm[[2]] <- data.frame(metaion,res.ind) ; res.norm[[3]] <- x[,c(1:nbid)]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	396 names(res.norm) <- c("dataMatrix","variableMetadata","sampleMetadata")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	397 return(res.norm)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	398 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	399
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	400
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	401
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	402
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	403
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	404 acplight <- function(ids, scaling="uv", indiv=FALSE,indcol=NULL) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	405 suppressPackageStartupMessages(library(ade4))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	406 suppressPackageStartupMessages(library(pcaMethods))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	407 # Make a PCA and plot scores and loadings.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	408 # First column must contain samples' identifiers.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	409 # Columns 2 to 4 contain factors to colour the plots.
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	410 for (i in 1:3) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	411 idss=ids[which(ids[,i+1]!="NA"),]
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	412 idss=data.frame(idss[idss[,i+1]!="",])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	413 classe=as.factor(idss[[i+1]])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	414 idsample=as.character(idss[[1]])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	415 colour=1:length(levels(classe))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	416 ions=as.matrix(idss[,5:dim(idss)[2]])
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	417 # Removing ions containing NA (not compatible with standard PCA)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	418 ions=t(na.omit(t(ions)))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	419 if(i==1){if(ncol(ions)!=(ncol(idss)-4)){cat("Note:",(ncol(idss)-4)-ncol(ions),"ions were ignored for PCA display due to NA in intensities.\n")}}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	420 # Scaling choice: "uv","none","pareto"
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	421 object=suppressWarnings(prep(ions, scale=scaling, center=TRUE))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	422 if(i==1){if(length(which(apply(ions,2,var)==0))>0){cat("Warning: there are",length(which(apply(ions,2,var)==0)),"constant ions.\n")}}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	423 # ALGO: nipals,svdImpute, Bayesian, svd, probalistic=F
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	424 result <- pca(object, center=F, method="svd", nPcs=2)
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	425 # ADE4 : to plot samples' ellipsoid for each class
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	426 s.class(result@scores, classe, cpoint = 1,xax=1,yax=2,col=colour,sub=sprintf("Scores - PCs %sx%s",1,2), possub="bottomright")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	427 #s.label(result@loadings,label = ions, cpoint = 0, clabel=0.4, xax=1,yax=2,sub="Loadings",possub="bottomright")
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	428 if(i==1){resulti <- result}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	429 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	430 if(indiv) {
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	431 colour <- rep("darkblue",length(resulti@loadings)) ; if(!is.null(indcol)) {colour[-c(indcol)] <- "red"}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	432 plot(resulti@loadings,col=colour,main="Loadings",xaxt="n",yaxt="n",pch=20,
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	433 xlab=bquote(PC1-R^2==.(resulti@R2[1])),ylab=bquote(PC2 - R^2 == .(resulti@R2[2])))
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	434 abline(h=0,v=0)}
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	435 }
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	436
78cb1efd7606 planemo upload for repository https://github.com/workflow4metabolomics/batch_correction.git commit 400138235741cbb21fd7c7ddeeb572235fa769c2-dirty ethevenot parents: diff changeset	437

Mercurial > repos > ethevenot > batchcorrection

annotate Normalisation_QCpool.r @ 2:57edfd3943ab draft