annotate Normalisation_QCpool.r @ 0:b74d1d533dea draft default tip

planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
author ethevenot
date Thu, 04 Aug 2016 11:40:35 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
1 # Author: jfmartin
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
2 # Modified by : mpetera
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
3 ###############################################################################
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
4 # Correction of analytical effects inter and intra batch on intensities using quality control pooled samples (QC-pools)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
5 # according to the algorithm mentioned by Van der Kloet (J Prot Res 2009).
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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 :
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
8 # "injectionOrder" integer defining the injection order of all samples : QC-pools and analysed samples
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
9 # "sampleType" indicates if defining a sample with "sample" or a QC-pool with "pool"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
10 # NO MISSING DATA are allowed
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
11 # Version 0.91 insertion of ok_norm function to assess correction feasibility
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
12 # Version 0.92 insertion of slope test in ok_norm
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
13 # Version 0.93 name of log file define as a parameter of the correction function
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
15 # Version 0.99 include non linear lowess correction.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
16 # Version 1.00 the corrected result matrix is return transposed in Galaxy
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
21 # Version 2.01 Correction for pools negative values earlier in norm_QCpool
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
26
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
27 ok_norm=function(qcp,qci,spl,spi,method) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
28 # Function used for one ion within one batch to determine whether or not batch correction is possible
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
29 # ok_norm values :
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
30 # 0 : no preliminary-condition problem
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
31 # 1 : standard deviation of QC-pools or samples = 0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
32 # 2 : insufficient number of QC-pools within a batch (n=3 for linear, n=8 for lowess or loess)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
33 # 3 : significant difference between QC-pools' and samples' means
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
34 # 4 : denominator =0 when on 1 pool per batch <> 0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
35 # 5 : (linear regression only) the slopes ratio ?QC-pools/samples? is lower than -0.2
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
36
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
37 ok=0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
38 if (method=="linear") {minQC=3} else {minQC=8}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
39 if (length(qcp)<minQC) { ok=2
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
40 } else {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
41 if (sd(qcp)==0 | sd(spl)==0) { ok=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
42 } else {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
43 cvp= sd(qcp)/mean(qcp); cvs=sd(spl)/mean(spl)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
44 rttest=t.test(qcp,y=spl)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
45 reslsfit=lsfit(qci, qcp)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
46 reslsfitSample=lsfit(spl, spi)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
47 ordori=reslsfit$coefficients[1]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
48 penteB=reslsfit$coefficients[2]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
49 penteS=reslsfitSample$coefficients[2]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
50 # Significant difference between samples and pools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
51 if (rttest$p.value < 0.01) { ok=3
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
52 } else {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
53 # to avoid denominator =0 when on 1 pool per batch <> 0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
54 if (method=="linear" & length(which(((penteB*qci)+ordori)==0))>0 ){ ok=6
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
55 } else {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
56 # different sloop between samples and pools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
57 if (method=="linear" & penteB/penteS < -0.20) { ok=5 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
58 }}}}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
59 ok_norm=ok
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
60 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
61
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
62 plotsituation <- function (x, nbid,outfic="plot_regression.pdf", outres="PreNormSummary.txt",fact="batch",span="none") {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
63 # Check for all ions in every batch if linear or lo(w)ess correction is possible.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
64 # Use ok_norm function and create a file (PreNormSummary.txt) with the error code.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
65 # Also create a pdf file with plots of linear and lo(w)ess regression lines.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
66 # x: dataframe with ions in columns and samples in rows ; x is the result of concatenation of sample metadata file and ions file
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
67 # nbid: number of samples description columns (id and factors) with at least : "batch","injectionOrder","sampleType"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
68 # outfic: name of regression plots pdf file
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
69 # fact: factor to be used as categorical variable for plots and PCA.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
70 indfact =which(dimnames(x)[[2]]==fact)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
71 indtypsamp =which(dimnames(x)[[2]]=="sampleType")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
72 indbatch =which(dimnames(x)[[2]]=="batch")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
73 indinject =which(dimnames(x)[[2]]=="injectionOrder")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
74 lastIon=dim(x)[2]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
75 nbi=lastIon-nbid # Number of ions = total number of columns - number of identifying columns
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
76 nbb=length(levels(x$batch)) # Number of batch = number of levels of "batch" comlumn (factor)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
77 nbs=length(x$sampleType[x$sampleType=="sample"])# Number of samples = number of rows with "sample" value in sampleType
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
78 pdf(outfic,width=27,height=20)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
79 cat(nbi," ions ",nbb," batch(es) \n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
80 cv=data.frame(matrix(0,nrow=nbi,ncol=2))# initialisation de la dataset qui contiendra les CV avant et apres correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
81 pre_bilan=matrix(0,nrow=nbi,ncol=3*nbb) # dataset of ok_norm function results
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
82 for (p in 1:nbi) {# for each ion
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
83 par (mfrow=c(3,nbb),ask=F,cex=1.2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
84 labion=dimnames(x)[[2]][p+nbid]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
85 indpool=which(x$sampleType=="pool") # QCpools subscripts in x
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
86 pools1=x[indpool,p+nbid];
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
87 for (b in 1:nbb) {# for each batch...
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
88 xb=data.frame(x[(x$batch==levels(x$batch)[b]),c(indtypsamp,indinject,p+nbid)])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
89 indpb = which(xb$sampleType=="pool")# QCpools subscripts in the current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
90 indsp = which(xb$sampleType=="sample")# samples subscripts in the current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
91 indbt = which(xb$sampleType=="sample" | xb$sampleType=="pool")# indices de tous les samples d'un batch pools+samples
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
92 normLinearTest=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="linear")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
93 normLoessTest=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="loess")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
94 normLowessTest=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="lowess")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
95 #cat(dimnames(x)[[2]][p+nbid]," batch ",b," loess ",normLoessTest," linear ",normLinearTest,"\n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
96 pre_bilan[ p,3*b-2]=normLinearTest
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
97 pre_bilan[ p,3*b-1]=normLoessTest
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
98 pre_bilan[ p,3*b]=normLowessTest
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
99 if(length(indpb)>1){
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
100 if(span=="none"){span1<-1 ; span2<-2*length(indpool)/nbs}else{span1<-span ; span2<-span}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
101 resloess=loess(xb[indpb,3]~xb[indpb,2],span=span1,degree=2,family="gaussian",iterations=4,surface="direct")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
102 resloessSample=loess(xb[indsp,3]~xb[indsp,2],span=2*length(indpool)/nbs,degree=2,family="gaussian",iterations=4,surface="direct")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
103 reslowess=lowess(xb[indpb,2],xb[indpb,3],f=span2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
104 reslowessSample=lowess(xb[indsp,2],xb[indsp,3])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
105 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
106 plot(xb[indsp,2],xb[indsp,3],pch=16, main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
107 points(xb[indpb,2], xb[indpb,3],pch=5)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
108 points(cbind(resloess$x,resloess$fitted)[order(resloess$x),],type="l",col="orange")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
109 points(cbind(resloessSample$x,resloessSample$fitted)[order(resloessSample$x),],type="l",col="green",lty=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
110 points(reslowess,type="l",col="red"); points(reslowessSample,type="l",col="cyan",lty=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
111 abline(lsfit(xb[indpb,2],xb[indpb,3]),col="blue")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
112 abline(lsfit(xb[indsp,2],xb[indsp,3]),lty=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
113 legend("topright",c("pools","samples"),lty=c(1,2),bty="n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
114 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
115 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
116 # series de plot avant et apres correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
117 minval=min(x[p+nbid]);maxval=max(x[p+nbid])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
118 plot( x$injectionOrder, x[,p+nbid],col=x$batch,ylim=c(minval,maxval),ylab=labion,main=paste("avant correction CV pools=",round(cv[p,1],2)))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
119 suppressWarnings(plot.design( x[c(indtypsamp,indbatch,indfact,p+nbid)],main="effet sur facteurs avant"))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
120 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
121 dev.off()
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
122 pre_bilan=data.frame(pre_bilan)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
123 labion=dimnames(x)[[2]][nbid+1:nbi]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
124 for (i in 1:nbb) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
125 dimnames(pre_bilan)[[2]][3*i-2]=paste("batch",i,"linear")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
126 dimnames(pre_bilan)[[2]][3*i-1]=paste("batch",i,"loess")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
127 dimnames(pre_bilan)[[2]][3*i]=paste("batch",i,"lowess")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
128 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
129 bilan=data.frame(labion,pre_bilan)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
130 write.table(bilan,file=outres,sep="\t",row.names=F,quote=F)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
131 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
132
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
133
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
134 normlowess=function (xb,detail="no",vref=1,b,span=NULL) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
135 # Correction function applied to 1 ion in 1 batch. Use a lowess regression computed on QC-pools in order to correct samples intensity values
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
136 # xb : dataframe for 1 ion in columns and samples in rows.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
137 # vref : reference value (average of ion)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
138 # b : batch subscript
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
139 # nbid: number of samples description columns (id and factors) with at least : "batch","injectionOrder","sampleType"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
140 indpb = which(xb$sampleType=="pool") # pools subscripts of current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
141 indsp = which(xb$sampleType=="sample") # samples of current batch subscripts
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
142 indbt = which(xb$sampleType=="sample" | xb$sampleType=="pool");# batch subscripts of all samples and QC-pools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
143 labion=dimnames(xb)[[2]][3]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
144 newval=xb[[3]] # initialisation of corrected values = intial values
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
145 ind <- 0 # initialisation of correction indicator
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
146 normTodo=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="lowess")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
147 #cat("batch:",b," dim xb=",dim(xb)," ok=",normTodo,"\n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
148 if (normTodo==0) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
149 if(length(span)==0){span2<-2*length(indpb)/length(indsp)}else{span2<-span}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
150 reslowess=lowess(xb[indpb,2],xb[indpb,3],f=span2) # lowess regression with QC-pools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
151 px=xb[indsp,2]; # vector of injectionOrder values only for samples
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
152 for(j in 1:length(indbt)) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
153 if (xb$sampleType[j]=="pool") {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
154 if (reslowess$y[which(indpb==j)]==0) reslowess$y[which(indpb==j)] <- 1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
155 newval[j]=(vref*xb[j,3]) / (reslowess$y[which(indpb==j)])}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
156 else { # for samples, the correction value cor correspond to the nearest QCpools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
157 cor= reslowess$y[which(abs(reslowess$x-px[which(indsp==j)])==min(abs(reslowess$x - px[which(indsp==j)])))]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
158 if (length(cor)>1) {cor=cor[1]}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
159 if (cor <= 0) {cor=vref} # no modification of initial value
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
160 newval[j]=(vref*xb[j,3]) / cor
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
161 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
162 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
163 if (detail=="reg") {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
164 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
165 plot(xb[indsp,2],xb[indsp,3],pch=16,main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
166 points(xb[indpb,2], xb[indpb,3],pch=5)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
167 points(reslowess,type="l",col="red")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
168 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
169 ind <- 1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
170 } else {# if ok_norm <> 0 , we perform a correction based on batch samples average
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
171 moySample=mean(xb[indsp,3]);if (moySample==0) moySample=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
172 newval[indsp] = (vref*xb[indsp,3])/moySample
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
173 if(length(indpb)>0){
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
174 moypool=mean(xb[indpb,3]) ; if (moypool==0) moypool=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
175 newval[indpb] = (vref*xb[indpb,3])/moypool
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
176 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
177 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
178 newval <- list(norm.ion=newval,norm.ind=ind)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
179 return(newval)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
180 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
181
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
182 normlinear <-function (xb,detail="no",vref=1,b) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
183 # Correction function applied to 1 ion in 1 batch. Use a linear regression computed on QC-pools in order to correct samples intensity values
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
184 # xb : dataframe with ions in columns and samples in rows ; x is a result of concatenation of samples metadata file and ions file
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
185 # nbid : number of samples description columns (id and factors) with at least : "batch","injectionOrder","sampleType"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
186 indpb = which(xb$sampleType=="pool")# pools subscripts of current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
187 indsp = which(xb$sampleType=="sample")# samples of current batch subscripts
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
188 indbt = which(xb$sampleType=="sample" | xb$sampleType=="pool") # QCpools and samples of current batch subscripts
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
189 labion=dimnames(xb)[[2]][3]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
190 newval=xb[[3]] # initialisation of corrected values = intial values
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
191 ind <- 0 # initialisation of correction indicator
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
192 normTodo=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="linear")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
193 #cat("batch:",b," ok=",normTodo,"\n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
194 if (normTodo==0) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
195 reslsfit=lsfit(xb[indpb,2],xb[indpb,3]) # linear regression for QCpools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
196 reslsfitSample=lsfit(xb[indsp,2],xb[indsp,3]) # linear regression for samples
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
197 ordori=reslsfit$coefficients[1]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
198 pente=reslsfit$coefficients[2]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
199 if (detail=="reg") {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
200 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
201 plot(xb[indsp,2],xb[indsp,3],pch=16,
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
202 main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
203 points(xb[indpb,2], xb[indpb,3],pch=5)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
204 abline(reslsfit)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
205 abline(reslsfitSample,lty=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
206 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
207 # correction avec remise a l'echelle de la valeur de l'ion (valref)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
208 newval = (vref*xb[indbt,3]) / ((pente * xb[indbt,2]) + ordori)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
209 ind <- 1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
210 } else {# if ok_norm<>0 , we perform a correction based on batch samples average.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
211 moySample=mean(xb[indsp,3]); if (moySample==0) moySample=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
212 newval[indsp] = (vref*xb[indsp,3])/moySample
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
213 if(length(indpb)>0){
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
214 moypool=mean(xb[indpb,3]) ; if (moypool==0) moypool=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
215 newval[indpb] = (vref*xb[indpb,3])/moypool
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
216 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
217 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
218 newval <- list(norm.ion=newval,norm.ind=ind)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
219 return(newval)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
220 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
221
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
222
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
223 normloess <- function (xb,detail="no",vref=1,b,span=NULL) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
224 # Correction function applied to 1 ion in 1 batch.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
225 # Use a loess regression computed on QC-pools in order to correct samples intensity values.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
226 # xb : dataframe for 1 ion in columns and samples in rows.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
227 # detail : level of detail in the outlog file.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
228 # vref : reference value (average of ion)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
229 # b : batch subscript
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
230 indpb = which(xb$sampleType=="pool") # pools subscripts of current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
231 indsp = which(xb$sampleType=="sample") # samples of current batch subscripts
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
232 indbt = which(xb$sampleType=="sample" | xb$sampleType=="pool");# batch subscripts of all samples and QCpools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
233 labion=dimnames(xb)[[2]][3]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
234 newval=xb[[3]] # initialisation of corrected values = intial values
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
235 ind <- 0 # initialisation of correction indicator
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
236 normTodo=ok_norm(xb[indpb,3],xb[indpb,2], xb[indsp,3],xb[indsp,2],method="loess")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
237 #cat("batch:",b," dim xb=",dim(xb)," ok=",normTodo,"\n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
238 if (normTodo==0) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
239 if(length(span)==0){span1<-1}else{span1<-span}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
240 resloess=loess(xb[indpb,3]~xb[indpb,2],span=span1,degree=2,family="gaussian",iterations=4,surface="direct") # loess regression with QCpools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
241 cor=predict(resloess,newdata=xb[,2])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
242 cor[cor<=1] <- 1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
243 newval=(vref*xb[,3]) / cor
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
244 if(length(which(newval>3*(quantile(newval)[4])))>0){newval <- xb[,3]} # no modification of initial value
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
245 else {ind <- 1} # confirmation of correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
246 if (detail=="reg") { # plot
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
247 liminf=min(xb[indbt,3]);limsup=max(xb[indbt,3])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
248 plot(xb[indsp,2],xb[indsp,3],pch=16,main=paste(labion,"batch ",b),ylab="intensity",xlab="injection order",ylim=c(liminf,limsup))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
249 points(xb[indpb,2], xb[indpb,3],pch=5)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
250 points(cbind(resloess$x,resloess$fitted)[order(resloess$x),],type="l",col="red")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
251 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
252 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
253 if (ind==0) {# if ok_norm != 0 or if correction creates outliers, we perform a correction based on batch samples average
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
254 moySample=mean(xb[indsp,3]);if (moySample==0) moySample=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
255 newval[indsp] = (vref*xb[indsp,3])/moySample
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
256 if(length(indpb)>0){
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
257 moypool=mean(xb[indpb,3]) ; if (moypool==0) moypool=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
258 newval[indpb] = (vref*xb[indpb,3])/moypool
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
259 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
260 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
261 newval <- list(norm.ion=newval,norm.ind=ind)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
262 return(newval)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
263 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
264
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
265
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
266
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
267 norm_QCpool <- function (x, nbid, outfic, outlog, fact, metaion, detail="no", NormMoyPool=F, NormInt=F, method="linear",span="none")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
268 {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
269 # Correction applying linear or lowess correction function on all ions for every batch of a dataframe.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
270 # x : dataframe with ions in column and samples' metadata
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
271 # nbid: number of samples description columns (id and factors) with at least : "batch","injectionOrder","sampleType"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
272 # outfic: result corrected intensity file
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
273 # outlog: name of regression plots and PCA pdf file
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
274 # fact : factor to be used as categorical variable for plots and PCA.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
275 # metaion : dataframe of ions' metadata
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
276 # detail : level of detail in the outlog file. detail="no" ACP+histogram of CV before and after correction.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
277 # detail="plot" with plot for all batch before and after correction. detail="reg" with added plots with regression lines for all batches.
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
278 # NormMoyPool : not used
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
279 # NormInt : not used
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
280 # method : regression method to be used to correct : "linear" oo "lowess" oo "loess"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
281 indfact =which(dimnames(x)[[2]]==fact)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
282 indtypsamp=which(dimnames(x)[[2]]=="sampleType")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
283 indbatch =which(dimnames(x)[[2]]=="batch")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
284 indinject =which(dimnames(x)[[2]]=="injectionOrder")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
285 lastIon=dim(x)[2]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
286 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
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
287 nbi=lastIon-nbid # number of ions
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
288 nbb=length(levels(x$batch)) # Number of batch(es) = number of levels of factor "batch" (can be =1)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
289 nbs=length(x$sampleType[x$sampleType=="sample"])# Number of samples
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
290 nbp=length(x$sampleType[x$sampleType=="pool"])# Number of QCpools
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
291 Xn=data.frame(x[,c(1:nbid)],matrix(0,nrow=nbp+nbs,ncol=nbi))# initialisation of the corrected dataframe (=initial dataframe)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
292 dimnames(Xn)=dimnames(x)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
293 cv=data.frame(matrix(0,nrow=nbi,ncol=2))# initialisation of dataframe containing CV before and after correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
294 dimnames(cv)[[2]]=c("avant","apres")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
295 if (detail!="reg" && detail!="plot" && detail!="no") {detail="no"}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
296 pdf(outlog,width=27,height=20)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
297 cat(nbi," ions ",nbb," batch(es) \n")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
298 if (detail=="plot") {par (mfrow=c(4,4),ask=F,cex=1.5)}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
299 res.ind <- matrix(NA,ncol=nbb,nrow=nbi,dimnames=list(dimnames(x)[[2]][-c(1:nbid)],paste("norm.b",1:nbb,sep="")))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
300 for (p in 1:nbi) {# for each ion
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
301 labion=dimnames(x)[[2]][p+nbid]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
302 if (detail == "reg") {par (mfrow=c(4,4),ask=F,cex=1.5)}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
303 indpool=which(x$sampleType=="pool")# QCpools subscripts in all batches
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
304 pools1=x[indpool,p+nbid]; cv[p,1]=sd(pools1)/mean(pools1)# CV before correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
305 for (b in 1:nbb) {# for every batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
306 indpb = which(x$batch==levels(x$batch)[b] & x$sampleType=="pool")# QCpools subscripts of the current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
307 indsp = which(x$batch==levels(x$batch)[b] & x$sampleType=="sample")# samples subscripts of the current batch
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
308 indbt = which(x$batch==levels(x$batch)[b] & (x$sampleType=="pool" | x$sampleType=="sample")) # subscripts of all samples
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
309 # cat(dimnames(x)[[2]][p+nbid]," indsp:",length(indsp)," indpb=",length(indpb)," indbt=",length(indbt)," ")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
310 sub=data.frame(x[(x$batch==levels(x$batch)[b]),c(indtypsamp,indinject,p+nbid)])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
311 if (method=="linear") { res.norm = normlinear(sub,detail,valref[p],b)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
312 } else { if (method=="loess"){ res.norm <- normloess(sub,detail,valref[p],b,span)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
313 } else { if (method=="lowess"){ res.norm <- normlowess(sub,detail,valref[p],b,span)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
314 } else {stop("\n--\nNo valid 'method' argument supplied.\nMust be 'linear','loess' or 'lowess'.\n--\n")}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
315 }}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
316 Xn[indbt,p+nbid] = res.norm[[1]]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
317 res.ind[p,b] <- res.norm[[2]]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
318 # CV batch test : if after normaliszation, CV before < CV after initial values are kept
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
319 # moypoolRaw=mean(x[indpb,p+nbid]) ; if (moypoolRaw==0) moypoolRaw=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
320 # moySampleRaw=mean(x[indsp,p+nbid]); if (moySampleRaw==0) moySampleRaw=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
321 # moypool=mean(Xn[indpb,p+nbid]) ; if (moypool==0) moypool=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
322 # #moySample=mean(Xn[indsp,p+nbid]); if (moySample==0) moySample=1
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
323 # if (sd( Xn[indpb,p+nbid])/moypool>sd(x[indpb,p+nbid])/moypoolRaw) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
324 # Xn[indpb,p+nbid] = (valref[p]*x[indpb,p+nbid])/moypoolRaw
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
325 # Xn[indsp,p+nbid] = (valref[p]*x[indsp,p+nbid])/moySampleRaw
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
326 # }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
327 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
328 Xn[indpool,p+nbid][Xn[indpool,p+nbid]<0] <- 0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
329 pools2=Xn[indpool,p+nbid]; cv[p,2]=sd(pools2)/mean(pools2)# CV apres correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
330 if (detail=="reg" || detail=="plot" ) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
331 # plot before and after correction
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
332 minval=min(cbind(x[p+nbid],Xn[p+nbid]));maxval=max(cbind(x[p+nbid],Xn[p+nbid]))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
333 plot( x$injectionOrder, x[,p+nbid],col=x$batch,ylab=labion,ylim=c(minval,maxval),main=paste("avant correction CV pools=",round(cv[p,1],2)))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
334 points(x$injectionOrder[indpool],x[indpool,p+nbid],col="maroon",pch=".",cex=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
335 plot(Xn$injectionOrder,Xn[,p+nbid],col=x$batch,ylab="",ylim=c(minval,maxval),main=paste("apres correction CV pools=",round(cv[p,2],2)))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
336 points(Xn$injectionOrder[indpool],Xn[indpool,p+nbid],col="maroon",pch=".",cex=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
337 suppressWarnings(plot.design( x[c(indtypsamp,indbatch,indfact,p+nbid)],main="effet sur facteurs avant"))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
338 suppressWarnings(plot.design(Xn[c(indtypsamp,indbatch,indfact,p+nbid)],main="effet sur facteurs apres"))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
339 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
340 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
341 ### Replacement of post correction negative values by 0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
342 Xnn=Xn
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
343 valNulle=0
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
344 for (i in c((nbid+1):dim(Xn)[2])) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
345 cneg=which(Xn[[i]]<0)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
346 Xnn[[i]]=replace(Xn[[i]],cneg,valNulle)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
347 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
348 Xn=Xnn
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
349 write.table(Xn,file=outfic,sep="\t",row.names=F,quote=F)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
350
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
351 if (detail=="reg" || detail=="plot" || detail=="no") {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
352 if (nbi > 3) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
353 par(mfrow=c(3,4),ask=F,cex=1.2) # PCA Plot before/after, normed only and ions plot
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
354 acplight(x[,c(indtypsamp,indbatch,indtypsamp,indfact,(nbid+1):lastIon)],"uv",TRUE)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
355 norm.ion <- which(colnames(Xn)%in%(rownames(res.ind)[which(rowSums(res.ind)>=1)]))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
356 acplight(Xn[,c(indtypsamp,indbatch,indtypsamp,indfact,(nbid+1):lastIon)],"uv",TRUE,norm.ion)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
357 if(length(norm.ion)>0){acplight(Xn[,c(indtypsamp,indbatch,indtypsamp,indfact,norm.ion)],"uv",TRUE)}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
358 par(mfrow=c(1,2),ask=F,cex=1.2) # Before/after boxplot
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
359 cvplot=cv[!is.na(cv[[1]])&!is.na(cv[[2]]),]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
360 if(nrow(cvplot)>0){
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
361 boxplot(cvplot[[1]],ylim=c(min(cvplot),max(cvplot)),main="CV avant")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
362 boxplot(cvplot[[2]],ylim=c(min(cvplot),max(cvplot)),main="CV apres")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
363 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
364 dev.off()
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
365 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
366 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
367 if (nbi<=3) {dev.off()}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
368 # transposed matrix is return (format of the initial matrix with ions in rows)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
369 Xr=Xn[,-c(1:nbid)]; dimnames(Xr)[[1]]=Xn[[1]]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
370 Xr=t(Xr) ; Xr <- data.frame(ions=rownames(Xr),Xr)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
371
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
372 res.norm[[1]] <- Xr ; res.norm[[2]] <- data.frame(metaion,res.ind) ; res.norm[[3]] <- x[,c(1:nbid)]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
373 names(res.norm) <- c("dataMatrix","variableMetadata","sampleMetadata")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
374 return(res.norm)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
375 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
376
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
377
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
378
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
379
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
380
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
381 acplight <- function(ids, scaling="uv", indiv=FALSE,indcol=NULL) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
382 suppressPackageStartupMessages(library(ade4))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
383 suppressPackageStartupMessages(library(pcaMethods))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
384 # fait une ACP sur ids sachant que la colonne 1 contient l'identificateur d'individu
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
385 # la colonne 2:nf contient les facteurs definissant la couleur des individus
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
386 for (i in 1:3) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
387 idss=ids[which(ids[,i+1]!="NA"),]
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
388 idss=data.frame(idss[idss[,i+1]!="",])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
389 classe=as.factor(idss[[i+1]])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
390 idsample=as.character(idss[[1]])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
391 colour=1:length(levels(classe))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
392 ions=as.matrix(idss[,5:dim(idss)[2]])
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
393 # choix du scaling : "uv","none","pareto"
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
394 object=suppressWarnings(prep(ions, scale=scaling, center=TRUE))
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
395 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")}}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
396 # ALGO: nipals,svdImpute, Bayesian, svd, probalistic=F
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
397 result <- pca(object, center=F, method="svd", nPcs=2)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
398 # ADE4 : representation des ellipsoides des individus de chaque classe
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
399 s.class(result@scores, classe, cpoint = 1,xax=1,yax=2,col=colour,sub=sprintf("Scores - PCs %sx%s",1,2), possub="bottomright")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
400 #s.label(result@loadings,label = ions, cpoint = 0, clabel=0.4, xax=1,yax=2,sub="Loadings",possub="bottomright")
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
401 if(i==1){resulti <- result}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
402 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
403 if(indiv) {
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
404 colour <- rep("darkblue",length(resulti@loadings)) ; if(!is.null(indcol)) {colour[-c(indcol)] <- "red"}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
405 plot(resulti@loadings,col=colour,main="Loadings",xaxt="n",yaxt="n",pch=20)
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
406 abline(h=0,v=0)}
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
407 }
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
408
b74d1d533dea planemo upload for repository https://github.com/workflow4metabolomics/batchcorrection.git commit 241fb99a843e13195c5054cd9731e1561f039bde
ethevenot
parents:
diff changeset
409