-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy path08_data_process_modules.R
4759 lines (3642 loc) · 246 KB
/
08_data_process_modules.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
.checkParamsOld = function(raw, processout, normalization, fillIncompleteRows,
logTrans, summaryMethod, cutoffCensored, MBimpute,
censoredInt, nameStandards, finalfile) {
## make case-insensitive for function options
normalization <- toupper(normalization)
## Check correct option or input
## check right column in input
requiredinput <- c("ProteinName", "PeptideSequence", "PrecursorCharge",
"FragmentIon", "ProductCharge", "IsotopeLabelType",
"Condition", "BioReplicate", "Run", "Intensity")
## [THT: disambiguation for PeptideSequence & PeptideModifiedSequence - begin]
## PeptideModifiedSequence is also allowed.
requiredInputUpper <- toupper(requiredinput)
providedInputUpper <- toupper(colnames(raw))
if (all(requiredInputUpper %in% providedInputUpper)) {
processout <- rbind(processout, c("The required input : provided - okay"))
write.table(processout, file = finalfile, row.names = FALSE)
} else if (all(setdiff(requiredInputUpper, "PEPTIDESEQUENCE") %in% providedInputUpper) && "PEPTIDEMODIFIEDSEQUENCE" %in% providedInputUpper) {
processout <- rbind(processout, c("The required input : provided - okay"))
write.table(processout, file = finalfile, row.names = FALSE)
# if PeptideModifiedSequence is provided instead of PeptideSequence,
# change the column name as PeptideSequence
colnames(raw)[which(providedInputUpper == "PEPTIDEMODIFIEDSEQUENCE")] <- "PeptideSequence"
} else {
missedInput <- which(!(requiredInputUpper %in% providedInputUpper))
processout <- rbind(processout, c(paste("ERROR : The required input : ",
paste(requiredinput[missedInput], collapse = ", "),
" are not provided in input - stop")))
write.table(processout, file = finalfile, row.names = FALSE)
stop("Please check the required input. The required input needs (ProteinName, PeptideSequence (or PeptideModifiedSequence), PrecursorCharge, FragmentIon, ProductCharge, IsotopeLabelType, Condition, BioReplicate, Run, Intensity)")
}
## [THT: disambiguation for PeptideSequence & PeptideModifiedSequence - end]
## check logTrans is 2,10 or not
if (logTrans!=2 & logTrans!=10) {
processout <- rbind(processout,c("ERROR : Logarithm transformation : log2 or log10 only - stop"))
write.table(processout, file=finalfile,row.names=FALSE)
stop("Only log2 or log10 are posssible.\n")
}
## check no row for some feature : balanced structure or not
if (!(fillIncompleteRows==TRUE | fillIncompleteRows==FALSE) | !is.logical(fillIncompleteRows)) {
processout <- rbind(processout, c(paste("The required input - fillIncompleteRows : 'fillIncompleteRows' value is wrong. It should be either TRUE or FALSE. - stop")))
write.table(processout, file=finalfile, row.names=FALSE)
stop("'fillIncompleteRows' must be one of TRUE or FALSE as a logical value.")
}
## check input for summaryMethod
if (sum(summaryMethod == c("linear", "TMP")) == 0) {
processout <- rbind(processout,c("The required input - summaryMethod : 'summaryMethod' value is wrong. It should be one of 'TMP' or 'linear'. - stop"))
write.table(processout, file=finalfile, row.names=FALSE)
stop("'summaryMethod' value is wrong. It should be one of 'TMP' or 'linear'.")
} else {
processout <- rbind(processout, c(paste("summaryMethod : ", as.character(summaryMethod), sep="")))
write.table(processout, file=finalfile, row.names=FALSE)
}
## check input for cutoffCensored
if (sum(cutoffCensored==c("minFeature","minRun","minFeatureNRun"))==0) {
processout <- rbind(processout,c("The required input - cutoffCensored : 'cutoffCensored' value is wrong. It should be one of 'minFeature','minRun','minFeatureNRun'. - stop"))
write.table(processout, file=finalfile, row.names=FALSE)
stop("'cutoffCensored' value is wrong. It should be one of 'minFeature','minRun','minFeatureNRun'.")
} else {
processout <- rbind(processout,c(paste("cutoffCensored : ",as.character(cutoffCensored), sep="")))
write.table(processout, file=finalfile, row.names=FALSE)
}
## check input for censoredInt
if (sum(censoredInt == c("0", "NA")) == 0 & !is.null(censoredInt)) {
processout <- rbind(processout,c("The required input - censoredInt : 'censoredInt' value is wrong.
It should be one of '0','NA', NULL. - stop"))
write.table(processout, file=finalfile, row.names=FALSE)
stop("'censoredInt' value is wrong. It should be one of '0','NA',NULL.")
} else {
processout <- rbind(processout, c(paste("censoredInt : ", as.character(censoredInt), sep="")))
write.table(processout, file=finalfile, row.names=FALSE)
}
## check input for censoredInt and MBimpute
if ( summaryMethod == 'TMP' & MBimpute & is.null(censoredInt) ) {
processout <- rbind(processout, c("The rcombination of equired input -
censoredInt and MBimpute : 'censoredInt=NULL' has no censored missing values.
Imputation will not be performed.- stop"))
write.table(processout, file=finalfile, row.names=FALSE)
stop("'censoredInt=NULL' means that dataset has no censored missing value and MSstats will not impute.
But, 'MBimpute=TRUE' is selected. Please replace by 'MBimpute=FALSE' or censoredInt='NA' or '0'")
}
## [THT: if (!all(normalization %in% c("NONE", "FALSE", "EQUALIZEMEDIANS", "QUANTILE", "GLOBALSTANDARDS")))]
## [THT: send a warning message if the user mixes "NONE" with any of the last three choices]
if (!(normalization=="NONE" | normalization=="FALSE" |
normalization=="EQUALIZEMEDIANS" | normalization=="QUANTILE" |
normalization=="GLOBALSTANDARDS")) {
processout <- rbind(processout,c(paste("The required input - normalization : 'normalization' value is wrong. - stop")))
write.table(processout, file=finalfile, row.names=FALSE)
stop("'normalization' must be one of \"None\", \"FALSE\", \"equalizeMedians\",
\"quantile\", or \"globalStandards\". Please assign 'normalization' again.")
}
## need the names of global standards
if (!is.element("NONE",normalization) &
!is.element("FALSE",normalization) &
is.element("GLOBALSTANDARDS",normalization) &
is.null(nameStandards)) {
processout <- rbind(processout, c("ERROR : For normalization with global standards,
the names of global standards are needed. Please add 'nameStandards' input."))
write.table(processout, file=finalfile,row.names=FALSE)
stop ("For normalization with global standards, the names of global standards are needed.
Please add 'nameStandards' input." )
}
processout
}
.checkDataOld = function(raw, processout, finalfile) {
## check whether class of intensity is factor or chaterer, if yes, neec to chage as numeric
if (is.factor(raw$Intensity) | is.character(raw$Intensity)) {
suppressWarnings(raw$Intensity <- as.numeric(as.character(raw$Intensity)))
}
## annotation information :
if ( any(is.na(raw$Run)) ) {
processout <- rbind(processout, c("ERROR : There is missing information in 'Run' column. Please check 'Run' column."))
write.table(processout, file=finalfile, row.names=FALSE)
stop ("There is missing information in 'Run' column. Please check 'Run' column." )
}
if ( any(is.na(raw$BioReplicate)) ) {
processout <- rbind(processout, c("ERROR : There is missing information in 'BioReplicate' column.
Please check 'BioReplicate' column."))
write.table(processout, file=finalfile, row.names=FALSE)
stop ("There is missing information in 'BioReplicate' column. Please check 'BioReplicate' column." )
}
if ( any(is.na(raw$Condition)) ) {
processout <- rbind(processout, c("ERROR : There is missing information in 'Condition' column.
Please check 'Condition' column."))
write.table(processout, file=finalfile, row.names=FALSE)
stop ("There is missing information in 'Condition' column. Please check 'Condition' column." )
}
## make letters case-insensitive
colnames(raw) <- toupper(colnames(raw))
if( any(is.element(colnames(raw), 'FRACTION')) ) {
fraction <- 'FRACTION'
} else {
fraction <- NULL
}
if( any(is.element(colnames(raw), 'TECHREPLICATE')) ) {
tech.rep <- 'TECHREPLICATE'
} else {
tech.rep <- NULL
}
require.col <- c("PROTEINNAME", "PEPTIDESEQUENCE", "PRECURSORCHARGE",
"FRAGMENTION", "PRODUCTCHARGE", "ISOTOPELABELTYPE",
"CONDITION", "BIOREPLICATE", "RUN", "INTENSITY", fraction, tech.rep)
raw.temp <- raw[, require.col]
## before remove, get PeptideSequence and combination of PeptideSequence and precursorcharge for global standard normalization
rm(raw)
## assign peptide, transition
raw.temp <- data.frame(raw.temp,
PEPTIDE=paste(raw.temp$PEPTIDESEQUENCE, raw.temp$PRECURSORCHARGE, sep="_"),
TRANSITION=paste(raw.temp$FRAGMENTION, raw.temp$PRODUCTCHARGE, sep="_"))
if (length(unique(raw.temp$ISOTOPELABELTYPE)) > 2) {
processout <- rbind(processout, c("ERROR : There are more than two levels of labeling.
So far, only label-free or reference-labeled experiment are supported. - stop"))
write.table(processout, file=finalfile, row.names=FALSE)
stop("Statistical tools in MSstats are only proper for label-free or with reference peptide experiments.")
}
## change light, heavy -> L,H
## [THT: should check if users really provide light/heavy, L/H, l/h, or something else ]
## [THT: should also check if users provide only H (instead of L)]
raw.temp$ISOTOPELABELTYPE <- factor(raw.temp$ISOTOPELABELTYPE)
if (nlevels(raw.temp$ISOTOPELABELTYPE) == 2) {
levels(raw.temp$ISOTOPELABELTYPE) <- c("H", "L")
}
if (nlevels(raw.temp$ISOTOPELABELTYPE) == 1) {
levels(raw.temp$ISOTOPELABELTYPE) <- c("L")
}
if( any(is.element(colnames(raw.temp), 'FRACTION')) ) {
fraction <- 'FRACTION'
} else {
fraction <- NULL
}
if( any(is.element(colnames(raw.temp), 'TECHREPLICATE')) ) {
tech.rep <- 'TECHREPLICATE'
} else {
tech.rep <- NULL
}
require.col <- c("PROTEINNAME", "PEPTIDE", "TRANSITION", "ISOTOPELABELTYPE",
"CONDITION", "BIOREPLICATE", "RUN", "INTENSITY",
fraction, tech.rep)
raw.temp <- raw.temp[, require.col]
if( ncol(raw.temp) == 10 &
any(is.element(colnames(raw.temp), 'FRACTION')) &
any(is.element(colnames(raw.temp), 'TECHREPLICATE'))) {
colnames(raw.temp) <- c("Protein", "Peptide", "Transition", "Label",
"Condition", "Sample", "Run", "Intensity", 'Fraction', 'TechReplicate')
} else if( ncol(raw.temp) == 9 &
any(is.element(colnames(raw.temp), 'FRACTION')) ) {
colnames(raw.temp) <- c("Protein", "Peptide", "Transition", "Label",
"Condition", "Sample", "Run", "Intensity", 'Fraction')
} else {
colnames(raw.temp) <- c("Protein", "Peptide", "Transition", "Label",
"Condition", "Sample", "Run", "Intensity")
}
# list(raw.temp, processout)
raw.temp
}
.reformatOld = function(raw.temp, processout, finalfile) {
raw.temp <- raw.temp[!is.na(raw.temp$Protein), ]
raw.temp <- raw.temp[raw.temp$Protein != '', ]
work <- data.frame(PROTEIN=raw.temp$Protein,
PEPTIDE=raw.temp$Peptide,
TRANSITION=raw.temp$Transition,
FEATURE=paste(raw.temp$Peptide, raw.temp$Transition, sep="_"),
LABEL=raw.temp$Label,
GROUP_ORIGINAL=raw.temp$Condition,
SUBJECT_ORIGINAL=raw.temp$Sample,
RUN=raw.temp$Run,
GROUP=0,
SUBJECT=0,
INTENSITY=raw.temp$Intensity)
work$GROUP_ORIGINAL <- factor(work$GROUP_ORIGINAL)
work$SUBJECT_ORIGINAL <- factor(work$SUBJECT_ORIGINAL, levels=unique(work$SUBJECT_ORIGINAL))
work$LABEL <- factor(work$LABEL, levels=levels(work$LABEL))
work[work$LABEL=="L", "GROUP"] <- work[work$LABEL=="L", "GROUP_ORIGINAL"]
work[work$LABEL=="L", "SUBJECT"] <- work[work$LABEL=="L", "SUBJECT_ORIGINAL"]
work <- data.frame(work, SUBJECT_NESTED=paste(work$GROUP, work$SUBJECT, sep="."))
if( any(is.element(colnames(raw.temp), 'Fraction')) ) {
work <- data.frame(work, FRACTION = raw.temp$Fraction)
}
if( any(is.element(colnames(raw.temp), 'TechReplicate')) ) {
work <- data.frame(work, TECHREPLICATE = raw.temp$TechReplicate)
}
processout <- rbind(processout, c("New input format : made new columns for analysis - okay"))
write.table(processout, file=finalfile, row.names=FALSE)
# list(work, processout)
work
}
.intensitiesOld = function(work, processout, finalfile) {
## 2016. 08.29 : replace <1 with zero for log2(intensity)
if ( length(which(!is.na(work$INTENSITY) & work$INTENSITY < 1)) > 0 ) {
processout <- rbind(processout, c(paste0("** There are ",
length(which(!is.na(work$INTENSITY) & work$INTENSITY < 1)),
" intensities which are zero. These intensities are replaced with 1.")))
write.table(processout, file=finalfile, row.names=FALSE)
message(paste0("** There are ", length(which(!is.na(work$INTENSITY) & work$INTENSITY < 1)),
" intensities which are zero or less than 1. These intensities are replaced with 1."))
work[!is.na(work$INTENSITY) & work$INTENSITY < 1, 'INTENSITY'] <- 1
}
## log transformation
work$ABUNDANCE <- work$INTENSITY
if (logTrans == 2) {
work$ABUNDANCE <- log2(work$ABUNDANCE)
} else if (logTrans == 10) {
work$ABUNDANCE <- log10(work$ABUNDANCE)
}
processout <- rbind(processout,
c(paste0("Logarithm transformation: log", logTrans,
" transformation is done - okay")))
write.table(processout, file=finalfile, row.names=FALSE)
# list(work, processout)
work
}
.fractionsOld = function(work, checkMultirun, processout, finalfile) {
if ( checkMultirun$is.risky ){
## if can't matching fractionation, make warning and stop it.
stop('** MSstats suspects that there are fractionations and potentially technical replicates too. Please add Fraction column in the input.')
} else if ( checkMultirun$out ) {
if ( any(is.element(colnames(work), 'FRACTION')) ){
processout <- rbind(processout,
c(paste("Multiple fractionations are existed : ",
length(unique(work$FRACTION)),
"fractionations per MS replicate.")))
write.table(processout, file=finalfile, row.names=FALSE)
} else {
## need to make new column 'Fraction'
## each sample has no technical replicate, all runs are fractionated MS runs.
work$FRACTION <- NA
info <- unique(work[, c('GROUP_ORIGINAL', 'SUBJECT_ORIGINAL', 'RUN')])
info$condition <- paste(info$GROUP_ORIGINAL, info$SUBJECT_ORIGINAL, sep="_")
tmp <- work[!is.na(work$ABUNDANCE), ]
## get on one sample first
info.sample1 <- info[info$condition == unique(info$condition)[1], ]
## assign fraction info first
info.sample1$FRACTION <- seq(1, nrow(info.sample1))
for(k in 1:length(unique(info.sample1$RUN))){
## then fine the same fraction for next sample
unique.feature <- unique( tmp[tmp$RUN %in% info.sample1$RUN[k], 'FEATURE'] )
tmptmp <- tmp[which(tmp$FEATURE %in% unique.feature), ]
tmptmp$condition <- paste(tmptmp$GROUP_ORIGINAL, tmptmp$SUBJECT_ORIGINAL, sep="_")
count.feature <- reshape2::dcast(RUN ~ GROUP_ORIGINAL + SUBJECT_ORIGINAL,
data=tmptmp, fun.aggregate=length, value.var='ABUNDANCE')
## !! get one run which has maximum overlapped feature by each sample
same.frac <- apply(count.feature[,-which(colnames(count.feature) %in% c('RUN'))], 2,
function(x) count.feature[which.max(x), 'RUN'])
work[ which(work$RUN %in% same.frac), 'FRACTION'] <- info.sample1[ which(info.sample1$RUN %in% info.sample1$RUN[k]), 'FRACTION']
}
rm(tmp)
## final check up
checkup <- sum( is.na(unique(work$FRACTION)) ) > 0
if ( !checkup ){
processout <- rbind(processout, c(paste("Multiple fractions are existed : ",
length(unique(work$FRACTION)), "fractions per MS replicate.")))
write.table(processout, file=finalfile, row.names=FALSE)
} else {
processout <- rbind(processout, c('** It is hard to find the same fractionation across sample, due to lots of overlapped features between fractionations.
Please add Fraction column in input.'))
write.table(processout, file=finalfile, row.names=FALSE)
stop("** It is hard to find the same fractionation across sample, due to lots of overlapped features between fractionations.
Please add Fraction column in input.")
}
}
if ( length(unique(work$FRACTION)) > 1 ){
## extra info for feature and fraction
work$tmp <- paste(work$FEATURE, work$FRACTION, sep="_")
tmp <- work[!is.na(work$ABUNDANCE) & work$ABUNDANCE > 0, ]
count.feature <- reshape2::dcast(FEATURE ~ FRACTION,
data=tmp,
fun.aggregate=length,
value.var='ABUNDANCE')
rm(tmp)
## 1. first, keep features which are measured in one fraction
count.fraction <- apply(count.feature[, -which(colnames(count.feature) %in% c('FEATURE'))],
1,
function(x) sum(x>0))
# keep.feature <- count.feature[count.fraction == 1, 'FEATURE']
## 2. second, if features are measured in multiple fractionations,
## use the fractionation with maximum number of measurements.
## if there are multiple maximum number of measurements, remove features completely.
## count.feature1 : features that are measured in multiple fractions
count.feature1 <- count.feature[count.fraction > 1, ]
if( nrow(count.feature1) > 0 ){
## how many fractions have maximum number of measurements?
count.fraction <- apply(count.feature1[, -which(colnames(count.feature1) %in% c('FEATURE'))],
1,
function(x) sum(x == max(x)))
## 2.1 count.fraction == 1 means that there is one fraction that have one maximum # measurements.
## count.feature2 : features that measured in multiple fractions.
## however, it has one fraction with max number of measurements across fractions.
count.feature2 <- count.feature1[count.fraction == 1, ]
count.feature2$FEATURE <- as.character(count.feature2$FEATURE)
if( nrow(count.feature2) > 0 ){
#remove.fraction <- apply(count.feature2, 1,
# function(x) paste(x[1], names(x[-1])[x[-1] != max(x[-1]) & x[-1] != 0], sep="_") )
#remove.fraction <- unlist(remove.fraction)
remove.fraction <- gather(count.feature2, 'Fraction', 'ncount', 2:ncol(count.feature2))
remove.fraction <- remove.fraction %>% group_by(FEATURE) %>% filter(ncount != max(ncount))
remove.fraction <- remove.fraction %>% filter(ncount != 0)
remove.fraction$tmp <- paste(remove.fraction$FEATURE, remove.fraction$Fraction, sep="_")
work[work$tmp %in% remove.fraction$tmp, 'INTENSITY'] <- NA
work[work$tmp %in% remove.fraction$tmp, 'ABUNDANCE'] <- NA
}
rm(count.feature2)
rm(remove.fraction)
## 2.2 count.fraction > 1 means that there are multiple fractions have the same # measurements.
## Then check whether there are multiple maximum number of measurements across fractionation
count.feature3 <- count.feature1[count.fraction > 1, ]
if( nrow(count.feature3) > 0 ){
## 2.2.1 : maximum number of measurement / fraction == 1, remove that feature
max.feature <- apply(count.feature3[, -which(colnames(count.feature3) %in% c('FEATURE'))],
1,
function(x) max(x))
max.feature.1 <- count.feature3[max.feature == 1, 'FEATURE']
if (length(max.feature.1) > 0){
work <- work[-which(work$FEATURE %in% max.feature.1), ]
count.feature3 <- count.feature3[-which(count.feature3$FEATURE %in% max.feature.1), ]
}
if ( nrow(count.feature3) > 0 ) {
###############
## 2.2.2 : remove fractionations which have not maximum number of measurements
remove.fraction <- gather(count.feature3, 'Fraction', 'ncount', 2:ncol(count.feature3))
remove.fraction <- remove.fraction %>% group_by(FEATURE) %>% filter(ncount != max(ncount))
remove.fraction <- remove.fraction %>% filter(ncount != 0)
remove.fraction$tmp <- paste(remove.fraction$FEATURE, remove.fraction$Fraction, sep="_")
work[work$tmp %in% remove.fraction$tmp, 'INTENSITY'] <- NA
work[work$tmp %in% remove.fraction$tmp, 'ABUNDANCE'] <- NA
rm(remove.fraction)
###############
## 2.2.3 : among fractionations, keep one fractionation which has maximum average
tmptmp <- work[which(work$FEATURE %in% count.feature3$FEATURE), ]
tmptmp <- tmptmp[!is.na(tmptmp$ABUNDANCE), ]
mean.frac.feature <- tmptmp %>% group_by(FEATURE, tmp) %>% summarise(mean=mean(ABUNDANCE))
remove.fraction <- mean.frac.feature %>% group_by(FEATURE) %>% filter(mean != max(mean))
work[work$tmp %in% remove.fraction$tmp, 'INTENSITY'] <- NA
work[work$tmp %in% remove.fraction$tmp, 'ABUNDANCE'] <- NA
rm(remove.fraction)
rm(tmptmp)
}
}
}
work <- work[, -which(colnames(work) %in% c('tmp'))]
}
} else { ## no fractionation
work$FRACTION <- 1
}
# list(work, processout)
work
}
.balancedOld = function(work, checkMultirun, fillIncompleteRows, processout, finalfile) {
processout <- rbind(processout, c(paste("fillIncompleteRows = ", fillIncompleteRows,sep="")))
write.table(processout, file=finalfile, row.names=FALSE)
if ( !checkMultirun$out | length(unique(work$FRACTION)) == 1 ) {
## label-free experiments
if (nlevels(work$LABEL) == 1) {
## get feature by Run count of data
structure = tapply ( work$ABUNDANCE, list ( work$FEATURE, work$RUN ) , function ( x ) length ( x ) )
## structure value should be 1 for label-free, if not there are missingness. if more there are duplicates.
flagmissing = sum(is.na(structure)) > 0
flagduplicate = sum(structure[!is.na(structure)]>1) > 0
### if there is missing rows
if ( flagmissing ) {
processout <- rbind(processout, c("CAUTION: the input dataset has incomplete rows.
If missing peaks occur they should be included in the dataset as separate rows,
and the missing intensity values should be indicated with 'NA'.
The incomplete rows are listed below."))
write.table(processout, file=finalfile,row.names=FALSE)
message("CAUTION : the input dataset has incomplete rows.
If missing peaks occur they should be included in the dataset as separate rows,
and the missing intensity values should be indicated with 'NA'.
The incomplete rows are listed below.")
## first, which run has missing
runstructure <- apply ( structure, 2, function ( x ) sum ( is.na ( x ) ) ) > 0
## get the name of Run
runID <- names(runstructure[runstructure==TRUE])
## for missign row, need to assign before looping
missingwork <- NULL
## then for each run, which features are missing,
for(j in 1:length(runID)) {
## get subject, group information for this run
nameID <- unique(work[work$RUN==runID[j], c("SUBJECT_ORIGINAL","GROUP_ORIGINAL",
"GROUP","SUBJECT","SUBJECT_NESTED",
"RUN","FRACTION")])
## get feature ID
featureID <- structure[,colnames(structure)==runID[j]]
## get feature ID which has no measuremnt.
finalfeatureID <- featureID[is.na(featureID)]
## print features ID
message(paste0("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]),
", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]),
" has incomplete rows for some features (",
paste(names(finalfeatureID), collapse=", "), ")"))
## save in process file.
processout <- rbind(processout, c(paste0("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]),
", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]),
" has incomplete rows for some features (",
paste(names(featureID[is.na(featureID)]), collapse=", "), ")")))
write.table(processout, file=finalfile, row.names=FALSE)
## add missing rows if option is TRUE
if (fillIncompleteRows) {
tempTogetfeature <- work[which(work$FEATURE %in% names(finalfeatureID)), ]
## get PROTEIN and FEATURE infomation
tempfeatureID <- unique(tempTogetfeature[, c("PROTEIN", "PEPTIDE", "TRANSITION", "FEATURE")])
## merge feature info and run info as 'work' format
tempmissingwork <- data.frame(tempfeatureID,
LABEL="L",
GROUP_ORIGINAL=nameID$GROUP_ORIGINAL,
SUBJECT_ORIGINAL=nameID$SUBJECT_ORIGINAL,
RUN=nameID$RUN,
GROUP=nameID$GROUP,
SUBJECT=nameID$SUBJECT,
SUBJECT_NESTED=nameID$SUBJECT_NESTED,
INTENSITY=NA,
ABUNDANCE=NA,
FRACTION=nameID$FRACTION)
## merge with tempary space, missingwork
missingwork <- rbind(missingwork, tempmissingwork)
} # end fillIncompleteRows options
} # end loop for run ID
## [THT: this part can probably be merged into the above.
## Also, it might be better to check fillIncompleteRows earlier
## and terminate the process when it's FALSE]
if (fillIncompleteRows) {
## merge with work
## in future, use rbindlist?? rbindlist(list(work, missingwork))
work <- rbind(work, missingwork)
## print message
message("\n DONE : Incomplete rows for missing peaks are added with intensity values=NA. \n")
## save in process file.
processout <- rbind(processout, "Incomplete rows for missing peaks are added with intensity values=NA. - done, Okay")
write.table(processout, file=finalfile, row.names=FALSE)
} else {
## save in process file.
processout <- rbind(processout,"Please check whether features in the list are generated from spectral processing tool.
Or the option, fillIncompleteRows=TRUE, will add incomplete rows for missing peaks with intensity=NA.")
write.table(processout, file=finalfile,row.names=FALSE)
stop("Please check whether features in the list are generated from spectral processing tool or not.
Or the option, fillIncompleteRows=TRUE, will add incomplete rows for missing peaks with intensity=NA.")
}
} # end for flag missing
## if there are duplicates measurements
if (flagduplicate) {
## first, which run has duplicates
runstructure <- apply ( structure, 2, function ( x ) sum (x[!is.na(x)] > 1 ) > 0 )
runID <- names(runstructure[runstructure==TRUE])
## then for each run, which features have duplicates,
for(j in 1:length(runID)) {
nameID <- unique(work[work$RUN == runID[j], c("SUBJECT_ORIGINAL", "GROUP_ORIGINAL",
"GROUP","SUBJECT", "SUBJECT_NESTED",
"RUN", "FRACTION")])
featureID <- structure[, colnames(structure)==runID[j]]
finalfeatureID <- featureID[!is.na(featureID) & featureID > 1]
message(paste0("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]),
", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]),
" has multiple rows (duplicate rows) for some features (",
paste(names(finalfeatureID), collapse=", "), ")"))
## save in process file.
processout <- rbind(processout, c(paste0("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]),
", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]),
" has multiple rows (duplicate rows) for some features (",
paste(names(featureID[is.na(featureID)]), collapse=", "), ")")))
write.table(processout, file=finalfile, row.names=FALSE)
}
## save in process file.
processout <- rbind(processout,"Please remove duplicate rows in the list above. ")
write.table(processout, file=finalfile,row.names=FALSE)
stop("Please remove duplicate rows in the list above.\n")
} # end flag duplicate
## no missing and no duplicates
if (!flagmissing & !flagduplicate) {
processout <- rbind(processout, c("Balanced data format with NA for missing feature intensities - okay"))
write.table(processout, file=finalfile, row.names=FALSE)
}
## end label-free
} else {
## label-based experiment
## count the reference and endobenous separately
work.l <- work[work$LABEL == "L", ]
work.h <- work[work$LABEL == "H", ]
## get feature by Run count of data
structure.l <- tapply(work.l$ABUNDANCE, list(work.l$FEATURE, work.l$RUN), function (x) length (x) )
structure.h <- tapply(work.h$ABUNDANCE, list(work.h$FEATURE, work.h$RUN), function (x) length (x) )
## first, check some features which completely missing across run
missingcomplete.l <- NULL
missingcomplete.h <- NULL
## 1. reference peptides
featurestructure.h <- apply(structure.h, 1, function (x) sum(is.na(x)))
## get feature ID of reference which are completely missing across run
featureID.h <- names(featurestructure.h[featurestructure.h == ncol(structure.h)])
if (length(featureID.h) > 0) {
## print message
message(paste0("CAUTION : some REFERENCE features have missing intensities in all the runs.
The completely missing REFERENCE features are ", paste(featureID.h, collapse=", "),
". Please check whether features in the list are correctly generated from spectral processing tool. \n"))
## save in process file.
processout <- rbind(processout,c(paste("CAUTION : some REFERENCE features have missing intensities in all the runs.
The completely missing REFERENCE features are ", paste(featureID.h, collapse=", "),
". Please check whether features in the list are correctly generated from spectral processing tool.", sep="")))
write.table(processout, file=finalfile, row.names=FALSE)
## add missing rows if option is TRUE
if (fillIncompleteRows) {
## get unique Run information
nameID <- unique(work.h[, c("SUBJECT_ORIGINAL", "GROUP_ORIGINAL", "GROUP", "SUBJECT", "SUBJECT_NESTED", "RUN", "FRACTION")])
## get PROTEIN and FEATURE information
## here use whole work dataset
tempTogetfeature <- work[which(work$FEATURE %in% featureID.h), ]
tempfeatureID <- unique(tempTogetfeature[, c("PROTEIN", "PEPTIDE", "TRANSITION", "FEATURE")])
## then generate data.frame for missingness,
#for(j in 1:nrow(nameID)) {
# ## merge feature info and run info as 'work' format
# tempmissingwork <- data.frame(tempfeatureID, LABEL="H",GROUP_ORIGINAL=nameID$GROUP_ORIGINAL[j], SUBJECT_ORIGINAL=nameID$SUBJECT_ORIGINAL[j], RUN=nameID$RUN[j], GROUP=nameID$GROUP[j], SUBJECT=nameID$SUBJECT[j], SUBJECT_NESTED=nameID$SUBJECT_NESTED[j], INTENSITY=NA, ABUNDANCE=NA, METHOD=nameID$METHOD[j])
# ## merge with tempary space, missingwork
# missingcomplete.h <- rbind(missingcomplete.h, tempmissingwork)
#}
# MC : 2016.04.21 : use merge for simplicity
tmp <- merge(nameID, tempfeatureID, by=NULL)
missingcomplete.h <- data.frame(PROTEIN=tmp$PROTEIN,
PEPTIDE=tmp$PEPTIDE,
TRANSITION=tmp$TRANSITION,
FEATURE=tmp$FEATURE,
LABEL="H",
GROUP_ORIGINAL=tmp$GROUP_ORIGINAL,
SUBJECT_ORIGINAL=tmp$SUBJECT_ORIGINAL,
RUN=tmp$RUN,
GROUP=tmp$GROUP,
SUBJECT=tmp$SUBJECT,
SUBJECT_NESTED=tmp$SUBJECT_NESTED,
INTENSITY=NA,
ABUNDANCE=NA,
FRACTION=tmp$FRACTION)
rm(tmp)
} # end fillIncompleteRows option
} # end for reference peptides
## 2. endogenous peptides
featurestructure.l <- apply(structure.l, 1, function (x) sum(is.na(x)))
## get feature ID of reference which are completely missing across run
featureID.l <- names(featurestructure.l[featurestructure.l == ncol(structure.l)])
if (length(featureID.l) > 0) {
## print message
message(paste("CAUTION : some ENDOGENOUS features have missing intensities in all the runs.
The completely missing ENDOGENOUS features are ", paste(featureID.l, collapse=", "),
". Please check whether features in the list are correctly generated from spectral processing tool. \n", sep=""))
## save in process file.
processout <- rbind(processout,c(paste("CAUTION : some ENDOGENOUS features have missing intensities in all the runs.
The completely missing ENDOGENOUS features are ",
paste(featureID.l, collapse=", "),
". Please check whether features in the list are correctly generated from spectral processing tool. \n", sep="")))
write.table(processout, file=finalfile, row.names=FALSE)
## add missing rows if option is TRUE
if (fillIncompleteRows) {
## get unique Run information
nameID <- unique(work.l[, c("SUBJECT_ORIGINAL",
"GROUP_ORIGINAL",
"GROUP",
"SUBJECT",
"SUBJECT_NESTED",
"RUN",
"FRACTION")])
## get PROTEIN and FEATURE information
## here use whole work dataset
tempTogetfeature <- work[which(work$FEATURE %in% featureID.l), ]
tempfeatureID <- unique(tempTogetfeature[, c("PROTEIN", "PEPTIDE", "TRANSITION", "FEATURE")])
## then generate data.frame for missingness,
#for (j in 1:nrow(nameID)) {
# ## merge feature info and run info as 'work' format
# tempmissingwork <- data.frame(tempfeatureID, LABEL="L",GROUP_ORIGINAL=nameID$GROUP_ORIGINAL[j], SUBJECT_ORIGINAL=nameID$SUBJECT_ORIGINAL[j], RUN=nameID$RUN[j], GROUP=nameID$GROUP[j], SUBJECT=nameID$SUBJECT[j], SUBJECT_NESTED=nameID$SUBJECT_NESTED[j], INTENSITY=NA, ABUNDANCE=NA, METHOD=nameID$METHOD[j])
# ## merge with tempary space, missingwork
# missingcomplete.l <- rbind(missingcomplete.l, tempmissingwork)
#}
# MC : 2016.04.21 : use merge for simplicity
tmp <- merge(nameID, tempfeatureID, by=NULL)
missingcomplete.l <- data.frame(PROTEIN=tmp$PROTEIN,
PEPTIDE=tmp$PEPTIDE,
TRANSITION=tmp$TRANSITION,
FEATURE=tmp$FEATURE,
LABEL="L",
GROUP_ORIGINAL=tmp$GROUP_ORIGINAL,
SUBJECT_ORIGINAL=tmp$SUBJECT_ORIGINAL,
RUN=tmp$RUN,
GROUP=tmp$GROUP,
SUBJECT=tmp$SUBJECT,
SUBJECT_NESTED=tmp$SUBJECT_NESTED,
INTENSITY=NA,
ABUNDANCE=NA,
FRACTION=tmp$FRACTION)
rm(tmp)
} # end fillIncompleteRows option
} # end endogenous peptides
## second, check other some missingness
## for missign row, need to assign before looping. need to assign at the beginning because it need either cases, with missingness or not
missingwork.l <- NULL
missingwork.h <- NULL
## structure value should be 1 for reference and endogenous separately, if not there are missingness. if more there are duplicates.
## if count of NA is not zero and not number of run (excluding complete missingness across runs)
missing.l <- names(featurestructure.l[featurestructure.l != ncol(structure.l) & featurestructure.l != 0])
missing.h <- names(featurestructure.h[featurestructure.h != ncol(structure.h) & featurestructure.h != 0])
flagmissing.l = length(missing.l) > 0
flagmissing.h = length(missing.h) > 0
## structure value is greater than 1, there are duplicates
flagduplicate.l = sum(structure.l[!is.na(structure.l)] > 1) > 0
flagduplicate.h = sum(structure.h[!is.na(structure.h)] > 1) > 0
## if there is missing rows for endogenous
if ( flagmissing.l | flagmissing.h ) {
processout <- rbind(processout,c("CAUTION: the input dataset has incomplete rows. If missing peaks occur they should be included in the dataset as separate rows, and the missing intensity values should be indicated with 'NA'. The incomplete rows are listed below."))
write.table(processout, file=finalfile, row.names=FALSE)
message("CAUTION : the input dataset has incomplete rows. If missing peaks occur they should be included in the dataset as separate rows, and the missing intensity values should be indicated with 'NA'. The incomplete rows are listed below.")
## endogenous intensities
if (flagmissing.l) {
if (length(missing.l) > 1){
runstructure <- apply ( structure.l[which(rownames(structure.l) %in% missing.l), ], 2, function ( x ) sum ( is.na ( x ) ) ) > 0
} else if (length(missing.l) == 1) {
runstructure <- is.na ( structure.l[which(rownames(structure.l) %in% missing.l), ]) > 0
}
## get the name of Run
runID <- names(runstructure[runstructure==TRUE])
## then for each run, which features are missing,
for(j in 1:length(runID)) {
## get subject, group information for this run
nameID <- unique(work.l[work.l$RUN==runID[j], c("SUBJECT_ORIGINAL",
"GROUP_ORIGINAL",
"GROUP",
"SUBJECT",
"SUBJECT_NESTED",
"RUN",
"FRACTION")])
# MC : 2016/04/21. if there is one row, can't catch up data.frame
## get feature ID
if (length(missing.l) > 1){
featureID <- structure.l[which(rownames(structure.l) %in% missing.l), colnames(structure.l) == runID[j]]
## get feature ID which has no measuremnt.
finalfeatureID <- names(featureID[is.na(featureID)])
## print features ID
message(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some ENDOGENOUS features (", paste(finalfeatureID, collapse=", "),")", sep="" ))
## save in process file.
processout <- rbind(processout,c(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some ENDOGENOUS features (", paste(finalfeatureID, collapse=", "),")", sep="" )))
write.table(processout, file=finalfile,row.names=FALSE)
} else if (length(missing.l) == 1) {
finalfeatureID <- missing.l
## print features ID
message(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some ENDOGENOUS features (", finalfeatureID,")", sep="" ))
## save in process file.
processout <- rbind(processout,c(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some ENDOGENOUS features (", finalfeatureID,")", sep="" )))
write.table(processout, file=finalfile,row.names=FALSE)
}
## add missing rows if option is TRUE
if (fillIncompleteRows) {
tempTogetfeature <- work.l[which(work.l$FEATURE %in% finalfeatureID), ]
## get PROTEIN and FEATURE infomation
tempfeatureID <- unique(tempTogetfeature[, c("PROTEIN", "PEPTIDE", "TRANSITION", "FEATURE")])
## merge feature info and run info as 'work' format
tempmissingwork <- data.frame(tempfeatureID,
LABEL="L",
GROUP_ORIGINAL=nameID$GROUP_ORIGINAL,
SUBJECT_ORIGINAL=nameID$SUBJECT_ORIGINAL,
RUN=nameID$RUN,
GROUP=nameID$GROUP,
SUBJECT=nameID$SUBJECT,
SUBJECT_NESTED=nameID$SUBJECT_NESTED,
INTENSITY=NA,
ABUNDANCE=NA,
FRACTION=nameID$FRACTION)
## merge with tempary space, missingwork
missingwork.l <- rbind(missingwork.l,tempmissingwork)
} # end fillIncompleteRows options
} # end loop for run ID
} # end for endogenous
## reference intensities
if (flagmissing.h) {
## first, which run has missing
if (length(missing.h) > 1){
runstructure <- apply ( structure.h[which(rownames(structure.h) %in% missing.h), ], 2,
function ( x ) sum ( is.na ( x ) ) ) > 0
} else if (length(missing.h) == 1) {
runstructure <- is.na ( structure.h[which(rownames(structure.h) %in% missing.h), ]) > 0
}
## get the name of Run
runID <- names(runstructure[runstructure==TRUE])
## then for each run, which features are missing,
for(j in 1:length(runID)) {
## get subject, group information for this run
nameID <- unique(work.h[work.h$RUN==runID[j], c("SUBJECT_ORIGINAL",
"GROUP_ORIGINAL",
"GROUP",
"SUBJECT",
"SUBJECT_NESTED",
"RUN",
"FRACTION")])
# MC : 2016/04/21. if there is one row, can't catch up data.frame
## get feature ID
if (length(missing.h) > 1){
featureID <- structure.h[which(rownames(structure.h) %in% missing.h), colnames(structure.h) == runID[j] ]
## get feature ID which has no measuremnt.
finalfeatureID <- names(featureID[is.na(featureID)])
## print features ID
message(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some REFERENCE features (", paste(finalfeatureID, collapse=", "),")", sep="" ))
## save in process file.
processout <- rbind(processout,c(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some REFERENCE features (", paste(finalfeatureID, collapse=", "),")", sep="" )))
write.table(processout, file=finalfile,row.names=FALSE)
} else if (length(missing.h) == 1) {
finalfeatureID <- missing.h
## print features ID
message(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some REFERENCE features (", finalfeatureID,")", sep="" ))
## save in process file.
processout <- rbind(processout,c(paste("*** Subject : ", as.character(nameID[,"SUBJECT_ORIGINAL"]) ,", Condition : ", as.character(nameID[,"GROUP_ORIGINAL"]), " has incomplete rows for some REFERENCE features (", finalfeatureID,")", sep="" )))
write.table(processout, file=finalfile,row.names=FALSE)
}
## add missing rows if option is TRUE
if (fillIncompleteRows) {
tempTogetfeature <- work.h[which(work.h$FEATURE %in% finalfeatureID), ]
## get PROTEIN and FEATURE infomation
tempfeatureID <- unique(tempTogetfeature[, c("PROTEIN", "PEPTIDE", "TRANSITION", "FEATURE")])
## merge feature info and run info as 'work' format
tempmissingwork <- data.frame(tempfeatureID,
LABEL="H",
GROUP_ORIGINAL=nameID$GROUP_ORIGINAL,
SUBJECT_ORIGINAL=nameID$SUBJECT_ORIGINAL,
RUN=nameID$RUN,
GROUP=nameID$GROUP,
SUBJECT=nameID$SUBJECT,
SUBJECT_NESTED=nameID$SUBJECT_NESTED,
INTENSITY=NA,
ABUNDANCE=NA,
FRACTION=nameID$FRACTION)
## merge with tempary space, missingwork
missingwork.h <- rbind(missingwork.h, tempmissingwork)
} # end fillIncompleteRows options
} # end loop for run ID
} # end for endogenous
} # end for flag missing
## merge missing rows if fillIncompleteRows=TRUE or message.
if (fillIncompleteRows) {
## merge with work
## in future, use rbindlist?? rbindlist(list(work, missingwork))
work <- rbind(work,missingcomplete.l, missingcomplete.h, missingwork.l, missingwork.h)
## print message
message("\n DONE : Incomplete rows for missing peaks are added with intensity values=NA. \n")
## save in process file.
processout <- rbind(processout, "Incomplete rows for missing peaks are added with intensity values=NA. - done, Okay")
write.table(processout, file=finalfile, row.names=FALSE)
} else if (!is.null(missingcomplete.l) |
!is.null(missingcomplete.h) |
!is.null(missingwork.l) |
!is.null(missingwork.l) ) {
## save in process file.
processout <- rbind(processout,
"Please check whether features in the list are generated from spectral processing tool.
Or the option, fillIncompleteRows=TRUE,
will add incomplete rows for missing peaks with intensity=NA.")
write.table(processout, file=finalfile, row.names=FALSE)
stop("Please check whether features in the list are generated from spectral processing tool or not. Or the option, fillIncompleteRows=TRUE, will add incomplete rows for missing peaks with intensity=NA.")