-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathAMBITION_Metabolomics.Rmd
1059 lines (961 loc) · 55.2 KB
/
AMBITION_Metabolomics.Rmd
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
---
title: "AMBITION_Metabolomics"
author: "Christina Schmidt"
date: "03 January 2022"
output:
html_document:
toc: yes
toc_depth: 3
toc_float: yes
pdf_document:
toc: yes
toc_depth: '3'
editor_options:
chunk_output_type: console
---
# Establish the functions
For this install the packages needed and load the libraries.
```{r intro-chunk, message=FALSE}
#load the needed libraries:
library(tidyverse) # used for data manipulation
library(rmarkdown) # used for paged_table function
library(dplyr)
```
```{r normalisation, message=FALSE}
Filtering <-function(Input){
#Find metabolites that have to be removed
miss <- c()
for(i in 1:ncol(Input)) {
if(length(which(is.na(Input[,i]))) > (0.8*nrow(Input)))
miss <- append(miss,i)
}
#remove metabolites if any are found
if(length(miss) ==0){
print("There where no metabolites exluded")
filtered_matrix <- Input
} else {
print(length(miss))
print(" metabolites where removed")
filtered_matrix <- Input[,-miss]
}
}
MVI <-function(Input){
replace(Input, is.na(Input), ((min(Input, na.rm = TRUE))/2))
}
TIC <- function(Input){
RowSums <- rowSums(Input)
Median_RowSums <- median(RowSums)#This will built the median
Data_TIC_Pre <- apply(Input, 2, function(i) i/RowSums)#This is dividing the ion intensity by the total ion count
Data_TIC <- Data_TIC_Pre*Median_RowSums#Multiplies with the median metabolite intensity
Data_TIC <- cbind(rownames(Data_TIC), data.frame(Data_TIC, row.names=NULL, check.names=FALSE))%>%
rename("UniqueID"="rownames(Data_TIC)")
}
```
```{r Heatmap, message=FALSE}
library(gplots)
Heatmap <- function(InputMatrix, maximum, minimum, OutputPlotName){
#Prepare the Input matrix and scale
dataHeat_matrix <- data.matrix(InputMatrix)
transpose<-t(scale(dataHeat_matrix))#scale by column
min(transpose)
max(transpose)
t <- as.vector(t(transpose))
#-------------------------------------------------------
#function to centralise the colour palette onto zero (Credit to Aurelien Dugourd)
createLinearColors <- function(numbers, withZero = T, maximum = 100)
{
if (min(numbers, na.rm = T) > 0)
{
if(withZero)
{
numbers <- c(0,numbers)
}
myPalette <- colorRampPalette(c("#F5B7B1", "#EC7063", "#E74C3C", "#CB4335", "#A93226", "#922B21", "#7B241C", "#641E16"))
myColors <- myPalette(maximum)
}
else
{
if (max(numbers, na.rm = T) < 0)
{
if(withZero)
{
numbers <- c(0,numbers)
}
myPalette <- colorRampPalette(c("#154360","#1A5276","#1F618D","#2874A6","#2E86C1","#3498DB","#5DADE2","#85C1E9","#D6EAF8"))
myColors <- myPalette(maximum)
}
else
{
myPalette_pos <- colorRampPalette(c("#F5B7B1", "#EC7063","#E74C3C","#CB4335", "#A93226","#922B21","#7B241C","#641E16"))
myPalette_neg <- colorRampPalette(c("#154360","#1A5276","#1F618D","#2874A6","#2E86C1","#3498DB","#5DADE2","#85C1E9","#D6EAF8"))
npos <- length(numbers[numbers >= 0]) + 1
nneg <- length(numbers[numbers <= 0]) + 1
myColors_pos <- myPalette_pos(npos)
myColors_neg <- myPalette_neg(nneg)
myColors <- c(myColors_neg[-(nneg)], myColors_pos[-1])
}
}
return(myColors)
}
#------------------------------------------
# Color palette normalization to zero
palette1 <- createLinearColors(t[t < 0],withZero = T , maximum = paste(maximum))
palette2 <- createLinearColors(t[t > 0],withZero = T , maximum = paste(minimum))
palette <- c(palette1,palette2)
#------------------------------------------
#Make the Heatmap
Heatmap <- heatmap.2(transpose, #the data frame we use
margins = c(7,14),#Figure Margins
col=palette,
scale="none", #data scaling
hclustfun=function(d) hclust(d, method="ward.D"),
Rowv=T,
Colv=T,
symm=F,
symkey=F,
symbreaks=F,
density.info="none",
trace="none",
main = paste(OutputPlotName),
key.title = "Metabolite Intensity",
key.xlab = NA,
cexRow=0.1,
cexCol=0.1,
ColSideColors=cols1)
}
```
```{r , message= FALSE}
library(gtools)#used for "foldchange"
DMA <-function(Log2FC_Condition1, Log2FC_Condition2,Stat_Condition1, Stat_Condition2, Patient_ID){
#Log2FC
FC_C1vC2 <- mapply(foldchange,Log2FC_Condition1,Log2FC_Condition2)
Log2FC_C1vC2 <- as.data.frame(foldchange2logratio(FC_C1vC2, base=2))
Log2FC_C1vC2 <- cbind(rownames(Log2FC_C1vC2), data.frame(Log2FC_C1vC2, row.names=NULL))
names(Log2FC_C1vC2)[names(Log2FC_C1vC2) == "rownames(Log2FC_C1vC2)"] <- "Metabolite"
names(Log2FC_C1vC2)[names(Log2FC_C1vC2) == "foldchange2logratio.FC_C1vC2..base...2."] <- paste("Log2FC",Patient_ID, sep="_")
#t-test
T_C1vC2 <-mapply(t.test, x= as.data.frame(Stat_Condition2), y = as.data.frame(Stat_Condition1), SIMPLIFY = F)
VecPVAL_C1vC2 <- c()
for(i in 1:length(T_C1vC2)){
p_value <- unlist(T_C1vC2[[i]][3])
VecPVAL_C1vC2[i] <- p_value
}
Metabolite <- colnames(Stat_Condition2)
PVal_C1vC2 <- data.frame(Metabolite, VecPVAL_C1vC2)
#Benjamini Hochberg p-adjusted
VecPADJ_C1vC2 <- p.adjust((PVal_C1vC2[,2]),method = "BH", n = length((PVal_C1vC2[,2])))
PADJ_C1vC2 <- data.frame(Metabolite, VecPADJ_C1vC2)
STAT_C1vC2 <- merge(PVal_C1vC2,PADJ_C1vC2, by="Metabolite")
STAT_C1vC2 <- merge(Log2FC_C1vC2,STAT_C1vC2, by="Metabolite")
names(STAT_C1vC2)[names(STAT_C1vC2) == "VecPVAL_C1vC2"] <- paste("p.val",Patient_ID, sep="_")
names(STAT_C1vC2)[names(STAT_C1vC2) == "VecPADJ_C1vC2"] <- paste("p.adj",Patient_ID, sep="_")
Output <- STAT_C1vC2
}
DMA_Single <-function(STAT_pval, STAT_padj, Log2FC_Condition1, Log2FC_Condition2,Stat_Condition1, Stat_Condition2, Output){
#Log2FC
FC_C1vC2 <- mapply(foldchange,Log2FC_Condition1,Log2FC_Condition2)
Log2FC_C1vC2 <- as.data.frame(foldchange2logratio(FC_C1vC2, base=2))
Log2FC_C1vC2 <- cbind(rownames(Log2FC_C1vC2), data.frame(Log2FC_C1vC2, row.names=NULL))
names(Log2FC_C1vC2)[names(Log2FC_C1vC2) == "rownames(Log2FC_C1vC2)"] <- "Metabolite"
names(Log2FC_C1vC2)[names(Log2FC_C1vC2) == "foldchange2logratio.FC_C1vC2..base...2."] <- "Log2FC"
#t-test
T_C1vC2 <-mapply(STAT_pval, x= as.data.frame(Stat_Condition2), y = as.data.frame(Stat_Condition1), SIMPLIFY = F)
VecPVAL_C1vC2 <- c()
for(i in 1:length(T_C1vC2)){
p_value <- unlist(T_C1vC2[[i]][3])
VecPVAL_C1vC2[i] <- p_value
}
Metabolite <- colnames(Stat_Condition2)
PVal_C1vC2 <- data.frame(Metabolite, VecPVAL_C1vC2)
#Benjamini Hochberg p-adjusted
VecPADJ_C1vC2 <- p.adjust((PVal_C1vC2[,2]),method = STAT_padj, n = length((PVal_C1vC2[,2])))
PADJ_C1vC2 <- data.frame(Metabolite, VecPADJ_C1vC2)
STAT_C1vC2 <- merge(PVal_C1vC2,PADJ_C1vC2, by="Metabolite")
STAT_C1vC2 <- merge(Log2FC_C1vC2,STAT_C1vC2, by="Metabolite")
names(STAT_C1vC2)[names(STAT_C1vC2) == "VecPVAL_C1vC2"] <- "p.val"
names(STAT_C1vC2)[names(STAT_C1vC2) == "VecPADJ_C1vC2"] <- "p.adj"
#write.csv(STAT_C1vC2, paste("",Output), row.names= TRUE)
Output <- STAT_C1vC2
}
```
```{r PCA, message=FALSE}
library(devtools)
library(ggfortify)
library(ggplot2)
library(RColorBrewer)
library(viridisLite)
library(viridis)#https://cran.r-project.org/web/packages/viridis/vignettes/intro-to-viridis.html
PCA_NoLoadings <- function(InputMatrix,OutputPlotName, DF, Color, Shape){
PCA <- autoplot (prcomp(InputMatrix),
data = DF,
colour = Color,
label=T,
label.size=1,
label.repel = TRUE,
#loadings=T, #draws Eigenvectors
#loadings.label = TRUE,
#loadings.label.vjust = 1.2,
#loadings.label.size=2,
#loadings.colour="grey10",
#loadings.label.colour="grey10",
fill = Color,#fill colour of the dots
color = "black",#outline colour
alpha = 0.8,#controls the transparency: 1 = 100% opaque; 0 = 100% transparent.
shape = Shape,#https://rpkgs.datanovia.com/ggpubr/reference/show_point_shapes.html, 21
size = 3.5#size of the dot
)+
labs(col=Color, size=1)+
scale_shape_manual(values=c(22,24,21,23,25,7,8,11,12))+ #needed if more than 6 shapes are in place
theme_classic()+
geom_hline(yintercept=0, linetype="dashed", color = "black", alpha=0.6, size=0.75)+
geom_vline(xintercept = 0, linetype="dashed", color = "black", alpha=0.6, size=0.75)+
ggtitle(paste(OutputPlotName))
ggsave(file=paste("Figures_AMBITION-Metabolomics/PCA_Color", OutputPlotName, ".pdf", sep="_"), plot=PCA, width=8, height=6)
plot(PCA)
}
```
```{r VolcanoPlot_Pathways, message=FALSE}
library(ggrepel)
library(EnhancedVolcano)
VolcanoPlot_Pathways <- function(InputData, OutputPlotName){
#Prepare new colour scheme:
keyvals <- ifelse(
InputData$Metabolic_Pathways == "glycolysis and PPP", "red",
ifelse(InputData$Metabolic_Pathways == "amino acid and conjugate", "blue",
ifelse(InputData$Metabolic_Pathways == "redox homeostasis", "orange",
ifelse(InputData$Metabolic_Pathways == "nucleotides", "seagreen",
ifelse(InputData$Metabolic_Pathways == "Carnitine metabolism", "gold4",
ifelse(InputData$Metabolic_Pathways == "TCA cycle", "firebrick4",
"gray"))))))
keyvals[is.na(keyvals)] <- 'gray'
names(keyvals)[keyvals == 'blue'] <- "Amino acid and Conjugates"
names(keyvals)[keyvals == 'red'] <- "Glycolysis and PPP"
names(keyvals)[keyvals == 'gold4'] <- "Carnitine metabolism"
names(keyvals)[keyvals == 'seagreen'] <- "Nucleotides"
#names(keyvals)[keyvals == 'darkorchid1'] <- "Purine metabolism"
#names(keyvals)[keyvals == 'darkorchid4'] <- "Pyrimidine metabolism"
names(keyvals)[keyvals == 'orange'] <- "Redox homeostasis"
#names(keyvals)[keyvals == 'gold1'] <- "Fatty acid metabolism"
names(keyvals)[keyvals == 'firebrick4'] <- "TCA cycle"
names(keyvals)[keyvals == 'gray'] <- 'Not assigned to pathway'
#Make the VolcanoPlot
VolcanoPlot0<- EnhancedVolcano (InputData,
lab = InputData$Metabolite,#Metabolite name
#lab =NA,#No labels on the plot
x = "Log2FC",#Log2FC
y = "p.adj",#p-value or q-value
xlab = bquote(~Log[2]~ "FC"),
ylab = bquote(~-Log[10]~p.adj),#(~-Log[10]~adjusted~italic(P))
pCutoff = 0.05,
FCcutoff = 0.5,#Cut off Log2FC, automatically 2
pointSize = 4,
labSize = 0.5,
titleLabSize = 16,
colCustom = keyvals,
colAlpha = 0.5,
title= paste(OutputPlotName),
subtitle = bquote(italic("Differential metabolomics analysis")),
caption = paste0("total = ", nrow(InputData), " Metabolites"),
#xlim = c((ceiling(Reduce(min,InputData$Log2FC))-0.2),(ceiling(Reduce(max,InputData$Log2FC))+0.2)),
xlim=c(-5.5, 1.5),
ylim = c(0,(ceiling(-log10(Reduce(min,InputData$p.adj))))),
#drawConnectors = TRUE,
#widthConnectors = 0.5,
#colConnectors = "black",
#arrowheads=FALSE,
cutoffLineType = "dashed",
cutoffLineCol = "black",
cutoffLineWidth = 0.5,
#legendLabels=c('No changes',"-0.5< Log2FC <0.5","-0.5< Log2FC <0.5", 'p.adj<0.05 & -0.5< Log2FC <0.5"'),
legendPosition = 'right',
legendLabSize = 8,
legendIconSize =4,
gridlines.major = FALSE,
gridlines.minor = FALSE,
)
ggsave(file=paste("Figures_AMBITION-Metabolomics/VolcanoPlot_padj", OutputPlotName, "Pathway_Select.pdf", sep="_"), plot=VolcanoPlot0, width=8, height=6)
#ggsave(file=paste("VolcanoPlot_padj", OutputPlotName, "Pathway_Select.png", sep="_"), plot=VolcanoPlot0, width=10, height=8)
plot(VolcanoPlot0)
VolcanoPlot1<- EnhancedVolcano (InputData,
lab = InputData$Metabolite,#Metabolite name
#lab =NA,#No labels on the plot
x = "Log2FC",#Log2FC
y = "p.val",#p-value or q-value
xlab = bquote(~Log[2]~ "FC"),
ylab = bquote(~-Log[10]~p.val),#(~-Log[10]~adjusted~italic(P))
pCutoff = 0.05,
FCcutoff = 0.5,#Cut off Log2FC, automatically 2
pointSize = 4,
labSize = 0.5,
titleLabSize = 16,
colCustom = keyvals,
colAlpha = 0.5,
title=paste(OutputPlotName),
subtitle = bquote(italic("Differential metabolomics analysis")),
caption = paste0("total = ", nrow(InputData), " Metabolites"),
#xlim = c((ceiling(Reduce(min,InputData$Log2FC))),(ceiling(Reduce(max,InputData$Log2FC)))),
xlim=c(-5.5, 1.5),
ylim = c(0,(ceiling(-log10(Reduce(min,InputData$p.val))))),
#drawConnectors = TRUE,
#widthConnectors = 0.5,
#colConnectors = "black",
#arrowheads=FALSE,
cutoffLineType = "dashed",
cutoffLineCol = "black",
cutoffLineWidth = 0.5,
#legendLabels=c('No changes',"-0.5< Log2FC <0.5","-0.5< Log2FC <0.5", 'p.adj<0.05 & -0.5< Log2FC <0.5"'),
legendPosition = 'right',
legendLabSize = 8,
legendIconSize =4,
gridlines.major = FALSE,
gridlines.minor = FALSE,
)
ggsave(file=paste("Figures_AMBITION-Metabolomics/VolcanoPlot_pval", OutputPlotName, "Pathway_Select.pdf", sep="_"), plot=VolcanoPlot1, width=8, height=6)
#ggsave(file=paste("VolcanoPlot_pval", OutputPlotName, "Pathway_Select.png", sep="_"), plot=VolcanoPlot1, width=10, height=8)
plot(VolcanoPlot1)
}
```
# Information
`The AMBITION study`\
`A`ssessing `M`itochondrial `BI`oenergetics in chronic coronary artery disease: A `T`ranslational study `I`ntegrating multi`Om`ic analysis of human left ventricular tissue and qua`N`titative stress perfusion cardiovascular magnetic resonance\
\
The notebook contains: Metabolomics data of patients myocardial biopsies that were analysed by liquid chromatography-mass spectrometry (LC-MS).LC-MS data aquistion has been performed by the Frezza Laboratory, CECAD Research Center, Faculty of Medicine, University Hospital Cologne, Germany. Input data will be available upon publication in the folder "InputData_AMBITION-Metabolomics".\
\
Code for the R analysis can be reproduced by following this notebook. This includes the data normalisation, differential metabolite analysis and all subsequent plots (PCA plot, Correlation plot, Volcano plot).
# Preparation of the Supplementary Data Tables
## Sheet 1: Raw Data
```{r, message=FALSE, warning=FALSE}
#Load the data:
TP_Intra <- read.csv("InputData_AMBITION-Metabolomics/AMBITION_RawData.csv", check.names=FALSE)%>%
unite("UniqueID",c("Patient.ID","class", "analytical_replicate"),sep="_", remove=FALSE)
```
## Sheet 2: Normalised Data
Total pools of the intracellular metabolites are used.\
\
```{r, message=FALSE, warning=FALSE}
#Prepare the input matrix
x <- TP_Intra[,6:250]
x_matrix <- apply(as.matrix(x), 2, as.numeric)
row.names(x_matrix) <- TP_Intra$UniqueID
x_matrix <- replace(x_matrix, x_matrix %in% 0, NA)#Replace 0 with NA
```
### Normalisation
Step1: Filtering 80% Rule\
Metabolites which where detected with "NA" in more than 80% of the samples are excluded:Here None\
\
Step2: Missing Value Imputation (MVI)
- We will search for the smallest detected value (x)\
- We will divide this value by 2 (x:2)\
- We will replace all "NA" with the value (x:2)\
\
Step3: Normalisation\
Normalization to total ion count (TIC)
```{r, message=FALSE, warning=FALSE}
filt <- Filtering(Input=x_matrix)
MVI <-MVI(filt)
TIC <- TIC(MVI)
#Merge with SampleInfo
norm <- merge(TP_Intra[,1:5], TIC, by="UniqueID", check.names=FALSE)
```
### Quality control: Mark Outliers
Here we perform ["muma"](https://cran.r-project.org/web/packages/muma/muma.pdf) (Metabolomics Univariate and Multivariate Analysis) analysis for outliers. This uses the Hotellin's T2 distribution test to estimate outliers (Here: Pareto scaling used)\
```{r, warning=FALSE, error=FALSE, eval=FALSE}
#Prepare DF:
Muma_Intra <- norm
Muma_Intra <- Muma_Intra[,c(1,5,6:250)]
names(Muma_Intra)[names(Muma_Intra) == "UniqueID"] <- "sample"#Rename the rowname
names(Muma_Intra)[names(Muma_Intra) == "analytical_replicate"] <- "class"#Rename the rowname
write.csv(Muma_Intra, "Muma/Muma_Intra_Tissue.csv", row.names=FALSE)
#Muma analysis
library(muma)
#Create "PCA_ScoreMatrix.csv
explore.data("Muma/Muma_Intra_Tissue.csv",#Data need to be imported as a .csv
"Pareto",#scaling is performed
normalize=FALSE,
imputation = FALSE)
#Test for Outlier based on geometric distances of each point in the PCA score plot
Plot.pca(1,#an integer indicating the principal component to be plotted in x
2,#an integer indicating the principal component to be plotted in y
"Pareto",#scaling previously specified in the function ’explore.data’
test.outlier=TRUE)#geometric outlier testing
#Safe ScorePlot_PC1vsPC2.pdf as .png to include in html!
```
\
We do have outliers in the samples:\
\
The outliers are:\
\
--> Definite outliers:\
1. Patient_040: All analytical replicates of the remote samples\
2. Patient_048: All analytical replicates of the remote samples\
These samples where already flanked to have very low total ion count (TIC) due to the amount of material. Therefore, we exclude these samples from the downstream analysis.\
\
--> Debatable outliers (close to boarder):\
1. Patient_075: All analytical replicates of the ischmia samples\
2. Patient_054: All analytical replicates of the ischmia samples\
Since these are close to the boarder, we check the metabolite distribution in the Heatmap to decide if we have to exclude them.\
```{r, warning= FALSE, message=FALSE}
#Prepare InputData:
dataHeat <- norm
row.names(dataHeat) <- dataHeat$UniqueID
Input_dataHeat <- dataHeat[,6:250]
#Prepare sample color code:
cols1 <- case_when(dataHeat$class == "Remote" ~ 'blue',
dataHeat$class == "Ischaemic" ~ 'red',
TRUE ~ 'grey')
#Make the Heatmap:
Heatmap2 <- Heatmap(InputMatrix=Input_dataHeat, maximum=25, minimum=75, OutputPlotName="Normalised Total Pool data")
```
\
I can not really spot a clear outlier in the Heatmap and hence I would not remove any other replicates from the data.
```{r, warning= FALSE, message=FALSE}
norm_outliers <- norm%>%
mutate(Excluded = case_when(UniqueID == "Patient_040_Remote_1" ~ 'YES',
UniqueID == "Patient_040_Remote_2" ~ 'YES',
UniqueID == "Patient_040_Remote_3" ~ 'YES',
UniqueID == "Patient_048_Remote_1" ~ 'YES',
UniqueID == "Patient_048_Remote_2" ~ 'YES',
UniqueID == "Patient_048_Remote_3" ~ 'YES',
TRUE ~ 'NO'))
norm_outliers <-norm_outliers[,c(1,251,2:251)]
write.csv(norm_outliers, "OutputData_AMBITION-Metabolomics/Sheet2_MVI-TIC-normalised_OutliersMarked.csv", row.names=FALSE)
```
## Sheet 3: Mean of analytical replicates
Each sample was measured three times (three independent injections). Here I will built the mean of these analytical replicates after removing the outliers.\
These results will be used for plotting individual metabolites of interest and to perform the differential metabolite analysis of impaired LVEF versus preserved LVEF.\
\
*Note: For Patient_050 two different samples were harvested and each injected three times, yet they are treated as six analytical replicates and hence combined.
```{r, warning= FALSE, message=FALSE}
#Remove Outliers:
norm_NoOutliers <- subset(norm_outliers,Excluded == "NO")%>%
unite(Sample,c("Patient.ID","class"),sep="_", remove=FALSE)
norm_NoOutliers <-norm_NoOutliers[,-c(2,253)]
#Built Means
H_Means <- (norm_NoOutliers[,7:251]) %>%
group_by(norm_NoOutliers$Sample) %>%
summarise_all(funs(mean))
H_Means <- merge(x=norm_NoOutliers[,c(2:5)], y=H_Means, by.x ="Sample",by.y ="norm_NoOutliers$Sample")
H_Means <- H_Means[!duplicated(H_Means$Sample),]
write.csv(H_Means, "OutputData_AMBITION-Metabolomics/Sheet3_MVI-TIC-normalised_Means.csv")
```
## Sheet 4: DMA ischemia versus remote
He we perform differential metabolite analysis for each patient with ischemia and remote sample (total 29):\
Ischemia versus Remote using the analytical replicates for the statistics. Here we performed the t-Test and p-value adjustment using Benjamini Hochberg.\
\
*Note: For Patient_050 two different samples were harvested and each injected three times, yet they are treated as six analytical replicates and hence combined.
```{r , warning= FALSE, message=FALSE}
# Prepare the Dataframes:
Data_DMA <- subset(norm_outliers,Excluded == "NO")%>%#remove the outliers!
unite("Sample",c("Patient.ID","class"),sep="_", remove=FALSE)
Data_DMA <-Data_DMA[,-253]
#--------------------
##Single replicates for STAT:
Stat_120_Ischaemic <- subset(Data_DMA, Sample == "Patient_120_Ischaemic", select=c(10:252))
Stat_120_Remote <- subset(Data_DMA, Sample == "Patient_120_Remote", select=c(10:252))
Stat_089_Ischaemic <- subset(Data_DMA, Sample == "Patient_089_Ischaemic", select=c(10:252))
Stat_089_Remote <- subset(Data_DMA, Sample == "Patient_089_Remote", select=c(10:252))
Stat_094_Ischaemic <- subset(Data_DMA, Sample == "Patient_094_Ischaemic", select=c(10:252))
Stat_094_Remote <- subset(Data_DMA, Sample == "Patient_094_Remote", select=c(10:252))
Stat_080_Ischaemic <- subset(Data_DMA, Sample == "Patient_080_Ischaemic", select=c(10:252))
Stat_080_Remote <- subset(Data_DMA, Sample == "Patient_080_Remote", select=c(10:252))
Stat_088_Ischaemic <- subset(Data_DMA, Sample == "Patient_088_Ischaemic", select=c(10:252))
Stat_088_Remote <- subset(Data_DMA, Sample == "Patient_088_Remote", select=c(10:252))
Stat_054_Ischaemic <- subset(Data_DMA, Sample == "Patient_054_Ischaemic", select=c(10:252))
Stat_054_Remote <- subset(Data_DMA, Sample == "Patient_054_Remote", select=c(10:252))
Stat_093_Ischaemic <- subset(Data_DMA, Sample == "Patient_093_Ischaemic", select=c(10:252))
Stat_093_Remote <- subset(Data_DMA, Sample == "Patient_093_Remote", select=c(10:252))
Stat_039_Ischaemic <- subset(Data_DMA, Sample == "Patient_039_Ischaemic", select=c(10:252))
Stat_039_Remote <- subset(Data_DMA, Sample == "Patient_039_Remote", select=c(10:252))
Stat_064_Ischaemic <- subset(Data_DMA, Sample == "Patient_064_Ischaemic", select=c(10:252))
Stat_064_Remote <- subset(Data_DMA, Sample == "Patient_064_Remote", select=c(10:252))
Stat_101_Ischaemic <- subset(Data_DMA, Sample == "Patient_101_Ischaemic", select=c(10:252))
Stat_101_Remote <- subset(Data_DMA, Sample == "Patient_101_Remote", select=c(10:252))
Stat_103_Ischaemic <- subset(Data_DMA, Sample == "Patient_103_Ischaemic", select=c(10:252))
Stat_103_Remote <- subset(Data_DMA, Sample == "Patient_103_Remote", select=c(10:252))
Stat_075_Ischaemic <- subset(Data_DMA, Sample == "Patient_075_Ischaemic", select=c(10:252))
Stat_075_Remote <- subset(Data_DMA, Sample == "Patient_075_Remote", select=c(10:252))
Stat_099_Ischaemic <- subset(Data_DMA, Sample == "Patient_099_Ischaemic", select=c(10:252))
Stat_099_Remote <- subset(Data_DMA, Sample == "Patient_099_Remote", select=c(10:252))
Stat_071_Ischaemic <- subset(Data_DMA, Sample == "Patient_071_Ischaemic", select=c(10:252))
Stat_071_Remote <- subset(Data_DMA, Sample == "Patient_071_Remote", select=c(10:252))
Stat_073_Ischaemic <- subset(Data_DMA, Sample == "Patient_073_Ischaemic", select=c(10:252))
Stat_073_Remote <- subset(Data_DMA, Sample == "Patient_073_Remote", select=c(10:252))
Stat_050_Ischaemic <- subset(Data_DMA, Sample == "Patient_050_Ischaemic", select=c(10:252))
Stat_050_Remote <- subset(Data_DMA, Sample == "Patient_050_Remote", select=c(10:252))
Stat_090_Ischaemic <- subset(Data_DMA, Sample == "Patient_090_Ischaemic", select=c(10:252))
Stat_090_Remote <- subset(Data_DMA, Sample == "Patient_090_Remote", select=c(10:252))
Stat_065_Ischaemic <- subset(Data_DMA, Sample == "Patient_065_Ischaemic", select=c(10:252))
Stat_065_Remote <- subset(Data_DMA, Sample == "Patient_065_Remote", select=c(10:252))
Stat_085_Ischaemic <- subset(Data_DMA, Sample == "Patient_085_Ischaemic", select=c(10:252))
Stat_085_Remote <- subset(Data_DMA, Sample == "Patient_085_Remote", select=c(10:252))
Stat_055_Ischaemic <- subset(Data_DMA, Sample == "Patient_055_Ischaemic", select=c(10:252))
Stat_055_Remote <- subset(Data_DMA, Sample == "Patient_055_Remote", select=c(10:252))
Stat_038_Ischaemic <- subset(Data_DMA, Sample == "Patient_038_Ischaemic", select=c(10:252))
Stat_038_Remote <- subset(Data_DMA, Sample == "Patient_038_Remote", select=c(10:252))
Stat_076_Ischaemic <- subset(Data_DMA, Sample == "Patient_076_Ischaemic", select=c(10:252))
Stat_076_Remote <- subset(Data_DMA, Sample == "Patient_076_Remote", select=c(10:252))
Stat_045_Ischaemic <- subset(Data_DMA, Sample == "Patient_045_Ischaemic", select=c(10:252))
Stat_045_Remote <- subset(Data_DMA, Sample == "Patient_045_Remote", select=c(10:252))
Stat_083_Ischaemic <- subset(Data_DMA, Sample == "Patient_083_Ischaemic", select=c(10:252))
Stat_083_Remote <- subset(Data_DMA, Sample == "Patient_083_Remote", select=c(10:252))
Stat_100_Ischaemic <- subset(Data_DMA, Sample == "Patient_100_Ischaemic", select=c(10:252))
Stat_100_Remote <- subset(Data_DMA, Sample == "Patient_100_Remote", select=c(10:252))
Stat_068_Ischaemic <- subset(Data_DMA, Sample == "Patient_068_Ischaemic", select=c(10:252))
Stat_068_Remote <- subset(Data_DMA, Sample == "Patient_068_Remote", select=c(10:252))
Stat_091_Ischaemic <- subset(Data_DMA, Sample == "Patient_091_Ischaemic", select=c(10:252))
Stat_091_Remote <- subset(Data_DMA, Sample == "Patient_091_Remote", select=c(10:252))
Stat_102_Ischaemic <- subset(Data_DMA, Sample == "Patient_102_Ischaemic", select=c(10:252))
Stat_102_Remote <- subset(Data_DMA, Sample == "Patient_102_Remote", select=c(10:252))
Stat_043_Ischaemic <- subset(Data_DMA, Sample == "Patient_043_Ischaemic", select=c(10:252))
Stat_043_Remote <- subset(Data_DMA, Sample == "Patient_043_Remote", select=c(10:252))
#---------------------
## Mean of the replicates:
Data_DMA_Means <- (Data_DMA[,10:252]) %>%
group_by(Data_DMA$Sample) %>%
summarise_all(funs(mean))%>%
rename("Sample"="Data_DMA$Sample")
Mean_120_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_120_Ischaemic", select=c(2:244))
Mean_120_Remote <- subset(Data_DMA_Means, Sample == "Patient_120_Remote", select=c(2:244))
Mean_089_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_089_Ischaemic", select=c(2:244))
Mean_089_Remote <- subset(Data_DMA_Means, Sample == "Patient_089_Remote", select=c(2:244))
Mean_094_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_094_Ischaemic", select=c(2:244))
Mean_094_Remote <- subset(Data_DMA_Means, Sample == "Patient_094_Remote", select=c(2:244))
Mean_080_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_080_Ischaemic", select=c(2:244))
Mean_080_Remote <- subset(Data_DMA_Means, Sample == "Patient_080_Remote", select=c(2:244))
Mean_088_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_088_Ischaemic", select=c(2:244))
Mean_088_Remote <- subset(Data_DMA_Means, Sample == "Patient_088_Remote", select=c(2:244))
Mean_054_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_054_Ischaemic", select=c(2:244))
Mean_054_Remote <- subset(Data_DMA_Means, Sample == "Patient_054_Remote", select=c(2:244))
Mean_093_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_093_Ischaemic", select=c(2:244))
Mean_093_Remote <- subset(Data_DMA_Means, Sample == "Patient_093_Remote", select=c(2:244))
Mean_039_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_039_Ischaemic", select=c(2:244))
Mean_039_Remote <- subset(Data_DMA_Means, Sample == "Patient_039_Remote", select=c(2:244))
Mean_064_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_064_Ischaemic", select=c(2:244))
Mean_064_Remote <- subset(Data_DMA_Means, Sample == "Patient_064_Remote", select=c(2:244))
Mean_101_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_101_Ischaemic", select=c(2:244))
Mean_101_Remote <- subset(Data_DMA_Means, Sample == "Patient_101_Remote", select=c(2:244))
Mean_103_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_103_Ischaemic", select=c(2:244))
Mean_103_Remote <- subset(Data_DMA_Means, Sample == "Patient_103_Remote", select=c(2:244))
Mean_075_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_075_Ischaemic", select=c(2:244))
Mean_075_Remote <- subset(Data_DMA_Means, Sample == "Patient_075_Remote", select=c(2:244))
Mean_099_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_099_Ischaemic", select=c(2:244))
Mean_099_Remote <- subset(Data_DMA_Means, Sample == "Patient_099_Remote", select=c(2:244))
Mean_071_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_071_Ischaemic", select=c(2:244))
Mean_071_Remote <- subset(Data_DMA_Means, Sample == "Patient_071_Remote", select=c(2:244))
Mean_073_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_073_Ischaemic", select=c(2:244))
Mean_073_Remote <- subset(Data_DMA_Means, Sample == "Patient_073_Remote", select=c(2:244))
Mean_050_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_050_Ischaemic", select=c(2:244))
Mean_050_Remote <- subset(Data_DMA_Means, Sample == "Patient_050_Remote", select=c(2:244))
Mean_090_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_090_Ischaemic", select=c(2:244))
Mean_090_Remote <- subset(Data_DMA_Means, Sample == "Patient_090_Remote", select=c(2:244))
Mean_065_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_065_Ischaemic", select=c(2:244))
Mean_065_Remote <- subset(Data_DMA_Means, Sample == "Patient_065_Remote", select=c(2:244))
Mean_085_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_085_Ischaemic", select=c(2:244))
Mean_085_Remote <- subset(Data_DMA_Means, Sample == "Patient_085_Remote", select=c(2:244))
Mean_055_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_055_Ischaemic", select=c(2:244))
Mean_055_Remote <- subset(Data_DMA_Means, Sample == "Patient_055_Remote", select=c(2:244))
Mean_038_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_038_Ischaemic", select=c(2:244))
Mean_038_Remote <- subset(Data_DMA_Means, Sample == "Patient_038_Remote", select=c(2:244))
Mean_076_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_076_Ischaemic", select=c(2:244))
Mean_076_Remote <- subset(Data_DMA_Means, Sample == "Patient_076_Remote", select=c(2:244))
Mean_045_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_045_Ischaemic", select=c(2:244))
Mean_045_Remote <- subset(Data_DMA_Means, Sample == "Patient_045_Remote", select=c(2:244))
Mean_083_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_083_Ischaemic", select=c(2:244))
Mean_083_Remote <- subset(Data_DMA_Means, Sample == "Patient_083_Remote", select=c(2:244))
Mean_100_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_100_Ischaemic", select=c(2:244))
Mean_100_Remote <- subset(Data_DMA_Means, Sample == "Patient_100_Remote", select=c(2:244))
Mean_068_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_068_Ischaemic", select=c(2:244))
Mean_068_Remote <- subset(Data_DMA_Means, Sample == "Patient_068_Remote", select=c(2:244))
Mean_091_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_091_Ischaemic", select=c(2:244))
Mean_091_Remote <- subset(Data_DMA_Means, Sample == "Patient_091_Remote", select=c(2:244))
Mean_102_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_102_Ischaemic", select=c(2:244))
Mean_102_Remote <- subset(Data_DMA_Means, Sample == "Patient_102_Remote", select=c(2:244))
Mean_043_Ischaemic <- subset(Data_DMA_Means, Sample == "Patient_043_Ischaemic", select=c(2:244))
Mean_043_Remote <- subset(Data_DMA_Means, Sample == "Patient_043_Remote", select=c(2:244))
#---------------------
## Apply function:
DMA_ISCHEMIAvREMOTE_120 <- DMA(Log2FC_Condition1=Mean_120_Ischaemic,
Log2FC_Condition2=Mean_120_Remote,
Stat_Condition1=Stat_120_Ischaemic,
Stat_Condition2=Stat_120_Remote,
Patient_ID="Patient_120")
DMA_ISCHEMIAvREMOTE_089 <- DMA(Log2FC_Condition1=Mean_089_Ischaemic,
Log2FC_Condition2=Mean_089_Remote,
Stat_Condition1=Stat_089_Ischaemic,
Stat_Condition2=Stat_089_Remote,
Patient_ID="Patient_089")
DMA_ISCHEMIAvREMOTE_094 <- DMA(Log2FC_Condition1=Mean_094_Ischaemic,
Log2FC_Condition2=Mean_094_Remote,
Stat_Condition1=Stat_094_Ischaemic,
Stat_Condition2=Stat_094_Remote,
Patient_ID="Patient_094")
DMA_ISCHEMIAvREMOTE_080 <- DMA(Log2FC_Condition1=Mean_080_Ischaemic,
Log2FC_Condition2=Mean_080_Remote,
Stat_Condition1=Stat_080_Ischaemic,
Stat_Condition2=Stat_080_Remote,
Patient_ID="Patient_080")
DMA_ISCHEMIAvREMOTE_088 <- DMA(Log2FC_Condition1=Mean_088_Ischaemic,
Log2FC_Condition2=Mean_088_Remote,
Stat_Condition1=Stat_088_Ischaemic,
Stat_Condition2=Stat_088_Remote,
Patient_ID="Patient_088")
DMA_ISCHEMIAvREMOTE_054 <- DMA(Log2FC_Condition1=Mean_054_Ischaemic,
Log2FC_Condition2=Mean_054_Remote,
Stat_Condition1=Stat_054_Ischaemic,
Stat_Condition2=Stat_054_Remote,
Patient_ID="Patient_054")
DMA_ISCHEMIAvREMOTE_093 <- DMA(Log2FC_Condition1=Mean_093_Ischaemic,
Log2FC_Condition2=Mean_093_Remote,
Stat_Condition1=Stat_093_Ischaemic,
Stat_Condition2=Stat_093_Remote,
Patient_ID="Patient_093")
DMA_ISCHEMIAvREMOTE_039 <- DMA(Log2FC_Condition1=Mean_039_Ischaemic,
Log2FC_Condition2=Mean_039_Remote,
Stat_Condition1=Stat_039_Ischaemic,
Stat_Condition2=Stat_039_Remote,
Patient_ID="Patient_039")
DMA_ISCHEMIAvREMOTE_064 <- DMA(Log2FC_Condition1=Mean_064_Ischaemic,
Log2FC_Condition2=Mean_064_Remote,
Stat_Condition1=Stat_064_Ischaemic,
Stat_Condition2=Stat_064_Remote,
Patient_ID="Patient_064")
DMA_ISCHEMIAvREMOTE_101 <- DMA(Log2FC_Condition1=Mean_101_Ischaemic,
Log2FC_Condition2=Mean_101_Remote,
Stat_Condition1=Stat_101_Ischaemic,
Stat_Condition2=Stat_101_Remote,
Patient_ID="Patient_101")
DMA_ISCHEMIAvREMOTE_103 <- DMA(Log2FC_Condition1=Mean_103_Ischaemic,
Log2FC_Condition2=Mean_103_Remote,
Stat_Condition1=Stat_103_Ischaemic,
Stat_Condition2=Stat_103_Remote,
Patient_ID="Patient_103")
DMA_ISCHEMIAvREMOTE_075 <- DMA(Log2FC_Condition1=Mean_075_Ischaemic,
Log2FC_Condition2=Mean_075_Remote,
Stat_Condition1=Stat_075_Ischaemic,
Stat_Condition2=Stat_075_Remote,
Patient_ID="Patient_075")
DMA_ISCHEMIAvREMOTE_099 <- DMA(Log2FC_Condition1=Mean_099_Ischaemic,
Log2FC_Condition2=Mean_099_Remote,
Stat_Condition1=Stat_099_Ischaemic,
Stat_Condition2=Stat_099_Remote,
Patient_ID="Patient_099")
DMA_ISCHEMIAvREMOTE_054 <- DMA(Log2FC_Condition1=Mean_054_Ischaemic,
Log2FC_Condition2=Mean_054_Remote,
Stat_Condition1=Stat_054_Ischaemic,
Stat_Condition2=Stat_054_Remote,
Patient_ID="Patient_054")
DMA_ISCHEMIAvREMOTE_071 <- DMA(Log2FC_Condition1=Mean_071_Ischaemic,
Log2FC_Condition2=Mean_071_Remote,
Stat_Condition1=Stat_071_Ischaemic,
Stat_Condition2=Stat_071_Remote,
Patient_ID="Patient_071")
DMA_ISCHEMIAvREMOTE_073 <- DMA(Log2FC_Condition1=Mean_073_Ischaemic,
Log2FC_Condition2=Mean_073_Remote,
Stat_Condition1=Stat_073_Ischaemic,
Stat_Condition2=Stat_073_Remote,
Patient_ID="Patient_073")
DMA_ISCHEMIAvREMOTE_050 <- DMA(Log2FC_Condition1=Mean_050_Ischaemic,
Log2FC_Condition2=Mean_050_Remote,
Stat_Condition1=Stat_050_Ischaemic,
Stat_Condition2=Stat_050_Remote,
Patient_ID="Patient_050")
DMA_ISCHEMIAvREMOTE_090 <- DMA(Log2FC_Condition1=Mean_090_Ischaemic,
Log2FC_Condition2=Mean_090_Remote,
Stat_Condition1=Stat_090_Ischaemic,
Stat_Condition2=Stat_090_Remote,
Patient_ID="Patient_090")
DMA_ISCHEMIAvREMOTE_065 <- DMA(Log2FC_Condition1=Mean_065_Ischaemic,
Log2FC_Condition2=Mean_065_Remote,
Stat_Condition1=Stat_065_Ischaemic,
Stat_Condition2=Stat_065_Remote,
Patient_ID="Patient_065")
DMA_ISCHEMIAvREMOTE_085 <- DMA(Log2FC_Condition1=Mean_085_Ischaemic,
Log2FC_Condition2=Mean_085_Remote,
Stat_Condition1=Stat_085_Ischaemic,
Stat_Condition2=Stat_085_Remote,
Patient_ID="Patient_085")
DMA_ISCHEMIAvREMOTE_055 <- DMA(Log2FC_Condition1=Mean_055_Ischaemic,
Log2FC_Condition2=Mean_055_Remote,
Stat_Condition1=Stat_055_Ischaemic,
Stat_Condition2=Stat_055_Remote,
Patient_ID="Patient_055")
DMA_ISCHEMIAvREMOTE_038 <- DMA(Log2FC_Condition1=Mean_038_Ischaemic,
Log2FC_Condition2=Mean_038_Remote,
Stat_Condition1=Stat_038_Ischaemic,
Stat_Condition2=Stat_038_Remote,
Patient_ID="Patient_038")
DMA_ISCHEMIAvREMOTE_076 <- DMA(Log2FC_Condition1=Mean_076_Ischaemic,
Log2FC_Condition2=Mean_076_Remote,
Stat_Condition1=Stat_076_Ischaemic,
Stat_Condition2=Stat_076_Remote,
Patient_ID="Patient_076")
DMA_ISCHEMIAvREMOTE_045 <- DMA(Log2FC_Condition1=Mean_045_Ischaemic,
Log2FC_Condition2=Mean_045_Remote,
Stat_Condition1=Stat_045_Ischaemic,
Stat_Condition2=Stat_045_Remote,
Patient_ID="Patient_045")
DMA_ISCHEMIAvREMOTE_083 <- DMA(Log2FC_Condition1=Mean_083_Ischaemic,
Log2FC_Condition2=Mean_083_Remote,
Stat_Condition1=Stat_083_Ischaemic,
Stat_Condition2=Stat_083_Remote,
Patient_ID="Patient_083")
DMA_ISCHEMIAvREMOTE_100 <- DMA(Log2FC_Condition1=Mean_100_Ischaemic,
Log2FC_Condition2=Mean_100_Remote,
Stat_Condition1=Stat_100_Ischaemic,
Stat_Condition2=Stat_100_Remote,
Patient_ID="Patient_100")
DMA_ISCHEMIAvREMOTE_068 <- DMA(Log2FC_Condition1=Mean_068_Ischaemic,
Log2FC_Condition2=Mean_068_Remote,
Stat_Condition1=Stat_068_Ischaemic,
Stat_Condition2=Stat_068_Remote,
Patient_ID="Patient_068")
DMA_ISCHEMIAvREMOTE_091 <- DMA(Log2FC_Condition1=Mean_091_Ischaemic,
Log2FC_Condition2=Mean_091_Remote,
Stat_Condition1=Stat_091_Ischaemic,
Stat_Condition2=Stat_091_Remote,
Patient_ID="Patient_091")
DMA_ISCHEMIAvREMOTE_102 <- DMA(Log2FC_Condition1=Mean_102_Ischaemic,
Log2FC_Condition2=Mean_102_Remote,
Stat_Condition1=Stat_102_Ischaemic,
Stat_Condition2=Stat_102_Remote,
Patient_ID="Patient_102")
DMA_ISCHEMIAvREMOTE_043 <- DMA(Log2FC_Condition1=Mean_043_Ischaemic,
Log2FC_Condition2=Mean_043_Remote,
Stat_Condition1=Stat_043_Ischaemic,
Stat_Condition2=Stat_043_Remote,
Patient_ID="Patient_043")
#-----------------------
## Sum all the results into one dataframe
library(plyr)
DMA_ISCHEMIAvREMOTE <- join_all(list(DMA_ISCHEMIAvREMOTE_120,
DMA_ISCHEMIAvREMOTE_089,
DMA_ISCHEMIAvREMOTE_094,
DMA_ISCHEMIAvREMOTE_080,
DMA_ISCHEMIAvREMOTE_088,
DMA_ISCHEMIAvREMOTE_054,
DMA_ISCHEMIAvREMOTE_093,
DMA_ISCHEMIAvREMOTE_039,
DMA_ISCHEMIAvREMOTE_064,
DMA_ISCHEMIAvREMOTE_101,
DMA_ISCHEMIAvREMOTE_103,
DMA_ISCHEMIAvREMOTE_075,
DMA_ISCHEMIAvREMOTE_099,
DMA_ISCHEMIAvREMOTE_071,
DMA_ISCHEMIAvREMOTE_073,
DMA_ISCHEMIAvREMOTE_050,
DMA_ISCHEMIAvREMOTE_090,
DMA_ISCHEMIAvREMOTE_065,
DMA_ISCHEMIAvREMOTE_085,
DMA_ISCHEMIAvREMOTE_055,
DMA_ISCHEMIAvREMOTE_038,
DMA_ISCHEMIAvREMOTE_076,
DMA_ISCHEMIAvREMOTE_045,
DMA_ISCHEMIAvREMOTE_083,
DMA_ISCHEMIAvREMOTE_100,
DMA_ISCHEMIAvREMOTE_068,
DMA_ISCHEMIAvREMOTE_091,
DMA_ISCHEMIAvREMOTE_102,
DMA_ISCHEMIAvREMOTE_043),
by = 'Metabolite',
type = 'full')
write.csv(DMA_ISCHEMIAvREMOTE, "OutputData_AMBITION-Metabolomics/Sheet4_DMA_ISCHEMIAvREMOTE.csv")
#Needed for CorrelationPlot:
DMA_ISCHEMIAvREMOTE_Log2FC <- join_all(list(DMA_ISCHEMIAvREMOTE_120[,1:2],
DMA_ISCHEMIAvREMOTE_089[,1:2],
DMA_ISCHEMIAvREMOTE_094[,1:2],
DMA_ISCHEMIAvREMOTE_080[,1:2],
DMA_ISCHEMIAvREMOTE_088[,1:2],
DMA_ISCHEMIAvREMOTE_054[,1:2],
DMA_ISCHEMIAvREMOTE_093[,1:2],
DMA_ISCHEMIAvREMOTE_039[,1:2],
DMA_ISCHEMIAvREMOTE_064[,1:2],
DMA_ISCHEMIAvREMOTE_101[,1:2],
DMA_ISCHEMIAvREMOTE_103[,1:2],
DMA_ISCHEMIAvREMOTE_075[,1:2],
DMA_ISCHEMIAvREMOTE_099[,1:2],
DMA_ISCHEMIAvREMOTE_071[,1:2],
DMA_ISCHEMIAvREMOTE_073[,1:2],
DMA_ISCHEMIAvREMOTE_050[,1:2],
DMA_ISCHEMIAvREMOTE_090[,1:2],
DMA_ISCHEMIAvREMOTE_065[,1:2],
DMA_ISCHEMIAvREMOTE_085[,1:2],
DMA_ISCHEMIAvREMOTE_055[,1:2],
DMA_ISCHEMIAvREMOTE_038[,1:2],
DMA_ISCHEMIAvREMOTE_076[,1:2],
DMA_ISCHEMIAvREMOTE_045[,1:2],
DMA_ISCHEMIAvREMOTE_083[,1:2],
DMA_ISCHEMIAvREMOTE_100[,1:2],
DMA_ISCHEMIAvREMOTE_068[,1:2],
DMA_ISCHEMIAvREMOTE_091[,1:2],
DMA_ISCHEMIAvREMOTE_102[,1:2],
DMA_ISCHEMIAvREMOTE_043[,1:2]),
by = 'Metabolite',
type = 'full')
detach(package:plyr)#We need to detach this package cause it will mask dyplr!
```
## Sheet 5: DMA impaired LVEF versus preserved LVEF
Here we use the mean values of the analytical replicates and we can define the two samples we have for some patients (ischemia and remote) as two biological replicates. We have a total of 61 samples, of which 3 are from patients with only one biological replicate (036_Remote, 081_Ischaemic, 040_Ischaemic), whilst 58 samples are from 29 patients where always a sample of an ischemic area and from an remote area has been taken.\
Of all those samples we have 10 samples that have impaired LVEF and 51 with preserved LVEF. This is a quite unequal amount of samples we are comparing here, which we definitely have to keep in mind.\
Here we use the Mann-Whitney-Wilcoxon Test and p-value adjustment using Benjamini Hochberg.
```{r, warning= FALSE, message=FALSE}
# Prepare the Dataframes:
Data_DMA_2 <- H_Means%>%#remove the outliers!
unite("Sample",c("Patient.ID","class"),sep="_", remove=FALSE)
#--------------------
##Single replicates for STAT:
MPR_impairedLVEF <- subset(Data_DMA_2, Impaired.LVEF == "TRUE", select=c(7:249))
MPR_preservedLVEF <- subset(Data_DMA_2, Impaired.LVEF == "FALSE", select=c(7:249))
#---------------------
## Mean of the replicates:
Data_DMA_Means_2 <- (Data_DMA_2[,7:249]) %>%
group_by(Data_DMA_2$Impaired.LVEF) %>%
summarise_all(funs(mean))%>%
rename("Impaired.LVEF"="Data_DMA_2$Impaired.LVEF")
Mean_MPR_impairedLVEF <- subset(Data_DMA_Means_2, Impaired.LVEF == "TRUE", select=c(2:244))
Mean_MPR_preservedLVEF <- subset(Data_DMA_Means_2, Impaired.LVEF == "FALSE", select=c(2:244))
#---------------------
## Apply function:
DMA_Impairedvspreserved_LVEF <- DMA_Single(STAT_pval =wilcox.test,
STAT_padj = "BH",
Log2FC_Condition1=Mean_MPR_impairedLVEF,
Log2FC_Condition2=Mean_MPR_preservedLVEF,
Stat_Condition1=MPR_impairedLVEF,
Stat_Condition2=MPR_preservedLVEF,
Output="DMA_Impairedvspreserved_LVEF.csv")
#---------------------
## Add the metabolic pathways:
Template_Pathways <- read.csv("InputData_AMBITION-Metabolomics/Template_MetabolicPathways.csv")
DMA_Impairedvspreserved_LVEF <- merge(x=DMA_Impairedvspreserved_LVEF, y=Template_Pathways, by="Metabolite", all.x=TRUE)
write.csv(DMA_Impairedvspreserved_LVEF, "OutputData_AMBITION-Metabolomics/Sheet5_DMA_Impairedvspreserved_LVEF_Pathways.csv")
```
# Figures:
## PCA plot
PCA plot of ischemia and remote to show that the samples do not cluster apart (symbol = ischemia or remote and colour=patients). Here we include all the patients that do have an ischemia and/or an remote samples.
```{r, message=FALSE, warning=FALSE}
#Remove outliers (also the corresponding ischemia sample):
PCA_Plot <- subset(norm_outliers,Excluded == "NO")%>%#remove the outliers!
unite("Sample",c("Patient.ID","class"),sep="_", remove=FALSE)
#Remove patients where we do not have information about the region (Ischemic or remote):
PCA_Plot <- subset(PCA_Plot,class == "Ischaemic" |class == "Remote")
row.names(PCA_Plot) <- PCA_Plot$UniqueID
#------------------------
#PLOT
PCA_Data_m<- PCA_Plot[,10:252]
PCA_Data_m <- apply(as.matrix(PCA_Data_m), 2, as.numeric)
row.names(PCA_Data_m) <- PCA_Plot$UniqueID
PCA_NoLoadings(InputMatrix= PCA_Data_m, OutputPlotName= "Patients_IschemicVSremote",DF=PCA_Plot, Color = "Patient.ID", Shape = "class")
```
## Correlation plot
Differential metabolite analysis of each individual patient using the analytical replicates for the statistics. This is a paired analysis given that the differential metabolite analysis always compares the ischemic sample of a patients to its remote counterpart. The result is summarised in the correlation plot showing the Log2FC of each individual patient when comparing ischemic versus remote.\
This is done in order to find patients with similar patterns in the metabolite fold change when comparing ischemia versus remote and the correlation matrix highlights the most correlated variables in our data table.\
The correlation coefficients [%] are colored according to their values.\
IMPORTANT to note: Here all metabolites are included and it has not been taken into consideration if the Log2FC was significant\
```{r, message=FALSE, warning=FALSE}
Correlation <- DMA_ISCHEMIAvREMOTE_Log2FC
row.names(Correlation) <- Correlation$Metabolite
Correlation_Matrix <- as.matrix(Correlation[,2:30])
#--------------------------
Correlation_Result <- cor(Correlation_Matrix)
library(corrplot)#correlation matrix
library(RColorBrewer)
pdf(file="Figures_AMBITION-Metabolomics/CorrelationPlot_IschemiaVSremote_PatientsLog2FC.pdf", width=6, height=6)
corrplot(Correlation_Result,
tl.cex = 0.6,# tl = text labels of samples
tl.col = "black",
method = "color", #colour of the bar
cl.lim = c(-1, 1), #range of correlations
col = brewer.pal(n = 10, name = 'BrBG'),
addCoef.col ="white",
addCoefasPercent = TRUE,
number.cex=0.5,#number= the coefficient
is.corr=TRUE,
#outline="gray20",#outline around the square/circle
order="hclust",#"hclust" for the hierarchical clustering order
hclust.method="complete",
main="Patients Log2FC(Ischemia versus Remote) ",
cex.main=1
#addrect=5
)
dev.off()
corrplot(Correlation_Result,
tl.cex = 0.6,# tl = text labels of samples
tl.col = "black",
method = "color", #colour of the bar
cl.lim = c(-1, 1), #range of correlations
col = brewer.pal(n = 10, name = 'BrBG'),
addCoef.col ="white",
addCoefasPercent = TRUE,
number.cex=0.5,#number= the coefficient
is.corr=TRUE,
#outline="gray20",#outline around the square/circle
order="hclust",#"hclust" for the hierarchical clustering order
hclust.method="complete",
main="Patients Log2FC(Ischemia versus Remote) ",
cex.main=1
#addrect=5
)
```
## Volcano Plot
Here we plot the results of the differential metabolite analysis comparing impaired versus preserved LVEF. Additionally, we colour code for the manually assigned (based on a priori knowledge) metabolic pathways.
```{r, message=FALSE, warning=FALSE}
#Plot
VolcanoPlot_Pathways(DMA_Impairedvspreserved_LVEF, "Impairedvspreserved_LVEF")
```
## Violin plots
Here we plot the individual metabolite changes as violin plots. This is done using "Sheet 3: Mean of analytical replicates".\
### 1. Ischemia versus remote
```{r, message=FALSE, warning=FALSE}
# In order to be able to do a paired wilcox.test, we need to remove the patients that only have one sample:
H_Means_paired <- H_Means[-c(1, 6,33),] #Remove Patient 036, 040, 081