-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathSuppl.Fig3.Rmd
118 lines (92 loc) · 4.05 KB
/
Suppl.Fig3.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
---
title: "Suppl.Fig3"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
# libraries
```{r message=FALSE}
library(plyr)
library(dplyr)
library(tidyr)
library(tibble)
library(ggplot2)
library(ComplexHeatmap)
library(colorspace)
```
# supplimentary figure 3A-I
```{r message=FALSE}
protein_quant_minDet_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_MINDET_prefilt_32021.csv")
protein_quant_knn_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_KNN_prefilt_32021.csv")
protein_quant_minProb_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_MINPROB_prefilt_32021.csv")
protein_quant_svd_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_SVD_prefilt_32021.csv")
protein_quant_bpca_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_BPCA_prefilt_32021.csv")
protein_quant_norm_noimp <- read.csv("./Data/prot_quant_msstats_mapdia_filt_SDF2_pilot_NOIMP_31621.csv")
protein_quant_zero_noimp <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_ZERO_prefilt_32021.csv")
protein_quant_lls_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_LLS_prefilt_32021.csv")
protein_quant_rf_pocroc <- read.csv("./Data/prot_quant_msstats_SDF2_pilot_RF_prefilt_32021.csv")
protein_quant_norm_noimp <- subset(protein_quant_norm_noimp, select = -c(pool__4,
pool__5,
pool__6))
data_correct_format <- function(data){
df <- as.data.frame(data[-1,-1])
rownames(df) <- NULL
df <- column_to_rownames(df, "Protein")
}
protein_quant_norm_noimp <- data_correct_format(protein_quant_norm_noimp)
protein_quant_zero_noimp <- data_correct_format(protein_quant_zero_noimp)
protein_quant_minDet_pocroc <- data_correct_format(protein_quant_minDet_pocroc)
protein_quant_minProb_pocroc <- data_correct_format(protein_quant_minProb_pocroc)
protein_quant_knn_pocroc <- data_correct_format(protein_quant_knn_pocroc)
protein_quant_svd_pocroc <- data_correct_format(protein_quant_svd_pocroc)
protein_quant_bpca_pocroc <- data_correct_format(protein_quant_bpca_pocroc)
protein_quant_lls_pocroc <- data_correct_format(protein_quant_lls_pocroc)
protein_quant_rf_pocroc <- data_correct_format(protein_quant_rf_pocroc)
protein_quant_norm_noimp[is.na(protein_quant_norm_noimp)] <- 0
protein_quant_zero_noimp[is.na(protein_quant_zero_noimp)] <- 0
protein_quant_lls_pocroc <- na.omit(protein_quant_lls_pocroc)
data_correlation <- function(data){
cor_data <- as.data.frame(cor(data[,c(1:14)]))
if(all(colnames(protein_quant_norm_noimp) == colnames(cor_data))){
colnames(cor_data) <- c("1_1", "1_2", "1_3", "2_1", "2_2",
"3_1", "3_2", "4_1", "4_2", "4_3",
"5_1", "5_2", "6_1", "6_2")
rownames(cor_data) <- colnames(cor_data)
}else{
print("Column names do not match")
}
cor_data
}
corr_noimp <- data_correlation(protein_quant_norm_noimp)
corr_zero <- data_correlation(protein_quant_zero_noimp)
corr_mindet <- data_correlation(protein_quant_minDet_pocroc)
corr_minprob <- data_correlation(protein_quant_minProb_pocroc)
corr_knn <- data_correlation(protein_quant_knn_pocroc)
corr_svd <- data_correlation(protein_quant_svd_pocroc)
corr_bpca <- data_correlation(protein_quant_bpca_pocroc)
corr_lls <- data_correlation(protein_quant_lls_pocroc)
corr_rf <- data_correlation(protein_quant_rf_pocroc)
s9 <- sequential_hcl(9, "Reds", rev = T)
hmap <- Heatmap(
corr_rf,
name = "Pearson's Correlation Coefficient",
show_row_names = T,
show_column_names = T,
cluster_rows = T,
cluster_columns = T,
show_column_dend = FALSE,
show_row_dend = FALSE,
row_dend_reorder = TRUE,
column_dend_reorder = TRUE,
clustering_method_rows = "ward.D2",
clustering_method_columns = "ward.D2",
width = unit(100, "mm"),
col = s9,
column_names_gp = gpar(fontsize = 25),
row_names_gp = gpar(fontsize = 25),
heatmap_legend_param = list(
title = "Pearson's correlation coefficient",
title_position = "leftcenter-rot"))
draw(hmap, heatmap_legend_side="left")
```