-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathUpSet Plots
201 lines (161 loc) · 10.7 KB
/
UpSet Plots
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
#UpSet Plots of CHDS DMRs ############################################################################################
# Sex differences in ASD ###########################################################################################
#Load Annotated DMRs from CHDS newborn blood
library(openxlsx)
TDfemalesASDfemales_DMRs_Annotated <- read.xlsx("/CHDS /DMRichR/Females/V2/DMRs/DMRs_annotated.xlsx")
TDmalesASDmales_DMRs_Annotated <- read.xlsx("/CHDS /DMRichR/Males/V7/DMRs/DMRs_annotated.xlsx")
ASDfemalesASDmales_DMRs_Annotated <- read.xlsx("/CHDS /DMRichR/MaleBrain_IncoherentGenderHypothesis/ASDfemalesASDmales/V1/DMRs/DMRs_annotated.xlsx")
TDfemalesTDmales_DMRs_Annotated <- read.xlsx("/CHDS /DMRichR/MaleBrain_IncoherentGenderHypothesis/TDfemalesTDmales/V1/DMRs/DMRs_annotated.xlsx")
ASDfemalesTDmales_DMRs_Annotated <- read.xlsx("/CHDS /DMRichR/MaleBrain_IncoherentGenderHypothesis/ASDfemalesTDmales/DMRs/DMRs_annotated.xlsx")
TDfemalesASDmales_DMRs_Annotated <- read.xlsx("/CHDS /DMRichR/MaleBrain_IncoherentGenderHypothesis/TDfemalesASDmales/DMRs/DMRs_annotated.xlsx")
#Remove all non-autosomal DMRs (chrX and chrY)
TDfemalesASDfemales_DMRs_Annotated_Autosomes <- subset(TDfemalesASDfemales_DMRs_Annotated, !(chr %in% c("chrX", "chrY")))
TDmalesASDmales_DMRs_Annotated_Autosomes <- subset(TDmalesASDmales_DMRs_Annotated, !(chr %in% c("chrX", "chrY")))
ASDfemalesASDmales_DMRs_Annotated_Autosomes <- subset(ASDfemalesASDmales_DMRs_Annotated, !(chr %in% c("chrX", "chrY")))
TDfemalesTDmales_DMRs_Annotated_Autosomes <- subset(TDfemalesTDmales_DMRs_Annotated, !(chr %in% c("chrX", "chrY")))
ASDfemalesTDmales_DMRs_Annotated_Autosomes <- subset(ASDfemalesTDmales_DMRs_Annotated, !(chr %in% c("chrX", "chrY")))
TDfemalesASDmales_DMRs_Annotated_Autosomes <- subset(TDfemalesASDmales_DMRs_Annotated, !(chr %in% c("chrX", "chrY")))
# Get list of unique genes that DMRs map to for each dataset ##########################
TDfemalesASDfemales_Unique_GeneNames <- unique(TDfemalesASDfemales_DMRs_Annotated_Autosomes$geneSymbol)
TDmalesASDmales_Unique_GeneNames <- unique(TDmalesASDmales_DMRs_Annotated_Autosomes$geneSymbol)
ASDfemalesASDmales_Unique_GeneNames <- unique(ASDfemalesASDmales_DMRs_Annotated_Autosomes$geneSymbol)
TDfemalesTDmales_Unique_GeneNames <- unique(TDfemalesTDmales_DMRs_Annotated_Autosomes$geneSymbol)
ASDfemalesTDmales_Unique_GeneNames <- unique(ASDfemalesTDmales_DMRs_Annotated_Autosomes$geneSymbol)
TDfemalesASDmales_Unique_GeneNames <- unique(TDfemalesASDmales_DMRs_Annotated_Autosomes$geneSymbol)
DMRgeneList <- list(TDfemales_ASDfemales = TDfemalesASDfemales_Unique_GeneNames, TDmales_ASDmales = TDmalesASDmales_Unique_GeneNames, ASDfemales_ASDmales = ASDfemalesASDmales_Unique_GeneNames,
TDfemales_TDmales = TDfemalesTDmales_Unique_GeneNames)
DMRgeneList_Full <- list(TDfemales_ASDfemales = TDfemalesASDfemales_Unique_GeneNames, TDmales_ASDmales = TDmalesASDmales_Unique_GeneNames, ASDfemales_ASDmales = ASDfemalesASDmales_Unique_GeneNames,
TDfemales_TDmales = TDfemalesTDmales_Unique_GeneNames, ASDfemales_TDmales = ASDfemalesTDmales_Unique_GeneNames, TDfemales_ASDmales = TDfemalesASDmales_Unique_GeneNames)
#Make UpSet Plot using DMRs from TD females v ASD females, TD males vs ASD males, ASD females vs ASD males, and TD females vs TD males ##############################
install.packages("UpSetR")
library(UpSetR)
pdf("CHDS_DMRs_UpSet_Plot.pdf", width = 8, height = 6)
upset(fromList(DMRgeneList),
order.by = "freq",
nsets = 6,
mainbar.y.label = "DMR Gene Name Intersections",
sets.x.label = "DMR Gene Names",
point.size = 3,
text.scale = 1.5)
dev.off()
# Make UpSet Plot using all DMR comparisons: TD females v ASD females, TD males vs ASD males, ASD females vs ASD males, TD females vs TD males, ASD females vs TD males, TD females vs ASD males ######
pdf("CHDS_DMRs_UpSet_Plot_Full.pdf", width = 10, height = 6)
upset(fromList(DMRgeneList_Full),
order.by = "freq",
nsets = 6,
mainbar.y.label = "DMR Gene Name Intersections",
sets.x.label = "DMR Gene Names",
point.size = 3,
text.scale = 1.5)
dev.off()
###################################################################################################################################
# Tissue comparisons of ASD DMRs ################################################################################
# Newborn Blood Data ####
# Discovery DMR Genes
CHDS_Combined_DMR_Genes <- read.xlsx("/CHDS /DMRichR/SexCombined/DMRs/DMRs_annotated.xlsx")
CHDS_Females_DMR_Genes <- read.xlsx("/CHDS /DMRichR/Females/DMRs/DMRs_annotated.xlsx")
CHDS_Males_DMR_Genes <- read.xlsx("/CHDS /DMRichR/Males/DMRs/DMRs_annotated.xlsx")
# Replication DMR Genes
ECHO_Combined_DMR_Genes <- read.xlsx("/ReCHARGE:ECHO/ASD NDBS NovaSeq260/DMRichR/Combined/DMRs/DMRs_annotated.xlsx")
ECHO_Males_DMR_Genes <- read.xlsx("/ReCHARGE:ECHO/ASD NDBS NovaSeq260/DMRichR/Males/DMRs/DMRs_annotated.xlsx")
ECHO_Females_DMR_Genes <- read.xlsx("/ReCHARGE:ECHO/ASD NDBS NovaSeq260/DMRichR/Females/DMRs/DMRs_annotated.xlsx")
# Cord Blood DMR Genes ####
Cord_Combined_DMR_Genes <- read.xlsx("/CHDS /CordBlood/DMRichR/Combined/DMRs/DMRs_annotated.xlsx")
Cord_Females_DMR_Genes <- read.xlsx("/CHDS /CordBlood/DMRichR/Females/DMRs/DMRs_annotated.xlsx")
Cord_Males_DMR_Genes <- read.xlsx("/CHDS /CordBlood/DMRichR/Males/DMRs/DMRs_annotated.xlsx")
# Placenta DMR Genes ######
Placenta_Combined_DMR_Genes <- read.xlsx("/CHDS /Placenta/DMRichR/Combined/DMRs/DMRs_annotated.xlsx")
Placenta_Females_DMR_Genes <- read.xlsx("/CHDS /Placenta/DMRichR/Females/DMRs/DMRs_annotated.xlsx")
Placenta_Males_DMR_Genes <- read.xlsx("/CHDS /Placenta/DMRichR/Males/DMRs/DMRs_annotated.xlsx")
# Cortex DMR Genes #######
Cortex_Combined_DMR_Genes <- read.xlsx("/CHDS /Cortex/DMRichR/Combined/DMRs/DMRs_annotated.xlsx")
Cortex_Females_DMR_Genes <- read.xlsx("/CHDS /Cortex/DMRichR/Females/DMRs/DMRs_annotated.xlsx")
Cortex_Males_DMR_Genes <- read.xlsx("/CHDS /Cortex/DMRichR/Males/DMRs/DMRs_annotated.xlsx")
### Females ######################################################################################################################
# Get unique gene names
CHDS_Females_DMR_Genes_Unique <- unique(CHDS_Females_DMR_Genes$geneSymbol)
Cord_Females_DMR_Genes_Unique <- unique(Cord_Females_DMR_Genes$geneSymbol)
Placenta_Females_DMR_Genes_Unique <- unique(Placenta_Females_DMR_Genes$geneSymbol)
Cortex_Females_DMR_Genes_Unique <- unique(Cortex_Females_DMR_Genes$geneSymbol)
DMR_GeneList_Females <- list(DiscoveryNewbornBlood = CHDS_Females_DMR_Genes_Unique,
CordBlood = Cord_Females_DMR_Genes_Unique,
Placenta = Placenta_Females_DMR_Genes_Unique,
Cortex = Cortex_Females_DMR_Genes_Unique)
# Convert the list into a binary matrix
binary_matrix_Females <- fromList(DMR_GeneList_Females)
# Filter the binary matrix to keep only rows (gene intersections) where DiscoveryNewbornBlood is present (i.e., column value is 1)
filtered_matrix_Females <- binary_matrix_Females[binary_matrix_Females$DiscoveryNewbornBlood == 1, ]
# Create the UpSet plot using the filtered data
dev.off()
pdf("CHDS_DMR_Genes_TissueOverlaps_UpSet_Plot_Females.pdf", width = 8, height = 6, onefile = FALSE)
upset(filtered_matrix_Females,
keep.order = TRUE,
set_size.show = FALSE,
order.by = "degree",
decreasing = FALSE,
nsets = 4,
sets = c("Cortex", "Placenta", "CordBlood", "DiscoveryNewbornBlood"),
mainbar.y.label = "DMR Gene Name Intersections",
sets.x.label = "",
point.size = 3,
text.scale = 2,
sets.bar.color = NA)
dev.off()
### Males ######################################################################################################################
# Get unique gene names
CHDS_Males_DMR_Genes_Unique <- unique(CHDS_Males_DMR_Genes$geneSymbol)
Cord_Males_DMR_Genes_Unique <- unique(Cord_Males_DMR_Genes$geneSymbol)
Placenta_Males_DMR_Genes_Unique <- unique(Placenta_Males_DMR_Genes$geneSymbol)
Cortex_Males_DMR_Genes_Unique <- unique(Cortex_Males_DMR_Genes$geneSymbol)
DMR_GeneList_Males <- list(DiscoveryNewbornBlood = CHDS_Males_DMR_Genes_Unique,
CordBlood = Cord_Males_DMR_Genes_Unique,
Placenta = Placenta_Males_DMR_Genes_Unique,
Cortex = Cortex_Males_DMR_Genes_Unique)
# Convert the list into a binary matrix
binary_matrix_Males <- fromList(DMR_GeneList_Males)
# Filter the binary matrix to keep only rows (gene intersections) where DiscoveryNewbornBlood is present (i.e., column value is 1)
filtered_matrix_Males <- binary_matrix_Males[binary_matrix_Males$DiscoveryNewbornBlood == 1, ]
# Create the UpSet plot using the filtered data
dev.off()
pdf("CHDS_DMR_Genes_TissueOverlaps_UpSet_Plot_Males.pdf", width = 8, height = 6, onefile = FALSE)
upset(filtered_matrix_Males,
keep.order = TRUE,
order.by = "degree",
decreasing = FALSE,
nsets = 4,
sets = c("Cortex", "Placenta", "CordBlood", "DiscoveryNewbornBlood"),
mainbar.y.label = "DMR Gene Name Intersections",
sets.x.label = "",
point.size = 3,
text.scale = 2,
sets.bar.color = NA)
dev.off()
### Sex Combined ######################################################################################################################
# Get unique gene names
CHDS_Combined_DMR_Genes_Unique <- unique(CHDS_Combined_DMR_Genes$geneSymbol)
Cord_Combined_DMR_Genes_Unique <- unique(Cord_Combined_DMR_Genes$geneSymbol)
Placenta_Combined_DMR_Genes_Unique <- unique(Placenta_Combined_DMR_Genes$geneSymbol)
Cortex_Combined_DMR_Genes_Unique <- unique(Cortex_Combined_DMR_Genes$geneSymbol)
DMR_GeneList_Combined <- list(DiscoveryNewbornBlood = CHDS_Combined_DMR_Genes_Unique,
CordBlood = Cord_Combined_DMR_Genes_Unique,
Placenta = Placenta_Combined_DMR_Genes_Unique,
Cortex = Cortex_Combined_DMR_Genes_Unique)
# Convert the list into a binary matrix
binary_matrix_Combined <- fromList(DMR_GeneList_Combined)
# Filter the binary matrix to keep only rows (gene intersections) where DiscoveryNewbornBlood is present (i.e., column value is 1)
filtered_matrix_Combined <- binary_matrix_Combined[binary_matrix_Combined$DiscoveryNewbornBlood == 1, ]
# Create the UpSet plot using the filtered data
dev.off()
pdf("CHDS_DMR_Genes_TissueOverlaps_UpSet_Plot_Combined.pdf", width = 8, height = 6, onefile = FALSE)
upset(filtered_matrix_Combined,
keep.order = TRUE,
order.by = "degree",
decreasing = FALSE,
nsets = 4,
sets = c("Cortex", "Placenta", "CordBlood", "DiscoveryNewbornBlood"),
mainbar.y.label = "DMR Gene Name Intersections",
sets.x.label = "",
point.size = 3,
text.scale = 2,
sets.bar.color = NA)
dev.off()