-
Notifications
You must be signed in to change notification settings - Fork 13
/
Copy pathSupplemental_Blastn_Figure
200 lines (165 loc) · 9.78 KB
/
Supplemental_Blastn_Figure
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
###SUPPLEMENTAL BLASTING
##mouse
setwd("~/Dropbox/lncRNA_03092017")
blast_genes_mouse <- read.table("coding_mm38_trans.outfmt6")
blast_lncRNA_mouse <- read.table("lncRNA_mm38_trans.outfmt6")
##[3]=%identity,
#make a new column in dataset that is %identity*%coverage
library(plyr)
blast_lncRNA_new<- ddply(blast_lncRNA_mouse, c("V1"), summarise,
cons=V3*(V4/100))
blast_genes_new<- ddply(blast_genes_mouse, c("V1"), summarise,
cons=V3*(V4/100))
blast_lncRNA_new <- blast_lncRNA_new[with(blast_lncRNA_new, order(V1, cons, decreasing = T)), ]
blast_lncRNA_new <- blast_lncRNA_new[!duplicated(blast_lncRNA_new$V1),]
blast_genes_new <- blast_genes_new[with(blast_genes_new, order(V1, cons, decreasing = T)), ]
blast_genes_new <- blast_genes_new[!duplicated(blast_genes_new$V1),]
#need to calc or count-freq of each identity*coverage then cumsum(this)=y
blast_lncRNA_freq <- count(blast_lncRNA_new,'cons')
blast_genes_freq <- count(blast_genes_new,'cons')
blast_lncRNA_freq_cumsum <- cbind(blast_lncRNA_freq,cumsum(blast_lncRNA_freq$freq))
blast_genes_freq_cumsum <- cbind(blast_genes_freq,cumsum(blast_genes_freq$freq))
names(blast_lncRNA_freq_cumsum)[3] <-"cumsum"
names(blast_genes_freq_cumsum)[3] <-"cumsum"
##using total transcript count (replace line 32 - 44)
setwd("~/Dropbox/lncRNA")
nc_count=length(readLines("lncRNA_final.bed"))
cod_count=length(readLines("refined_codingRNA.bed"))
blast_lncRNA_freq_cumsum[1,2]= blast_lncRNA_freq_cumsum[1,2] + (nc_count - dim(blast_lncRNA_new)[1])
blast_lncRNA_freq_cumsum[,3]= blast_lncRNA_freq_cumsum[,3] + (nc_count - dim(blast_lncRNA_new)[1])
blast_genes_freq_cumsum[1,2]= blast_genes_freq_cumsum[1,2] + (cod_count - dim(blast_genes_new)[1])
blast_genes_freq_cumsum[,3]= blast_genes_freq_cumsum[,3] + (cod_count - dim(blast_genes_new)[1])
blast_lncRNA_freq_cumsum["cum_rel"]<-(blast_lncRNA_freq_cumsum$cumsum/nc_count)
blast_genes_freq_cumsum["cum_rel"]<-(blast_genes_freq_cumsum$cumsum/cod_count)
blast_lncRNA_gene_cumsum_rel_mouse <- rbind(data.frame(id="lncRNA",blast_lncRNA_freq_cumsum),
data.frame(id="PCG",blast_genes_freq_cumsum))
setwd("~/Dropbox/lncRNA_03092017")
write.table(blast_lncRNA_gene_cumsum_rel_mouse, "blast_lncRNA_gene_cumsum_rel_mouse.txt")
# plot
require(ggplot2)
pdf("Fig3_mouse.pdf")
ggplot(blast_lncRNA_gene_cumsum_rel, aes(x=cons, y=cum_rel, colour=id, group=id)) +
geom_line(lwd=2) + ylab("Cumulative frequency") +
scale_color_discrete(name="Type of annotation",
labels=c("lncRNA","Protein coding transcript")) + xlab("Blast conservation") +
theme(legend.title = element_text(colour="black", size=16, face="bold")) +
theme(legend.text = element_text(colour="black", size = 14)) +
theme(axis.text = element_text(colour="black", size = 11)) +
theme(axis.title = element_text(colour="black", size = 16, face="bold")) +
theme(panel.background = element_rect(colour = "black", size=0.25))
dev.off()
##COW
##Cow
blast_genes_cow <- read.table("coding_bt_trans.outfmt6")
blast_lncRNA_cow <- read.table("lncRNA_bt_trans.outfmt6")
##[3]=%identity,
#make a new column in dataset that is %identity*%coverage
library(plyr)
blast_lncRNA_new<- ddply(blast_lncRNA_cow, c("V1"), summarise,
cons=V3*(V4/100))
blast_genes_new<- ddply(blast_genes_cow, c("V1"), summarise,
cons=V3*(V4/100))
blast_lncRNA_new <- blast_lncRNA_new[with(blast_lncRNA_new, order(V1, cons, decreasing = T)), ]
blast_lncRNA_new <- blast_lncRNA_new[!duplicated(blast_lncRNA_new$V1),]
blast_genes_new <- blast_genes_new[with(blast_genes_new, order(V1, cons, decreasing = T)), ]
blast_genes_new <- blast_genes_new[!duplicated(blast_genes_new$V1),]
#need to calc or count-freq of each identity*coverage then cumsum(this)=y
blast_lncRNA_freq <- count(blast_lncRNA_new,'cons')
blast_genes_freq <- count(blast_genes_new,'cons')
blast_lncRNA_freq_cumsum <- cbind(blast_lncRNA_freq,cumsum(blast_lncRNA_freq$freq))
blast_genes_freq_cumsum <- cbind(blast_genes_freq,cumsum(blast_genes_freq$freq))
names(blast_lncRNA_freq_cumsum)[3] <-"cumsum"
names(blast_genes_freq_cumsum)[3] <-"cumsum"
## using total transcript count (replace line 32 - 44)
setwd("~/Dropbox/lncRNA")
nc_count=length(readLines("lncRNA_final.bed"))
cod_count=length(readLines("refined_codingRNA.bed"))
blast_lncRNA_freq_cumsum[1,2]= blast_lncRNA_freq_cumsum[1,2] + (nc_count - dim(blast_lncRNA_new)[1])
blast_lncRNA_freq_cumsum[,3]= blast_lncRNA_freq_cumsum[,3] + (nc_count - dim(blast_lncRNA_new)[1])
blast_genes_freq_cumsum[1,2]= blast_genes_freq_cumsum[1,2] + (cod_count - dim(blast_genes_new)[1])
blast_genes_freq_cumsum[,3]= blast_genes_freq_cumsum[,3] + (cod_count - dim(blast_genes_new)[1])
blast_lncRNA_freq_cumsum["cum_rel"]<-(blast_lncRNA_freq_cumsum$cumsum/nc_count)
blast_genes_freq_cumsum["cum_rel"]<-(blast_genes_freq_cumsum$cumsum/cod_count)
blast_lncRNA_gene_cumsum_rel_cow <- rbind(data.frame(id="lncRNA",blast_lncRNA_freq_cumsum),
data.frame(id="PCG",blast_genes_freq_cumsum))
setwd("~/Dropbox/lncRNA_03092017")
write.table(blast_lncRNA_gene_cumsum_rel_cow, "blast_lncRNA_gene_cumsum_rel_cow.txt")
# plot
require(ggplot2)
pdf("Fig3_cow.pdf")
ggplot(blast_lncRNA_gene_cumsum_rel, aes(x=cons, y=cum_rel, colour=id, group=id)) +
geom_line(lwd=2) + ylab("Cumulative frequency") +
scale_color_discrete(name="Type of annotation",
labels=c("lncRNA","Protein coding transcript")) + xlab("Blast conservation") +
theme(legend.title = element_text(colour="black", size=16, face="bold")) +
theme(legend.text = element_text(colour="black", size = 14)) +
theme(axis.text = element_text(colour="black", size = 11)) +
theme(axis.title = element_text(colour="black", size = 16, face="bold")) +
theme(panel.background = element_rect(colour = "black", size=0.25))
dev.off()
##PIG
blast_genes_pig <- read.table("coding_ss10_trans.outfmt6")
blast_lncRNA_pig <- read.table("lncRNA_ss10_trans.outfmt6")
##[3]=%identity,
#make a new column in dataset that is %identity*%coverage
library(plyr)
blast_lncRNA_new<- ddply(blast_lncRNA_pig, c("V1"), summarise,
cons=V3*(V4/100))
blast_genes_new<- ddply(blast_genes_pig, c("V1"), summarise,
cons=V3*(V4/100))
blast_lncRNA_new <- blast_lncRNA_new[with(blast_lncRNA_new, order(V1, cons, decreasing = T)), ]
blast_lncRNA_new <- blast_lncRNA_new[!duplicated(blast_lncRNA_new$V1),]
blast_genes_new <- blast_genes_new[with(blast_genes_new, order(V1, cons, decreasing = T)), ]
blast_genes_new <- blast_genes_new[!duplicated(blast_genes_new$V1),]
#need to calc or count-freq of each identity*coverage then cumsum(this)=y
blast_lncRNA_freq <- count(blast_lncRNA_new,'cons')
blast_genes_freq <- count(blast_genes_new,'cons')
blast_lncRNA_freq_cumsum <- cbind(blast_lncRNA_freq,cumsum(blast_lncRNA_freq$freq))
blast_genes_freq_cumsum <- cbind(blast_genes_freq,cumsum(blast_genes_freq$freq))
names(blast_lncRNA_freq_cumsum)[3] <-"cumsum"
names(blast_genes_freq_cumsum)[3] <-"cumsum"
##using total transcript count (replace line 32 - 44)
setwd("~/Dropbox/lncRNA")
nc_count=length(readLines("lncRNA_final.bed"))
cod_count=length(readLines("refined_codingRNA.bed"))
blast_lncRNA_freq_cumsum[1,2]= blast_lncRNA_freq_cumsum[1,2] + (nc_count - dim(blast_lncRNA_new)[1])
blast_lncRNA_freq_cumsum[,3]= blast_lncRNA_freq_cumsum[,3] + (nc_count - dim(blast_lncRNA_new)[1])
blast_genes_freq_cumsum[1,2]= blast_genes_freq_cumsum[1,2] + (cod_count - dim(blast_genes_new)[1])
blast_genes_freq_cumsum[,3]= blast_genes_freq_cumsum[,3] + (cod_count - dim(blast_genes_new)[1])
blast_lncRNA_freq_cumsum["cum_rel"]<-(blast_lncRNA_freq_cumsum$cumsum/nc_count)
blast_genes_freq_cumsum["cum_rel"]<-(blast_genes_freq_cumsum$cumsum/cod_count)
blast_lncRNA_gene_cumsum_rel_pig <- rbind(data.frame(id="lncRNA",blast_lncRNA_freq_cumsum),
data.frame(id="PCG",blast_genes_freq_cumsum))
setwd("~/Dropbox/lncRNA_03092017")
write.table(blast_lncRNA_gene_cumsum_rel_pig, "blast_lncRNA_gene_cumsum_rel_pig.txt")
# plot
require(ggplot2)
pdf("Fig3_mouse.pdf")
ggplot(blast_lncRNA_gene_cumsum_rel, aes(x=cons, y=cum_rel, colour=id, group=id)) +
geom_line(lwd=2) + ylab("Cumulative frequency") +
scale_color_discrete(name="Type of annotation",
labels=c("lncRNA","Protein coding transcript")) + xlab("Blast conservation") +
theme(legend.title = element_text(colour="black", size=16, face="bold")) +
theme(legend.text = element_text(colour="black", size = 14)) +
theme(axis.text = element_text(colour="black", size = 11)) +
theme(axis.title = element_text(colour="black", size = 16, face="bold")) +
theme(panel.background = element_rect(colour = "black", size=0.25))
dev.off()
##combining all the species into one plot
ggplot() +
geom_line(data=blast_lncRNA_gene_cumsum_rel_mouse, aes(x=cons, y=cum_rel, linetype=id, group=id, colour="mouse")) +
geom_line(data=blast_lncRNA_gene_cumsum_rel_cow, aes(x=cons, y=cum_rel, linetype=id, group=id, colour="cow")) +
geom_line(data=blast_lncRNA_gene_cumsum_rel_pig, aes(x=cons, y=cum_rel, linetype=id, group=id, colour="pig")) +
ylab("Cumulative frequency") +
scale_colour_manual(name="Species",
values=c("green", "blue", "red"),
labels=c("mouse","cow", "pig")) +
scale_linetype_manual(name="Type of annotation",
values=c("twodash", "solid"),
labels=c("lncRNA","Protein coding transcript")) +
xlab("Blast conservation") +
theme(legend.title = element_text(colour="black", size=16, face="bold")) +
theme(legend.text = element_text(colour="black", size = 14)) +
theme(axis.text = element_text(colour="black", size = 11)) +
theme(axis.title = element_text(colour="black", size = 16, face="bold")) +
theme(panel.background = element_rect(colour = "black", size=0.25))