-
Notifications
You must be signed in to change notification settings - Fork 2
/
.Rhistory
266 lines (266 loc) · 11.2 KB
/
.Rhistory
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
#Load the edgeR library
library("edgeR")
#Import gene count data
countsTable <- read.csv("/home/mae/Documents/RNASeq_Workshop_ND/daphnia_genesCounted.csv", row.names="gene")[ ,1:6]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Write normalized counts to file
normList <- cpm(list, normalized.lib.sizes=TRUE)
write.table(normList, file="normalizedCounts.csv", sep=",", row.names=TRUE)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
topTags(tested)
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Output resulting table
write.table(resultsTbl, file="exactTestResults.csv", sep=",", row.names=TRUE)
#Load the edgeR library
library("edgeR")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,1:6]
head(countsTable)
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#Plot the library sizes before normalization
jpeg("plotBarsBefore.jpg")
barplot(list$samples$lib.size*1e-6, names=1:6, ylab="Library size (millions)")
dev.off()
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
topTags(tested)
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Output resulting table
write.table(resultsTbl, file="stats_exactTest.csv", sep=",", row.names=TRUE)
#Load the edgeR library
library("edgeR")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,1:6]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
resultsTbl
nrow(resultsTbl)
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,7:13]
head(countsTable)
#Load the edgeR library
library("edgeR")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,7:12]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
nrow(resultsTbl)
#Load the edgeR library
library("edgeR")
#Set index range for selected genotype
start=1
end=6
outputName=paste(start,end,"exactTest.csv",sep="_")
outputName
#Import gene count data
countsTable <- read.csv(file=args[1], row.names="gene")[ ,start:end]
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,start:end]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Write test results to csv file
write.table(resultsTbl, file=outputName, sep=",", row.names=TRUE)
#!/usr/bin/env Rscript
#Usage: Rscript exactTest_edgeR.r countsFile.csv startColumn endColumn
#Usage Ex: Rscript exactTest_edgeR.r daphnia_genesCounted.csv 1 6
#R script to perform statistical analysis of gene count tables using edgeR exact test
#Install edgeR, this should only need to be done once
#if (!requireNamespace("BiocManager", quietly = TRUE))
# install.packages("BiocManager")
#BiocManager::install("edgeR")
#Load the edgeR library
library("edgeR")
#Set index range for selected genotype
start=7
end=12
outputName=paste(start,end,"exactTest.csv",sep="_")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,start:end]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Write test results to csv file
write.table(resultsTbl, file=outputName, sep=",", row.names=TRUE)
#!/usr/bin/env Rscript
#Usage: Rscript exactTest_edgeR.r countsFile.csv startColumn endColumn
#Usage Ex: Rscript exactTest_edgeR.r daphnia_genesCounted.csv 1 6
#R script to perform statistical analysis of gene count tables using edgeR exact test
#Install edgeR, this should only need to be done once
#if (!requireNamespace("BiocManager", quietly = TRUE))
# install.packages("BiocManager")
#BiocManager::install("edgeR")
#Load the edgeR library
library("edgeR")
#Set index range for selected genotype
start=13
end=18
outputName=paste(start,end,"exactTest.csv",sep="_")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,start:end]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Write test results to csv file
write.table(resultsTbl, file=outputName, sep=",", row.names=TRUE)
head(countsTable)
#!/usr/bin/env Rscript
#Usage: Rscript exactTest_edgeR.r countsFile.csv startColumn endColumn
#Usage Ex: Rscript exactTest_edgeR.r daphnia_genesCounted.csv 1 6
#R script to perform statistical analysis of gene count tables using edgeR exact test
#Install edgeR, this should only need to be done once
#if (!requireNamespace("BiocManager", quietly = TRUE))
# install.packages("BiocManager")
#BiocManager::install("edgeR")
#Load the edgeR library
library("edgeR")
#Set index range for selected genotype
start=18
end=24
outputName=paste(start,end,"exactTest.csv",sep="_")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,start:end]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Write test results to csv file
write.table(resultsTbl, file=outputName, sep=",", row.names=TRUE)
#!/usr/bin/env Rscript
#Usage: Rscript exactTest_edgeR.r countsFile.csv startColumn endColumn
#Usage Ex: Rscript exactTest_edgeR.r daphnia_genesCounted.csv 1 6
#R script to perform statistical analysis of gene count tables using edgeR exact test
#Install edgeR, this should only need to be done once
#if (!requireNamespace("BiocManager", quietly = TRUE))
# install.packages("BiocManager")
#BiocManager::install("edgeR")
#Load the edgeR library
library("edgeR")
#Set index range for selected genotype
start=19
end=24
outputName=paste(start,end,"exactTest.csv",sep="_")
#Import gene count data
countsTable <- read.csv(file="/home/mae/Documents/RNASeq_Workshop_ND/daphniaRawCounts_onlyEntrez_noDups.csv", row.names="gene")[ ,start:end]
#Add grouping factor
group <- factor(c(rep("ctrl",3),rep("treat",3)))
#Create DGE list object
list <- DGEList(counts=countsTable,group=group)
#There is no purpose in analysing genes that are not expressed in either
# experimental condition, so genes are first filtered on expression levels
keep <- filterByExpr(list)
list <- list[keep, , keep.lib.sizes=FALSE]
#Calculate normalized factors
list <- calcNormFactors(list)
#Produce a matrix of pseudo-counts
#Estimate common dispersion and tagwise dispersions
list <- estimateDisp(list)
#Perform an exact test for treat vs ctrl
tested <- exactTest(list, pair=c("ctrl", "treat"))
#Create results table of DE genes
resultsTbl <- topTags(tested, n=nrow(tested$table))$table
#Write test results to csv file
write.table(resultsTbl, file=outputName, sep=",", row.names=TRUE)