-
Notifications
You must be signed in to change notification settings - Fork 0
/
Snakefile
209 lines (189 loc) · 6.68 KB
/
Snakefile
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
# Bulk RNASeq
# author yhao at cshl dot edu
import pandas as pd
import os
import glob
import numpy as np
from itertools import combinations
from snakemake.utils import validate, min_version
from snakemake.shell import shell
min_version("5.1.2")
configfile: "config.yaml"
#validate(config, schema="config.schema.yaml")
threads_max = config["params"]["threads"]
def get_fq(wildcards):
reads=SAMPLES.loc[wildcards.id, ["R1","R2"]].dropna(how="all")
in_dir=config['fastqc']['fastq_dir']
if(not in_dir or in_dir == './' ):
return reads
else:
return [in_dir+r for r in reads]
def get_CONTRAST(conditions):
cond=np.unique(conditions)
#cond.sort()
cond=sorted(cond, key=str.casefold)
b = list()
for i in combinations(cond,2):
b.append(i[0]+"_vs_"+i[1])
return b
onsuccess:
print("Workflow finished, no error")
onerror:
print("An error occurred")
try:
SAMPLES = pd.read_table(config["samples"]).set_index("sample", drop=False)
except:
SAMPLES = pd.read_csv(config["samples"]).set_index("sample", drop=False)
else:
print("There is an error with sample file.")
IDS = SAMPLES['sample']
READS = [os.path.basename(x).split(".")[0] for x in SAMPLES['R1'].dropna().tolist() + SAMPLES['R2'].dropna().tolist()]
#CONTRASTS=get_CONTRAST(SAMPLES['condition'])
CONTRASTS = ["A_vs_Control","B_vs_Control"]
rule all:
input:
#expand("fastqc/{id}.html", id=IDS)
#"genome/genomeLog.out"
#expand("mapping/{id}.STAR.genome.bam", id=IDS)
#expand("expression/{type}.txt", type=["expected_count","TPM","FPKM"])
expand("diffexp/gsea_{contrast}.rnk", contrast=CONTRASTS)
#expand("gsea/gsea_{contrast}.log", contrast=CONTRASTS)
rule fastqc:
input:
get_fq
threads: threads_max
output:
html="fastqc/{id}.html",
zip=temp("fastqc/{id}.zip")
params:
prefix=config['fastqc']['out_dir']
run:
if not os.path.exists("fastqc"):
os.makedirs("fastqc")
shell("fastqc -t 4 --outdir {params.prefix} {input}")
shell("touch {output}")
rule index_genome:
input:
fa=config['align']['genome_fasta'],
gtf=config['align']['gtf']
output:
"genome/genomeLog.out"
threads: threads_max
params:
ref=config['align']['reference'],
starpath=config['align']['star_path'],
fout="genome/genome",
overhang=config['align']['star_sjdboverhang']
run:
if {params.ref}.pop() is None or not list({params.ref})[0].strip():
if {input.fa}.pop() is None or not list({input.fa})[0].strip() or {input.gtf}.pop() is None or not list({input.gtf})[0].strip() or {params.overhang}.pop() is None or not str(list({params.overhang})[0]).strip():
sys.exit('error: missing genome index!')
else:
# do genome indexing
shell("echo \"Indexing genome ... \"")
shell("rsem-prepare-reference --star "
"--star-path {params.starpath} "
"-p {threads} "
"--gtf {input.gtf} "
"--star-sjdboverhang {params.overhang} "
"{input.fa} {params.fout}")
else:
shell("touch genome/genomeLog.out")
rule align:
input:
sp=get_fq,
gn="genome/genomeLog.out"
threads: threads_max
output:
result="mapping/{id}.genes.results",
bam="mapping/{id}.STAR.genome.bam"
params:
fraglensd=config['align']['fragment_len_sd'],
fraglenmean=config['align']['fragment_len_mean'],
ref=config['align']['reference'],
gtf=config['align']['gtf'],
starpath=config['align']['star_path'],
prefix="mapping/{id}"
log:
"mapping/{id}.align.log"
run:
if {params.ref}.pop() is None or not list({params.ref})[0].strip():
this_ref="genome/genome"
else:
this_ref={params.ref}
fc = len(unpack({input.sp})[0])
if fc>1:
#paired end
shell("rsem-calculate-expression --star "
"--star-path {params.starpath} "
"-p {threads} "
"--star-gzipped-read-file "
"--star-output-genome-bam "
"--paired-end "
"{input.sp[0]} {input.sp[1]} "
"{this_ref} {params.prefix}")
elif fc == 1:
#single end
shell("rsem-calculate-expression --star "
"--star-path {params.starpath} "
"-p {threads} "
"--star-gzipped-read-file "
"--star-output-genome-bam "
"--fragment-length-mean {params.fraglenmean} "
"--fragment-length-sd {params.fraglensd} "
"{input.sp[0]} {this_ref} {params.prefix}")
else:
print("Wrong number of input fastq. Exit.");exit(1)
rule get_exp_table:
input:
expand("mapping/{sample}.genes.results",sample=SAMPLES['sample'])
output:
expand("expression/{type}.txt", type=["expected_count","TPM","FPKM"])
params:
tpm="TPM", fpkm="FPKM", cnt="CNT"
run:
if not os.path.exists("expression"):
os.makedirs("expression")
if not os.path.exists("diffexp"):
os.makedirs("diffexp")
sel_cols=["expected_count", "TPM","FPKM"]
all_files=glob.glob("mapping/*.genes.results")
results = [pd.read_table(i).set_index("gene_id")[sel_cols] for i in all_files]
for col in sel_cols:
tab= pd.concat([ df[col] for df in results ],axis=1)
new_cols=[ n.split(".genes.results")[0]+"_"+col for n in all_files]
tab.columns = [n.split("/")[1] for n in new_cols]
tab.to_csv('expression/{}.txt'.format(col), sep='\t', index=True)
rule deseq2:
input:
counts="expression/expected_count.txt"
output:
"diffexp/dds.rds","diffexp/diffexp.pdf",
expand("diffexp/gsea_{contrast}.rnk", contrast=CONTRASTS)
params:
coldata=config['samples'],
adjusted_pvalue=config['diffexp']['adjusted_pvalue'],
rnk=config['diffexp']['rnk'],
gtf=config['align']['gtf'],
contrast=CONTRASTS
log:
"diffexp/diffexp.log"
script:
"script/deseq2.R"
rule gsea:
input:
expand("diffexp/gsea_{contrast}.rnk", contrast=CONTRASTS)
output:
expand("gsea/gsea_{contrast}.log", contrast=CONTRASTS)
params:
jar=config['gsea']['exe_jar'],
gmt=config['gsea']['gmt'],
no_perm=config['gsea']['no_perm'],
no_plot=config['gsea']['no_plot'],
set_max=config['gsea']['set_max'],
set_min=config['gsea']['set_min'],
seed=config['gsea']['seed'],
log:
"gsea/gsea.log"
script:
"script/gsea_preranked.R"