-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathSnakefile
175 lines (150 loc) · 6.55 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
configfile: "refs/config.json"
# CONFIG VARIABLES
#--------------------------------------------------------------------------------
trimmedReadsDir = config["DIRECTORIES"]["trimmedReads"]
rawQCDir = config["DIRECTORIES"]["rawQC"]
trimmedQCDir = config["DIRECTORIES"]["trimmedQC"]
starDir = config["DIRECTORIES"]["starAligned"]
countsDir = config["DIRECTORIES"]["featureCounts"]
# ENVIRONMENT VARIABLES
#-------------------------------------------------------------------------------
import os
from dotenv import load_dotenv
# Load the .env file
load_dotenv("refs/.env")
# Get paths from environment variables
rawReadsDir = os.getenv("RAW_READS_DIR") + "/"
gtf_file = os.getenv("MMUSCULUS_GTF")
fa_file = os.getenv("MMUSCULUS_FA")
# RULE ALL
#-------------------------------------------------------------------------------
rule all:
input:
config["DIRECTORIES"]["genomeDir"] + "SA",
expand(trimmedReadsDir + "{sample}_trim_R1.fastq.gz", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
expand(trimmedReadsDir + "{sample}_trim_R2.fastq.gz", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
expand(rawQCDir + "{sample}_R1_fastqc.zip", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
expand(trimmedQCDir + "{sample}_trim_R1_fastqc.zip", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
rawQCDir + "multiqc_report.html",
trimmedQCDir + "multiqc_report.html",
expand(starDir + "{sample}.Aligned.sortedByCoord.out.bam", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
expand(countsDir + "{sample}_{feature_type}.counts", sample=config["SAMPLE_INFORMATION"]["allSamples"], feature_type=["gene", "exon"])
# INDEX GENOME
#-------------------------------------------------------------------------------
rule index_genome:
input:
fa = fa_file,
gtf = gtf_file
output:
starIndex = config["DIRECTORIES"]["genomeDir"] + "SA",
params:
genomeDir = config["DIRECTORIES"]["genomeDir"],
threads = config["CLUSTER_INFORMATION"]["threads"]
shell:
"""
STAR --runMode genomeGenerate --runThreadN {params.threads} --genomeFastaFiles {input.fa} --sjdbGTFfile {input.gtf} --genomeDir {params.genomeDir}
"""
# RAW FASTQC
#-------------------------------------------------------------------------------
rule raw_fastqc:
input:
R1 = lambda wildcards: rawReadsDir + config["SAMPLES"][wildcards.sample]["read1"] + ".fastq.gz",
R2 = lambda wildcards: rawReadsDir + config["SAMPLES"][wildcards.sample]["read2"] + ".fastq.gz"
output:
qc1 = rawQCDir + "{sample}_R1_fastqc.zip",
qc2 = rawQCDir + "{sample}_R2_fastqc.zip"
params:
threads = config["CLUSTER_INFORMATION"]["threads"]
shell:
"""
fastqc {input.R1} {input.R2} -o {rawQCDir} --threads {params.threads}
"""
# TRIM BBDUK
#-------------------------------------------------------------------------------
rule trim_bbduk:
input:
R1 = lambda wildcards: rawReadsDir + config["SAMPLES"][wildcards.sample]["read1"] + ".fastq.gz",
R2 = lambda wildcards: rawReadsDir + config["SAMPLES"][wildcards.sample]["read2"] + ".fastq.gz"
output:
trimR1 = trimmedReadsDir + "{sample}_trim_R1.fastq.gz",
trimR2 = trimmedReadsDir + "{sample}_trim_R2.fastq.gz"
params:
threads = config["CLUSTER_INFORMATION"]["threads"]
shell:
"""
bbduk.sh -Xmx3g in1={input.R1} in2={input.R2} out1={output.trimR1} out2={output.trimR2} ref=refs/adapters.fa ktrim=r k=23 mink=11 hdist=1 tpe tbo threads={params.threads} trimpolyg=1 trimpolya=1
"""
# TRIMMED FASTQC
#-------------------------------------------------------------------------------
rule trimmed_fastqc:
input:
R1 = trimmedReadsDir + "{sample}_trim_R1.fastq.gz",
R2 = trimmedReadsDir + "{sample}_trim_R2.fastq.gz"
output:
qc1 = trimmedQCDir + "{sample}_trim_R1_fastqc.zip",
qc2 = trimmedQCDir + "{sample}_trim_R2_fastqc.zip"
params:
threads = config["CLUSTER_INFORMATION"]["threads"]
shell:
"""
fastqc {input.R1} {input.R2} -o {trimmedQCDir} --threads {params.threads}
"""
# ALIGN READS
#-------------------------------------------------------------------------------
rule align_reads:
input:
trimR1 = trimmedReadsDir + "{sample}_trim_R1.fastq.gz",
trimR2 = trimmedReadsDir + "{sample}_trim_R2.fastq.gz",
genomeDir = config["DIRECTORIES"]["genomeDir"]
output:
aligned = starDir + "{sample}.Aligned.sortedByCoord.out.bam"
params:
prefix = starDir + "{sample}.",
threads = config["CLUSTER_INFORMATION"]["threads"]
shell:
"""
STAR --genomeDir {input.genomeDir} --runThreadN {params.threads} --readFilesCommand zcat --limitBAMsortRAM 31000000000 --readFilesIn {input.trimR1} {input.trimR2} --outFileNamePrefix {params.prefix} --outSAMtype BAM SortedByCoordinate
"""
# FEATURE COUNTS
#-------------------------------------------------------------------------------
rule feature_count:
input:
bam = starDir + "{sample}.Aligned.sortedByCoord.out.bam",
gtf = gtf_file
output:
counts = countsDir + "{sample}_{feature_type}.counts"
params:
feature_type = "{feature_type}", # can be 'gene' or 'exon'
threads = config["CLUSTER_INFORMATION"]["threads"]
shell:
"""
featureCounts -p --primary -t {params.feature_type} -T {params.threads} -s 2 -a {input.gtf} -o {output.counts} {input.bam}
"""
# MULTIQC FOR RAW FASTQC
#-------------------------------------------------------------------------------
rule multiqc_raw:
input:
expand(rawQCDir + "{sample}_R1_fastqc.zip", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
expand(rawQCDir + "{sample}_R2_fastqc.zip", sample=config["SAMPLE_INFORMATION"]["allSamples"])
output:
html = rawQCDir + "multiqc_report.html"
params:
outdir = rawQCDir
shell:
"""
multiqc {rawQCDir} -o {params.outdir}
"""
# MULTIQC FOR TRIMMED FASTQC
#-------------------------------------------------------------------------------
rule multiqc_trimmed:
input:
expand(trimmedQCDir + "{sample}_trim_R1_fastqc.zip", sample=config["SAMPLE_INFORMATION"]["allSamples"]),
expand(trimmedQCDir + "{sample}_trim_R2_fastqc.zip", sample=config["SAMPLE_INFORMATION"]["allSamples"])
output:
html = trimmedQCDir + "multiqc_report.html"
params:
outdir = trimmedQCDir
shell:
"""
multiqc {trimmedQCDir} -o {params.outdir}
"""