-
Notifications
You must be signed in to change notification settings - Fork 0
/
data_download.nf
executable file
·163 lines (99 loc) · 3.44 KB
/
data_download.nf
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
// General command to download any files and save to folder is
// wget "url-link-to-file" -O outputdir/file.extension // here -O is capital O
// Data
/*
==============================================
Reference Download
url = "https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz"
only Mitochondiral region genome
https://hgdownload.soe.ucsc.edu/goldenPath/hg38/chromosomes/chrM.fa.gz
==============================================
*/
params.genomedir = "$projectDir/genome"
process REFDOWNLOAD{
publishDir params.genomedir, mode:'copy'
output:
path ("*")
script:
"""
mkdir genome
wget "https://hgdownload.soe.ucsc.edu/goldenPath/hg38/chromosomes/chrM.fa.gz" -O genome.fa.gz
"""
}
/*
==============================================
Known variant sites Data Download
urls :
wget https://storage.googleapis.com/genomics-public-data/resources/broad/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf
wget https://storage.googleapis.com/genomics-public-data/resources/broad/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx
==============================================
*/
params.knowndir = "$projectDir/known"
process KNOWNDOWNLOAD{
publishDir params.knowndir, mode:'copy'
output:
path ("*")
script:
"""
mkdir known
wget "https://storage.googleapis.com/genomics-public-data/resources/broad/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf" -O known_dbsnp138.vcf
wget "https://storage.googleapis.com/genomics-public-data/resources/broad/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx" -O known_dbsnp138.vcf.idx
"""
}
/*
==============================================
FASTQ Data Download
FASTQ Data Download
Tumor -Normal data :
urls:
https://zenodo.org/record/2582555/files/SLGFSK-N_231335_r1_chr5_12_17.fastq.gz
https://zenodo.org/record/2582555/files/SLGFSK-N_231335_r2_chr5_12_17.fastq.gz
https://zenodo.org/record/2582555/files/SLGFSK-T_231336_r1_chr5_12_17.fastq.gz
https://zenodo.org/record/2582555/files/SLGFSK-T_231336_r2_chr5_12_17.fastq.gz
urls :
https://zenodo.org/record/1251112/files/raw_child-ds-1.fq
https://zenodo.org/record/1251112/files/raw_child-ds-2.fq
https://zenodo.org/record/1251112/files/raw_mother-ds-1.fq
https://zenodo.org/record/1251112/files/raw_mother-ds-2.fq
==============================================
*/
params.data = "$projectDir/data"
process DATADOWNLOAD{
publishDir params.data, mode:'copy'
output:
path ("*")
script:
"""
mkdir data
wget "https://zenodo.org/record/1251112/files/raw_child-ds-1.fq" -O child_1.fq
wget "https://zenodo.org/record/1251112/files/raw_child-ds-2.fq" -O child_2.fq
wget "https://zenodo.org/record/1251112/files/raw_mother-ds-1.fq" -O mother_1.fq
wget "https://zenodo.org/record/1251112/files/raw_mother-ds-2.fq" -O mother_2.fq
"""
}
/*
Adapter sequence download
url:
https://github.com/timflutre/trimmomatic/blob/master/adapters/TruSeq3-PE.fa
*/
params.adapter = "$projectDir/adapter"
process ADAPTERDOWNLOAD {
publishDir params.adapter , mode:'copy'
output:
path ("*")
script:
"""
wget "https://github.com/timflutre/trimmomatic/blob/master/adapters/TruSeq3-PE.fa" -O adapter.fa
"""
}
/*
==============================================
WorkFLow
==============================================
*/
workflow {
REFDOWNLOAD()
KNOWNDOWNLOAD()
DATADOWNLOAD()
ADAPTERDOWNLOAD()
}