Newer
Older
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
params.fastq = "$baseDir/data/*.fastq"
params.fasta = "$baseDir/data/*.fasta"
log.info "fastq files : ${params.fastq}"
log.info "fasta files : ${params.fasta}"
Channel
.fromPath( params.fasta )
.ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
.map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fasta_file }
Channel
.fromFilePairs( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
.set { fastq_files }
process adaptor_removal {
tag "$pair_id"
publishDir "results/fastq/adaptor_removal/", mode: 'copy'
input:
set pair_id, file(reads) from fastq_files
output:
set pair_id, "*_cut_R{1,2}.fastq.gz" into fastq_files_cut
script:
"""
cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT -A AGATCGGAAGAG -G CTCTTCCGATCT \
-o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \
${reads[0]} ${reads[1]} > ${pair_id}_report.txt
"""
}
process trimming {
tag "${reads}"
cpus 4
publishDir "results/fastq/trimming/", mode: 'copy'
input:
set pair_id, file(reads) from fastq_files_cut
output:
set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
script:
"""
UrQt --t 20 --m ${task.cpus} --gz \
--in ${reads[0]} --inpair ${reads[1]} \
--out ${pair_id}_trim_R1.fastq.gz --outpair ${pair_id}_trim_R2.fastq.gz \
> ${pair_id}_trimming_report.txt
"""
}
process index_fasta {
tag "$fasta_id"
cpus 4
publishDir "results/mapping/index/", mode: 'copy'
input:
set fasta_id, file(fasta) from fasta_file
output:
set fasta_id, "${fasta.baseName}.*" into index_files
file "*_bwa_report.txt" into index_files_report
script:
"""
bwa index -p ${fasta.baseName} ${fasta} \
&> ${fasta.baseName}_bwa_report.txt
"""
}
process mapping_fastq {
tag "$reads"
cpus 4
publishDir "results/mapping/sam/", mode: 'copy'
input:
set pair_id, file(reads) from fastq_files_trim
set index_id, file(index) from index_files.collect()
output:
file "${pair_id}.sam" into sam_files
file "${pair_id}_bwa_report.txt" into mapping_repport_files
script:
"""
bwa mem -t ${task.cpus} \
${index_id} ${reads[0]} ${reads[1]} \
-o ${pair_id}.sam &> ${pair_id}_bwa_report.txt
"""
}