forked from sheynkman-lab/Long-Read-Proteogenomics
-
Notifications
You must be signed in to change notification settings - Fork 0
/
isoseq_sqanti.nf
257 lines (202 loc) · 12.7 KB
/
isoseq_sqanti.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
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
#!/usr/bin/env nextflow
/*
* Copyright (c) 2020, Sheynkman Lab and the authors.
*
* This file is part of 'proteogenomics-nf' a pipeline repository to run
* the "long read proteogenomics" pipeline.
*
*
* @authors
* Ben Jordan
* Rachel Miller
* Gloria Sheynkman
* Christina Chatzipantsiou
* Anne Deslattes Mays ([email protected])
*/
def helpMessage() {
log.info logHeader()
log.info """
Usage:
The typical command for running the pipeline is as follows:
Other:
--max_cpus Maximum number of CPUs (int)
--max_memory Maximum memory (memory unit)
--max_time Maximum time (time unit)
See here for more info: https://github.com/sheynkman-lab/Long-Read-Proteogenomics/blob/master/docs/usage.md
""".stripIndent()
}
// Show help message
if (params.help) {
helpMessage()
exit 0
}
log.info "Longread Proteogenomics - N F ~ version 0.1"
log.info "====================================="
// Header log info
log.info "\nPARAMETERS SUMMARY"
log.info "mainScript : ${params.mainScript}"
log.info "config : ${params.config}"
log.info "max_cpus : ${params.max_cpus}"
log.info "outdir : ${params.outdir}"
log.info "name : ${params.name}"
log.info "gencode_gtf : ${params.gencode_gtf}"
log.info "gencode_transcript_fasta : ${params.gencode_transcript_fasta}"
log.info "gencode_translation_fasta : ${params.gencode_translation_fasta}"
log.info "genome_fasta : ${params.genome_fasta}"
log.info "sample_ccs : ${params.sample_ccs}"
log.info "primers_fasta : ${params.primers_fasta}"
log.info ""
if (params.gencode_gtf.endsWith('.gz')){
ch_gencode_gtf = Channel.value(file(params.gencode_gtf))
}
if (!params.gencode_gtf.endsWith('.gz')){
ch_gencode_gtf_uncompressed = Channel.value(file(params.gencode_gtf))
}
if (params.genome_fasta.endsWith('.gz')){
ch_genome_fasta = Channel.value(file(params.genome_fasta))
}
if (!params.genome_fasta.endsWith('.gz')){
ch_genome_fasta_uncompressed = Channel.value(file(params.genome_fasta))
}
if (!params.sample_ccs) exit 1, "Cannot find file for parameter --sample_ccs: ${params.sample_ccs}"
ch_sample_ccs = Channel.value(file(params.sample_ccs))
if (!params.primers_fasta) exit 1, "Cannot find any seq file for parameter --primers_fasta: ${params.primers_fasta}"
ch_primers_fasta = Channel.value(file(params.primers_fasta))
if (params.genome_fasta.endsWith('.gz')) {
process gunzip_gencode_fasta {
tag "decompress gzipped fasta"
cpus 1
input:
file(genome_fasta) from ch_genome_fasta
output:
file("*.{fa,fasta}") into ch_genome_fasta_uncompressed
script:
"""
gunzip -f ${genome_fasta}
"""
}
}
if (params.gencode_gtf.endsWith('.gz')) {
process gunzip_gencode_gtf {
tag "decompress gzipped gtf"
cpus 1
input:
file(gencode_gtf) from ch_gencode_gtf
output:
file("*.gtf") into ch_gencode_gtf_uncompressed
script:
"""
gunzip -f ${gencode_gtf}
"""
}
}
ch_genome_fasta_uncompressed.into{
ch_genome_fasta_isoseq
ch_genome_fasta_sqanti
}
/*--------------------------------------------------
IsoSeq3
---------------------------------------------------*/
process isoseq3 {
tag "${sample_ccs}, ${gencode_fasta}, ${primers_fasta}"
cpus params.max_cpus
publishDir "${params.outdir}/isoseq3/", mode: 'copy'
input:
file(sample_ccs) from ch_sample_ccs
file(genome_fasta) from ch_genome_fasta_isoseq
file(primers_fasta) from ch_primers_fasta
output:
file("${params.name}.collapsed.gff") into ch_isoseq_gtf
file("${params.name}.collapsed.abundance.txt") into ch_fl_count
file("${params.name}.collapsed.fasta")
file("${params.name}.collapsed.report.json")
file("${params.name}.demult.lima.summary")
file("${params.name}.flnc.bam")
file("${params.name}.flnc.bam.pbi")
file("${params.name}.flnc.filter_summary.json")
script:
"""
# ensure that only qv10 reads from ccs are input
bamtools filter -tag 'rq':'>=0.90' -in $sample_ccs -out filtered.$sample_ccs
# create an index for the ccs bam
pbindex filtered.$sample_ccs
# find and remove adapters/barcodes
lima --isoseq --dump-clips --peek-guess -j ${task.cpus} filtered.$sample_ccs $primers_fasta ${params.name}.demult.bam
# filter for non-concatamer, polya containing reads
isoseq3 refine --require-polya ${params.name}.demult.NEB_5p--NEB_3p.bam $primers_fasta ${params.name}.flnc.bam
# clustering of reads, can only make faster by putting more cores on machine (cannot parallelize)
isoseq3 cluster ${params.name}.flnc.bam ${params.name}.clustered.bam --verbose --use-qvs
# align reads to the genome, takes few minutes (40 core machine)
pbmm2 align $genome_fasta ${params.name}.clustered.hq.bam ${params.name}.aligned.bam --preset ISOSEQ --sort -j ${task.cpus} --log-level INFO
# collapse redundant reads
isoseq3 collapse ${params.name}.aligned.bam ${params.name}.collapsed.gff
"""
}
/*--------------------------------------------------
SQANTI3
---------------------------------------------------*/
process sqanti3 {
tag "${fl_count}, ${gencode_gtf}, ${genome_fasta}, ${sample_gtf},"
cpus params.max_cpus
publishDir "${params.outdir}/sqanti3/", mode: 'copy'
input:
file(fl_count) from ch_fl_count
file(gencode_gtf) from ch_gencode_gtf_uncompressed
file(genome_fasta) from ch_genome_fasta_sqanti
file(sample_gtf) from ch_isoseq_gtf
output:
file("${params.name}_classification.txt") into ch_sample_unfiltered_classification
file("${params.name}_corrected.fasta") into ch_sample_unfiltered_fasta
file("${params.name}_corrected.gtf") into ch_sample_unfiltered_gtf
file("${params.name}_junctions.txt")
file("${params.name}_sqanti_report.pdf")
file("${params.name}.params.txt")
script:
"""
sqanti3_qc.py \
$sample_gtf \
$gencode_gtf \
$genome_fasta \
--skipORF \
-o ${params.name} \
--fl_count $fl_count \
--gtf
"""
}
def logHeader() {
// Log colors ANSI codes
c_black = params.monochrome_logs ? '' : "\033[0;30m";
c_blue = params.monochrome_logs ? '' : "\033[0;34m";
c_cyan = params.monochrome_logs ? '' : "\033[0;36m";
c_dim = params.monochrome_logs ? '' : "\033[2m";
c_green = params.monochrome_logs ? '' : "\033[0;32m";
c_purple = params.monochrome_logs ? '' : "\033[0;35m";
c_reset = params.monochrome_logs ? '' : "\033[0m";
c_white = params.monochrome_logs ? '' : "\033[0;37m";
c_yellow = params.monochrome_logs ? '' : "\033[0;33m";
return """ -${c_dim}--------------------------------------------------${c_reset}-
${c_cyan} sheynkman-lab/Long-Read-Proteogenomics v${workflow.manifest.version}${c_reset}
${c_cyan}███████╗██╗ ██╗███████╗██╗ ██╗███╗ ██╗██╗ ██╗███╗ ███╗ █████╗ ███╗ ██╗ ██╗ █████╗ ██████╗ ${c_reset}
${c_cyan}██╔════╝██║ ██║██╔════╝╚██╗ ██╔╝████╗ ██║██║ ██╔╝████╗ ████║██╔══██╗████╗ ██║ ██║ ██╔══██╗██╔══██╗ ${c_reset}
${c_cyan}███████╗███████║█████╗ ╚████╔╝ ██╔██╗ ██║█████╔╝ ██╔████╔██║███████║██╔██╗ ██║█████╗██║ ███████║██████╔╝ ${c_reset}
${c_cyan}╚════██║██╔══██║██╔══╝ ╚██╔╝ ██║╚██╗██║██╔═██╗ ██║╚██╔╝██║██╔══██║██║╚██╗██║╚════╝██║ ██╔══██║██╔══██╗ ${c_reset}
${c_cyan}███████║██║ ██║███████╗ ██║ ██║ ╚████║██║ ██╗██║ ╚═╝ ██║██║ ██║██║ ╚████║ ███████╗██║ ██║██████╔╝ ${c_reset}
${c_cyan}╚══════╝╚═╝ ╚═╝╚══════╝ ╚═╝ ╚═╝ ╚═══╝╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚══════╝╚═╝ ╚═╝╚═════╝ ${c_reset}
${c_cyan} ${c_reset}
${c_cyan}██╗ ██████╗ ███╗ ██╗ ██████╗ ██████╗ ███████╗ █████╗ ██████╗ ${c_reset}
${c_cyan}██║ ██╔═══██╗████╗ ██║██╔════╝ ██╔══██╗██╔════╝██╔══██╗██╔══██╗ ${c_reset}
${c_cyan}██║ ██║ ██║██╔██╗ ██║██║ ███╗ ██████╔╝█████╗ ███████║██║ ██║ ${c_reset}
${c_cyan}██║ ██║ ██║██║╚██╗██║██║ ██║ ██╔══██╗██╔══╝ ██╔══██║██║ ██║ ${c_reset}
${c_cyan}███████╗╚██████╔╝██║ ╚████║╚██████╔╝ ██║ ██║███████╗██║ ██║██████╔╝ ${c_reset}
${c_cyan}╚══════╝ ╚═════╝ ╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝╚═════╝ ${c_reset}
${c_cyan} ${c_reset}
${c_cyan}██████╗ ██████╗ ██████╗ ████████╗███████╗ ██████╗ ██████╗ ███████╗███╗ ██╗ ██████╗ ███╗ ███╗██╗ ██████╗███████╗ ${c_reset}
${c_cyan}██╔══██╗██╔══██╗██╔═══██╗╚══██╔══╝██╔════╝██╔═══██╗██╔════╝ ██╔════╝████╗ ██║██╔═══██╗████╗ ████║██║██╔════╝██╔════╝ ${c_reset}
${c_cyan}██████╔╝██████╔╝██║ ██║ ██║ █████╗ ██║ ██║██║ ███╗█████╗ ██╔██╗ ██║██║ ██║██╔████╔██║██║██║ ███████╗ ${c_reset}
${c_cyan}██╔═══╝ ██╔══██╗██║ ██║ ██║ ██╔══╝ ██║ ██║██║ ██║██╔══╝ ██║╚██╗██║██║ ██║██║╚██╔╝██║██║██║ ╚════██║ ${c_reset}
${c_cyan}██║ ██║ ██║╚██████╔╝ ██║ ███████╗╚██████╔╝╚██████╔╝███████╗██║ ╚████║╚██████╔╝██║ ╚═╝ ██║██║╚██████╗███████║ ${c_reset}
${c_cyan}╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚══════╝ ╚═════╝ ╚═════╝ ╚══════╝╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═════╝╚══════╝ ${c_reset}
${c_cyan}
-${c_dim}--------------------------------------------------${c_reset}-
""".stripIndent()
}