forked from h3abionet/h3arefgraph
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmain.nf
450 lines (382 loc) · 16.8 KB
/
main.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
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
#!/usr/bin/env nextflow
/*
========================================================================================
h3abionet/h3arefgraph
========================================================================================
h3abionet/h3arefgraph Analysis Pipeline.
#### Homepage / Documentation
https://github.com/h3abionet/h3arefgraph
----------------------------------------------------------------------------------------
*/
/*
----------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------
Pipeline overview:
- 1: FastQC on raw sequence reads (fastq)
- 2: Adapter and read trimming with Trim_Galore!
- 3: FastQC on trimmed reads (Part of Trim_Galore output)
- ?: Overview of QC with MultiQC
----------------------------------------------------------------------------------------
*/
def helpMessage() {
// TODO nf-core: Add to this help message with new command line parameters
log.info"""
=======================================================
,--./,-.
___ __ __ __ ___ /,-._.--~\'
|\\ | |__ __ / ` / \\ |__) |__ } {
| \\| | \\__, \\__/ | \\ |___ \\`-._,-`-,
`._,._,\'
h3abionet/h3arefgraph v${workflow.manifest.version}
=======================================================
Usage:
The typical command for running the pipeline is as follows:
nextflow run h3abionet/h3arefgraph --reads '*_R{1,2}.fastq.gz' -profile docker
Mandatory arguments:
--reads Path to input data (must be surrounded with quotes)
--genome Name of iGenomes reference
-profile Configuration profile to use. Can use multiple (comma separated)
Available: conda, docker, singularity, awsbatch, test and more.
Options:
--singleEnd Specifies that the input is single end reads
References If not specified in the configuration file or you wish to overwrite any of the references.
--fasta Path to Fasta reference
Trimming options
--length [int] Discard reads that became shorter than length [int] because of either quality or adapter trimming. Default: 18
--clip_R1 [int] Instructs Trim Galore to remove [int] bp from the 5' end of read 1 (or single-end reads)
--clip_R2 [int] Instructs Trim Galore to remove [int] bp from the 5' end of read 2 (paired-end reads only)
--three_prime_clip_R1 [int] Instructs Trim Galore to remove [int] bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed
--three_prime_clip_R2 [int] Instructs Trim Galore to remove [int] bp from the 3' end of read 2 AFTER adapter/quality trimming has been performed
--quality_trim [int] Instructs Trim Galore to trim bases lower than [int]
Other options:
--outdir The output directory where the results will be saved
--email Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits
-name Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic.
AWSBatch options:
--awsqueue The AWSBatch JobQueue that needs to be set when running on AWSBatch
--awsregion The AWS Region for your AWS Batch job to run on
"""
.stripIndent()
}
/*
* SET UP CONFIGURATION VARIABLES
*/
// Show help emssage
if (params.help){
helpMessage()
exit 0
}
// Configuration variables
params.name = "microrefgraph"
// Custom trimming options
params.clip_R1 = 0
params.clip_R2 = 0
params.three_prime_clip_R1 = 0
params.three_prime_clip_R2 = 0
params.qtrim = 20
params.length = 18
// TODO nf-core: Add any reference files that are needed
// Configurable reference genomes
fasta = params.genome ? params.genomes[ params.genome ].fasta ?: false : false
if ( params.fasta ){
fasta = file(params.fasta)
if( !fasta.exists() ) exit 1, "Fasta file not found: ${params.fasta}"
}
//
// NOTE - THIS IS NOT USED IN THIS PIPELINE, EXAMPLE ONLY
// If you want to use the above in a process, define the following:
// input:
// file fasta from fasta
//
// Has the run name been specified by the user?
// this has the bonus effect of catching both -name and --name
custom_runName = params.name
if( !(workflow.runName ==~ /[a-z]+_[a-z]+/) ){
custom_runName = workflow.runName
}
if( workflow.profile == 'awsbatch') {
// AWSBatch sanity checking
if (!params.awsqueue || !params.awsregion) exit 1, "Specify correct --awsqueue and --awsregion parameters on AWSBatch!"
if (!workflow.workDir.startsWith('s3') || !params.outdir.startsWith('s3')) exit 1, "Specify S3 URLs for workDir and outdir parameters on AWSBatch!"
// Check workDir/outdir paths to be S3 buckets if running on AWSBatch
// related: https://github.com/nextflow-io/nextflow/issues/813
if (!workflow.workDir.startsWith('s3:') || !params.outdir.startsWith('s3:')) exit 1, "Workdir or Outdir not on S3 - specify S3 Buckets for each to run on AWSBatch!"
}
// Stage config files
ch_multiqc_config = Channel.fromPath(params.multiqc_config)
ch_output_docs = Channel.fromPath("$baseDir/docs/output.md")
/*
* Create a channel for input read files
*/
if(params.readPaths){
if(params.singleEnd){
Channel
.from(params.readPaths)
.map { row -> [ row[0], [file(row[1][0])]] }
.ifEmpty { exit 1, "params.readPaths was empty - no input files supplied" }
.into { read_files_fastqc; read_files_trimming }
} else {
Channel
.from(params.readPaths)
.map { row -> [ row[0], [file(row[1][0]), file(row[1][1])]] }
.ifEmpty { exit 1, "params.readPaths was empty - no input files supplied" }
.into { read_files_fastqc; read_files_trimming }
}
} else {
Channel
.fromFilePairs( params.reads, size: params.singleEnd ? 1 : 2 )
.ifEmpty { exit 1, "Cannot find any reads matching: ${params.reads}\nNB: Path needs to be enclosed in quotes!\nIf this is single-end data, please specify --singleEnd on the command line." }
.into { read_files_fastqc; read_files_trimming }
}
// Header log info
log.info """=======================================================
,--./,-.
___ __ __ __ ___ /,-._.--~\'
|\\ | |__ __ / ` / \\ |__) |__ } {
| \\| | \\__, \\__/ | \\ |___ \\`-._,-`-,
`._,._,\'
h3abionet/h3arefgraph v${workflow.manifest.version}"
======================================================="""
def summary = [:]
summary['Pipeline Name'] = 'h3abionet/h3arefgraph'
summary['Pipeline Version'] = workflow.manifest.version
summary['Run Name'] = custom_runName ?: workflow.runName
// TODO nf-core: Report custom parameters here
summary['Reads'] = params.reads
summary['Fasta Ref'] = params.fasta
summary['Data Type'] = params.singleEnd ? 'Single-End' : 'Paired-End'
summary['Max Memory'] = params.max_memory
summary['Max CPUs'] = params.max_cpus
summary['Max Time'] = params.max_time
summary['Output dir'] = params.outdir
summary['Working dir'] = workflow.workDir
//trimming
summary['Trim R1'] = params.clip_R1
summary['Trim R2'] = params.clip_R2
summary["Trim 3' R1"] = params.three_prime_clip_R1
summary["Trim 3' R2"] = params.three_prime_clip_R2
summary["Quality Trim"] = params.qtrim
summary["Trim Length"] = params.length
summary['Container Engine'] = workflow.containerEngine
if(workflow.containerEngine) summary['Container'] = workflow.container
summary['Current home'] = "$HOME"
summary['Current user'] = "$USER"
summary['Current path'] = "$PWD"
summary['Working dir'] = workflow.workDir
summary['Output dir'] = params.outdir
summary['Script dir'] = workflow.projectDir
summary['Config Profile'] = workflow.profile
if(workflow.profile == 'awsbatch'){
summary['AWS Region'] = params.awsregion
summary['AWS Queue'] = params.awsqueue
}
if(params.email) summary['E-mail Address'] = params.email
log.info summary.collect { k,v -> "${k.padRight(15)}: $v" }.join("\n")
log.info "========================================="
def create_workflow_summary(summary) {
def yaml_file = workDir.resolve('workflow_summary_mqc.yaml')
yaml_file.text = """
id: 'nf-core-h3arefgraph-summary'
description: " - this information is collected when the pipeline is started."
section_name: 'h3abionet/h3arefgraph Workflow Summary'
section_href: 'https://github.com/h3abionet/h3arefgraph'
plot_type: 'html'
data: |
<dl class=\"dl-horizontal\">
${summary.collect { k,v -> " <dt>$k</dt><dd><samp>${v ?: '<span style=\"color:#999999;\">N/A</a>'}</samp></dd>" }.join("\n")}
</dl>
""".stripIndent()
return yaml_file
}
/*
* Parse software version numbers
*/
process get_software_versions {
output:
file 'software_versions_mqc.yaml' into software_versions_yaml
script:
// TODO nf-core: Get all tools to print their version number here
"""
echo $workflow.manifest.version > v_pipeline.txt
echo $workflow.nextflow.version > v_nextflow.txt
fastqc --version > v_fastqc.txt
multiqc --version > v_multiqc.txt
trim_galore --version | grep "version" | tr -d '[:space:]' > v_trimgalore.txt
cutadapt --version > v_cutadapt.txt
scrape_software_versions.py > software_versions_mqc.yaml
"""
}
/*
* STEP 1 - FastQC
*/
process fastqc {
tag "$name"
publishDir "${params.outdir}/fastqc", mode: 'copy',
saveAs: {filename -> filename.indexOf(".zip") > 0 ? "zips/$filename" : "$filename"}
input:
set val(name), file(reads) from read_files_fastqc
output:
file "*_fastqc.{zip,html}" into fastqc_results
script:
"""
fastqc -q $reads
"""
}
// TODO nf-core: Expose trim_galore vars, split for single/paired
/*
* STEP 2 - Trim_Galore
*/
process trimGalore {
tag "$name"
publishDir "${params.outdir}/trim_galore", mode: 'copy',
saveAs: {filename ->
if (filename.endsWith(".html")) "fastqc/$filename"
else if (filename.endsWith(".zip")) "fastqc/zip/$filename"
else if (filename.endsWith("trimming_report.txt")) "logs/$filename"
else if (filename.endsWith(".fq.gz")) "trimmed_reads/$filename"
else filename : null
}
input:
set val(name), file(reads) from read_files_trimming
output:
set val(name), file("*.fq.gz") into read_files_trimmed_reads
file "*.txt" into trimgalore_results_mqc
file "*.{zip,html}" into trimgalore_fastqc_reports_mqc
script:
c_R1 = params.clip_R1 > 0 ? "--clip_R1 $params.clip_R1" : ''
c_R2 = params.clip_R2 > 0 ? "--clip_R2 $params.clip_R2" : ''
tpc_R1 = params.three_prime_clip_R1 > 0 ? "--three_prime_clip_R1 $params.three_prime_clip_R1" : ''
tpc_R2 = params.three_prime_clip_R2 > 0 ? "--three_prime_clip_R2 $params.three_prime_clip_R2" : ''
qt = params.qtrim > 0 ? "-q $params.qtrim" : ''
if (params.singleEnd) {
"""
trim_galore \
--fastqc --gzip \
$c_R1 \
$c_R2 \
$tpc_R1 \
$tpc_R2 \
$qt \
--length $params.length \
$reads
"""
} else {
"""
trim_galore \
--paired --fastqc --gzip \
$c_R1 \
$c_R2 \
$tpc_R1 \
$tpc_R2 \
$qt \
--length $params.length \
${name}_R1.fastq.gz ${name}_R2.fastq.gz
"""
}
}
/*
* STEP 3 - MultiQC
*/
process multiqc {
publishDir "${params.outdir}/MultiQC", mode: 'copy'
input:
file multiqc_config from ch_multiqc_config
// TODO nf-core: Add in log files from your new processes for MultiQC to find!
file ('trim_galore/fastqc/*') from trimgalore_fastqc_reports_mqc.collect().ifEmpty([])
file ('fastqc/*') from fastqc_results.collect().ifEmpty([])
file ('software_versions/*') from software_versions_yaml
file workflow_summary from create_workflow_summary(summary)
output:
file "*multiqc_report.html" into multiqc_report
file "*_data"
script:
rtitle = custom_runName ? "--title \"$custom_runName\"" : ''
rfilename = custom_runName ? "--filename " + custom_runName.replaceAll('\\W','_').replaceAll('_+','_') + "_multiqc_report" : ''
// TODO nf-core: Specify which MultiQC modules to use with -m for a faster run time
"""
multiqc -f $rtitle $rfilename --config $multiqc_config .
"""
}
/*
* STEP 3 - Output Description HTML
*/
process output_documentation {
publishDir "${params.outdir}/Documentation", mode: 'copy'
input:
file output_docs from ch_output_docs
output:
file "results_description.html"
script:
"""
markdown_to_html.r $output_docs results_description.html
"""
}
/*
* Completion e-mail notification
*/
workflow.onComplete {
// Set up the e-mail variables
def subject = "[h3abionet/h3arefgraph] Successful: $workflow.runName"
if(!workflow.success){
subject = "[h3abionet/h3arefgraph] FAILED: $workflow.runName"
}
def email_fields = [:]
email_fields['version'] = workflow.manifest.version
email_fields['runName'] = custom_runName ?: workflow.runName
email_fields['success'] = workflow.success
email_fields['dateComplete'] = workflow.complete
email_fields['duration'] = workflow.duration
email_fields['exitStatus'] = workflow.exitStatus
email_fields['errorMessage'] = (workflow.errorMessage ?: 'None')
email_fields['errorReport'] = (workflow.errorReport ?: 'None')
email_fields['commandLine'] = workflow.commandLine
email_fields['projectDir'] = workflow.projectDir
email_fields['summary'] = summary
email_fields['summary']['Date Started'] = workflow.start
email_fields['summary']['Date Completed'] = workflow.complete
email_fields['summary']['Pipeline script file path'] = workflow.scriptFile
email_fields['summary']['Pipeline script hash ID'] = workflow.scriptId
if(workflow.repository) email_fields['summary']['Pipeline repository Git URL'] = workflow.repository
if(workflow.commitId) email_fields['summary']['Pipeline repository Git Commit'] = workflow.commitId
if(workflow.revision) email_fields['summary']['Pipeline Git branch/tag'] = workflow.revision
email_fields['summary']['Nextflow Version'] = workflow.nextflow.version
email_fields['summary']['Nextflow Build'] = workflow.nextflow.build
email_fields['summary']['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp
// Render the TXT template
def engine = new groovy.text.GStringTemplateEngine()
def tf = new File("$baseDir/assets/email_template.txt")
def txt_template = engine.createTemplate(tf).make(email_fields)
def email_txt = txt_template.toString()
// Render the HTML template
def hf = new File("$baseDir/assets/email_template.html")
def html_template = engine.createTemplate(hf).make(email_fields)
def email_html = html_template.toString()
// Render the sendmail template
def smail_fields = [ email: params.email, subject: subject, email_txt: email_txt, email_html: email_html, baseDir: "$baseDir" ]
def sf = new File("$baseDir/assets/sendmail_template.txt")
def sendmail_template = engine.createTemplate(sf).make(smail_fields)
def sendmail_html = sendmail_template.toString()
// Send the HTML e-mail
if (params.email) {
try {
if( params.plaintext_email ){ throw GroovyException('Send plaintext e-mail, not HTML') }
// Try to send HTML e-mail using sendmail
[ 'sendmail', '-t' ].execute() << sendmail_html
log.info "[h3abionet/h3arefgraph] Sent summary e-mail to $params.email (sendmail)"
} catch (all) {
// Catch failures and try with plaintext
[ 'mail', '-s', subject, params.email ].execute() << email_txt
log.info "[h3abionet/h3arefgraph] Sent summary e-mail to $params.email (mail)"
}
}
// Write summary e-mail HTML to a file
def output_d = new File( "${params.outdir}/Documentation/" )
if( !output_d.exists() ) {
output_d.mkdirs()
}
def output_hf = new File( output_d, "pipeline_report.html" )
output_hf.withWriter { w -> w << email_html }
def output_tf = new File( output_d, "pipeline_report.txt" )
output_tf.withWriter { w -> w << email_txt }
log.info "[h3abionet/h3arefgraph] Pipeline Complete"
}