-
Notifications
You must be signed in to change notification settings - Fork 10
/
Copy pathmain.nf
2542 lines (1980 loc) · 54.8 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
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env nextflow
/*
vim: syntax=groovy
-*- mode: groovy;-*-
*/
def helpMessage() {
log.info"""
# PanTE
A pipeline for predicting and masking transposable elements in multiple genomes.
## Examples
Say you have a bunch of genomes in `genomes`, you can predict
ncRNAs and TEs like so:
```bash
nextflow run darcyabjones/pante \
-profile singularity \
-resume \
--genomes "genomes/*.fasta"
```
If you have access to RepBase you can include that:
```
nextflow run darcyabjones/pante -profile singularity -resume \
--genomes "genomes/*.fasta" \
--repbase "downloads/RepBaseRepeatMaskerEdition-20181026.tar.gz" \
--rm_meta "downloads/RepeatMaskerMetaData-20181026.tar.gz" \
--rm_species "fungi"
```
## Parameters
--genomes <glob>
Required
A glob of the fasta genomes to search for genes in.
The basename of the file is used as the genome name.
--outdir <path>
Default: `results`
The directory to store the results in.
--repbase <path>
Optional
The RepBase RepeatMasker edition tarball to use to construct
the repeatmasker database. Download from
https://www.girinst.org/server/RepBase/index.php.
--rm_meta <path>
Optional
The RepeatMasker meta tarball to use to construct the
repeatmasker database. Download from
http://www.repeatmasker.org/libraries/. Make sure the version
matches the version of Repbase if you're using RepBase.
--dfam_hmm <glob>
Optional
Pre downloaded Dfam HMMs to use. Will download latest
if this isn't provided.
--dfam_hmm_url <url>
http://dfam.org/releases/current/families/Dfam.hmm.gz
The url to download the Dfam HMMs from if `--dfam_hmm` isn't provided.
--dfam_embl <path>
Optional
Pre downloaded Dfam consensus sequences to use. Will download
latest if this isn't provided.
--dfam_embl_url <url>
http://dfam.org/releases/current/families/Dfam.embl.gz
The url to download the Dfam consensus sequences from
if `--dfam_embl` isn't provided.
--rm_repeatpeps <path>
Optional
Repeat proteins to use for repeatmasker. By default this
is taken from the RepeatMasker `Library/RepeatPeps.lib`
and assumes that you're using the containers.
--rm_species <str>
Optional
An NCBI taxonomy name to use to predict transposable
elements from RepBase with. Something like `fungi` usually works fine. |
--mitefinder_profiles <path>
Optional
A text file for MiteFinderII containing profiles to search for.
Corresponds to https://github.com/screamer/miteFinder/blob/master/profile/pattern_scoring.txt.
By default will use a file pointed to by the
`MITEFINDER_PROFILE` environment variable, which is
set in the provided containers.
--noinfernal
false
Don't run Infernal `cmscan` against Rfam. This can save some time.
--rfam <path>
Optional
Pre-downloaded Rfam CM models (un-gzipped) to use.
--rfam_url <url>
ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.cm.gz
The url to download Rfam CM models from if `--rfam`
isn't provided. Will not download if `--noinfernal`.
--rfam_clanin
Optional
Pre-downloaded Rfam clan information to use.
--rfam_clanin_url <url>
ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.clanin
The URL to download Rfam clan info from if `--rfam_clanin`
isn't provided.
--rfam_gomapping <path>
Optional
Pre-downloaded Rfam GO term mappings to use.
--rfam_gomapping_url <url>
ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/rfam2go/rfam2go
The URL to download Rfam GO term mappings from if
`--rfam_gomapping` isn't provided.
--rnammer
false
Run RNAmmer analyses on the genomes. Assumes that you
are using the containers with RNAmmer installed or
have otherwise set RNAmmer. Will fail if it isn't installed.
--pfam <glob>
Optional
A glob of Pfam stockholm formatted alignments (not gzipped)
to use to search against the genomes.
--pfam_ids <path>
`data/pfam_ids.txt`
A file containing a list of Pfam accessions to download
and use if `--pfam` isn't provided.
--gypsydb <path>
Optional
A glob of stockholm formatted alignments from
GyDB to search against the genomes.
--gypsydb_url <url>
http://gydb.org/gydbModules/collection/collection/db/GyDB_collection.zip
The URL to download GyDB from if `--gypsydb` is not provided.
--protein_families <path>
`data/proteins/families.stk`
A stockholm formatted file of custom aligned protein families
to search against the genomes.
--infernal_max_evalue <float>
0.00001
The maximum e-value to use to consider `cmscan` matches significant.
--mmseqs_max_evalue
0.001
The maximum e-value to use to consider `mmseqs` profile
matches against the genomes significant.
--min_intra_frequency <int>
4
The minimum number of copies a clustered repeat family
must have within a genome for it to be considered "present".
--min_inter_proportion <float>
0.2
The minimum proportion of genomes that the clustered repeat
family must be present in (after `--min_intra_frequency`)
to be considered a geniune family.
--repeatmodeler_min_len <int>
10000
The minimum scaffold length to allow for predicting repeats in repeatmodeler.
Scaffolds smaller than this will be removed to avoid sampling bias.
--eahelitron_three_prime_fuzzy_level <int>
3
Passed on to the EAHelitron parameter `-r`.
--eahelitron_upstream_length <url>
3000
Passed on to the EAHElitron parameter `-u`.
--eahelitron_downstream_length <int>
50
Passed on to the EAHelitron parameter `d`.
--ltrharvest_similar <int>
85
Passed on to the LTRHarvest parameter `-similar`.
--ltrharvest_vic <int>
10
Passed on to the LTRHarvest parameter `-vic`.
--ltrharvest_seed <int>
20
Passed on to the LTRHarvest parameter `-seed`.
--ltrharvest_minlenltr <int>
100
Passed on to the LTRHarvest parameter `-minlenltr`.
--ltrharvest_maxlenltr <int>
7000
Passed on to the LTRHarvest parameter `-maxlenltr`.
--ltrharvest_mintsd <int>
4
Passed on to the LTRHarvest parameter `-mintsd`.
--ltrharvest_maxtsd <int>
6
Passed on to the LTRHarvest parameter `-maxtsd`.
--mitefinder_threshold <float>
0.5
Passed on to the MiteFinderII parameter `-threshold`.
--trans_table <int>
1
The ncbi translation table number to use for MMSeqs searches.
## Exit codes
- 0: All ok.
- 1: Incomplete parameter inputs.
""".stripIndent()
}
if (params.help) {
helpMessage()
exit 0
}
params.genomes = false
// RepeatMasker config
params.repbase = false
params.rm_meta = false
params.dfam_hmm = false
params.dfam_hmm_url = "http://dfam.org/releases/current/families/Dfam.hmm.gz"
params.dfam_embl = false
params.dfam_embl_url = "http://dfam.org/releases/current/families/Dfam.embl.gz"
params.rm_repeatpeps = false
params.rm_species = false
// Mitefinder comes with a set of profiles to use for searching.
// We can fetch this from the installation directory in the containers.
// But if you aren't using the containers or want to use a different
// set of profiles use this.
params.mitefinder_profiles = false
// Infernal takes quite a long time to run and tRNAscan and RNAmmer cover
// a lot of what we want it for. So option is offered to disable it.
params.noinfernal = false
params.rfam = false
params.rfam_url = "ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.cm.gz"
params.rfam_clanin = false
params.rfam_clanin_url = "ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.clanin"
params.rfam_gomapping = false
params.rfam_gomapping_url = "ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/rfam2go/rfam2go"
params.rnammer = false
params.pfam = false
params.gypsydb = false
params.gypsydb_url = "http://gydb.org/gydbModules/collection/collection/db/GyDB_collection.zip"
params.pfam_ids = "$baseDir/data/pfam_ids.txt"
params.protein_families = "$baseDir/data/proteins/families.stk"
params.repeatmodeler_min_len = 1000
params.infernal_max_evalue = 0.00001
params.mmseqs_max_evalue = 0.001
params.min_intra_frequency = 4
params.min_inter_proportion = 0.2
params.eahelitron_three_prime_fuzzy_level = 3
params.eahelitron_upstream_length = 3000
params.eahelitron_downstream_length = 50
params.ltrharvest_similar = 85
params.ltrharvest_vic = 10
params.ltrharvest_seed = 20
params.ltrharvest_minlenltr = 100
params.ltrharvest_maxlenltr = 7000
params.ltrharvest_mintsd = 4
params.ltrharvest_maxtsd = 6
params.mitefinder_threshold = 0.5
params.trans_table = 1
def run_infernal = !params.noinfernal
def exclude_unclean = { filename -> filename.endsWith(".unclean") ? null : filename }
if ( params.genomes ) {
genomes = Channel
.fromPath(params.genomes, checkIfExists: true, type: "file")
.map { file -> [file.baseName, file] }
} else {
log.info "Hey I need some genomes to assess please."
exit 1
}
if ( params.repbase ) {
Channel
.fromPath(params.repbase, checkIfExists: true, type: "file")
.first()
.set { repbase }
} else {
Channel
.value( file("REPBASE_WAS_NULL") )
.set { repbase }
}
if ( params.rm_meta ) {
Channel
.fromPath(params.rm_meta, checkIfExists: true, type: "file")
.first()
.set { rmMeta }
} else {
Channel
.value( file("RM_META_WAS_NULL") )
.set { rmMeta }
}
if ( params.dfam_hmm ) {
Channel
.fromPath(params.dfam_hmm, checkIfExists: true, type: "file")
.first()
.set { dfamHMMs }
} else {
process getDfamHMMs {
label "download"
label "small_task"
time "24h"
publishDir "${params.outdir}/downloads"
output:
file "dfam.hmm.gz" into dfamHMMs
script:
"""
wget \
--no-check-certificate \
-c \
-O dfam.hmm.gz \
"${params.dfam_hmm_url}"
"""
}
}
if ( params.dfam_embl ) {
Channel
.fromPath(params.dfam_embl, checkIfExists: true, type: "file")
.first()
.set { dfamEMBLs }
} else {
process getDfamEMBLs {
label "download"
label "small_task"
time "12h"
publishDir "${params.outdir}/downloads"
output:
file "dfam.embl.gz" into dfamEMBLs
script:
"""
wget \
--no-check-certificate \
-c \
-O dfam.embl.gz \
"${params.dfam_embl_url}"
"""
}
}
if ( params.rm_repeatpeps ) {
Channel
.fromPath(params.rm_repeatpeps, checkIfExists: true, type: "file")
.first()
.set { rmRepeatPeps }
} else {
process getRMRepeatPeps {
label "repeatmasker"
label "small_task"
time "20m"
publishDir "${params.outdir}/downloads"
output:
file "RepeatPeps.lib" into rmRepeatPeps
script:
"""
cp -L "\${RMASK_PREFIX}/Libraries/RepeatPeps.lib" RepeatPeps.lib
"""
}
}
if ( params.pfam_ids ) {
Channel
.fromPath(params.pfam_ids, checkIfExists: true, type: "file")
.first()
.set { pfamIds }
} else {
pfamLtrIds = Channel.empty()
}
if ( params.rfam && params.rfam_clanin ) {
Channel
.value([
file(params.rfam, checkIfExists: true),
file(params.rfam_clanin, checkIfExists: true),
])
.set { rfam }
} else if ( run_infernal ) {
/*
* Rfam
* doi: 10.1093/nar/gkx1038
* url: https://rfam.xfam.org/
*
* Download Rfam to search with infernal.
* Contains curated CMs/HMMs of ncRNA families.
*/
process getRfam {
label "download"
label "small_task"
time "4h"
publishDir "${params.outdir}/downloads"
output:
set file("Rfam.cm"), file("Rfam.clanin") into rfam
script:
"""
wget -O Rfam.cm.gz "${params.rfam_url}"
wget -O Rfam.clanin "${params.rfam_clanin_url}"
gunzip Rfam.cm.gz
"""
}
} else {
rfam = Channel.empty()
}
if ( params.rfam_gomapping ) {
Channel
.value(file(params.rfam_gomapping, checkIfExists: true))
.set { rfam2GO }
} else if ( run_infernal ) {
process getRfam2GO {
label "download"
label "small_task"
time "1h"
publishDir "${params.outdir}/downloads"
output:
file "rfam2go" into rfam2GO
script:
"""
wget -O rfam2go "${params.rfam_gomapping_url}"
"""
}
} else {
rfam2GO = Channel.empty()
}
if ( params.pfam ) {
Channel
.fromPath( params.pfam, checkIfExists: true, type: "file")
.collectFile(name: "pfam.stk", newLine: true)
.set { pfamMSAs }
} else {
/*
* Download a number of Pfam domains and families associated with
* TE activity.
*/
process getPfam {
label "download"
label "medium_task"
time "4h"
publishDir "${params.outdir}/downloads"
input:
file "pfam_ids.txt" from pfamIds
output:
file "pfam.stk" into pfamMSAs
script:
"""
mkdir -p pfam
cd pfam
cat ../pfam_ids.txt \
| xargs \
-n 1 \
-P "${task.cpus}" \
-I "{}" \
-- \
wget \
--no-check-certificate \
-c \
-O "{}.stk.gz" \
"https://pfam.xfam.org/family/{}/alignment/full/gzipped"
gunzip *.gz
cd ..
cat pfam/*.stk > pfam.stk
rm -rf -- pfam
"""
}
}
if ( params.gypsydb ) {
Channel
.fromPath( params.gypsydb, checkIfExists: true, type: "file")
.set { gypsydb }
} else {
/*
* GypsyDB
*
* doi: 10.1093/nar/gkq1061
* url: http://www.gydb.org/index.php/Main_Page
*
* Curated msas and HMMs of many LTR families.
* It apparently also contains some DNA elements.
*/
process getGypsyDB {
label "download"
label "small_task"
time "4h"
publishDir "${params.outdir}/downloads"
output:
file "gypsydb/*" into gypsydb mode flatten
script:
"""
mkdir gypsydb
wget -O gypsy.zip "${params.gypsydb_url}"
unzip gypsy.zip
mv GyDB*/alignments/*.sto ./gypsydb
rm -rf -- GyDB*
"""
}
}
process processGydb {
label "posix"
label "small_task"
time "20m"
input:
file "stk/*" from gypsydb.collect()
output:
file "gypsydb.stk" into gypsyDBMSAs
script:
"""
touch gypsydb.stk
for f in stk/*;
do
if grep -q "#=GF AC"
then
cat "\${f}" >> gypsydb.stk
else
# Strips directory and extension
FILENAME=\$(basename \${f%.*})
sed "1a #=GF AC \${FILENAME}" "\${f}" >> gypsydb.stk
fi
done
"""
}
Channel
.fromPath(params.protein_families, checkIfExists: true, type: "file")
.first()
.set { proteinFamilies }
if ( params.mitefinder_profiles ) {
Channel
.fromPath(params.mitefinder_profiles, checkIfExists: true, type: "file")
.first()
.set { miteFinderProfiles }
} else {
process getMiteFinderProfiles {
label "mitefinder"
label "small_task"
time "20m"
output:
file "pattern_scoring.txt" into miteFinderProfiles
script:
"""
cp "\${MITEFINDER_PROFILE}" ./
"""
}
}
genomes.into {
genomes4RunTRNAScan;
genomes4ChunkifyGenomes;
genomes4RunStructRNAFinder;
genomes4RunRNAmmer;
genomes4RunOcculterCut;
genomes4GetOcculterCutRegionFrequencies;
genomes4GetOcculterCutGroupedRegionFrequencies;
genomes4RunRepeatMaskerSpecies;
genomes4RunRepeatMasker;
genomes4RunRepeatModeler;
genomes4GetMMSeqsGenomes;
genomes4GetMMSeqsGenomeFastas;
genomes4GetGtSuffixArrays;
genomes4RunLtrHarvest;
genomes4RunEAHelitron;
genomes4RunMiteFinder;
genomes4GetMiteFinderGFFs;
genomes4GetMiteFinderFastas;
genomes4GetSoftmaskedGenomes;
}
//
// Finding non-coding RNA
//
/*
* tRNAScan-SE
* doi: 10.1101/614032
* url: http://lowelab.ucsc.edu/tRNAscan-SE/
*/
process runTRNAScan {
label "trnascan"
label "medium_task"
time "5h"
publishDir "${params.outdir}/${name}/noncoding"
tag "${name}"
input:
set val(name), file(fasta) from genomes4RunTRNAScan
output:
set val(name),
file("${name}_trnascan.txt"),
file("${name}_trnascan_ss.txt") into tRNAScanResults
set val(name), file("${name}_trnascan.fasta") into tRNAScanFasta
file "${name}_trnascan_iso.txt"
file "${name}_trnascan_stats.txt"
file "${name}_trnascan.bed"
script:
"""
tRNAscan-SE \
-E \
-o "${name}_trnascan.txt" \
-f "${name}_trnascan_ss.txt" \
-s "${name}_trnascan_iso.txt" \
-m "${name}_trnascan_stats.txt" \
-b "${name}_trnascan.bed" \
-a "${name}_trnascan.fasta" \
--forceow \
--log trna.log \
--thread "${task.cpus}" \
"${fasta}"
"""
}
/*
* Convert trnascan-se output to nice GFF3.
* Add predicted secondary structure and anticodons as attributes.
*/
process getTRNAScanGFF {
label "gffpal"
label "small_task"
time "1h"
tag "${name}"
input:
set val(name), file("ts.txt"), file("ss.txt") from tRNAScanResults
output:
set val(name),
val("noncoding"),
val("tRNAScan-SE"),
val("trnascan"),
file("trnascan.gff3") into tRNAScanGFF
script:
"""
gffpal trnascan2gff -o "trnascan.gff3" ts.txt ss.txt
"""
}
/*
* Prepare the Rfam database to search with infernal.
*/
process pressRfam {
label "infernal"
label "small_task"
time "2h"
when:
run_infernal
input:
set file("Rfam.cm"), file("Rfam.clanin") from rfam
output:
file "out" into pressedRfam
script:
"""
mkdir out
cp -L Rfam.cm out/Rfam.cm
cp -L Rfam.clanin out/Rfam.clanin
cmpress -F out/Rfam.cm
"""
}
/*
* Split genome fastas into multiple fastas for parallelisation.
*/
process chunkifyGenomes {
label "python3"
label "small_task"
time "1h"
tag "${name}"
when:
run_infernal
input:
set val(name),
file("input.fasta") from genomes4ChunkifyGenomes
output:
set val(name),
file("input.fasta"),
file("out_*.fasta") into chunkifiedGenomes
script:
"""
chunk_genomes.py -n 32 --prefix "out_" input.fasta
"""
}
/*
* Infernal
* doi: 10.1093/bioinformatics/btt509
* url: http://eddylab.org/infernal/
*
* Searches Rfam vs genome.
* tblout2gff script comes from <https://github.com/nawrockie/jiffy-infernal-hmmer-scripts>
*/
process runInfernal {
label "infernal"
label "small_task"
time "5h"
tag "${name}"
publishDir "${params.outdir}/${name}/noncoding", saveAs: exclude_unclean
when:
run_infernal
input:
set val(name),
file("genome.fasta"),
file("chunk.fasta") from chunkifiedGenomes
.flatMap { n, g, cs -> cs.collect { c -> [n, g, c] } }
file "rfam" from pressedRfam
output:
set val(name), file("cmscan.gff3.unclean") into infernalMatches
file "${name}_rfam_cmscan.tblout"
file "${name}_rfam_cmscan.out"
script:
"""
SIZE=\$(grep -v "^>" genome.fasta | sed 's/[[:space:]]//' | tr -d '\\n' | wc -c)
TRSIZE=\$(perl -E "say \${SIZE} * 2 / 1e6")
cmscan \
--cpu 1 \
-Z "\${TRSIZE}" \
--cut_ga \
--rfam \
--nohmmonly \
--tblout "${name}_rfam_cmscan.tblout" \
--fmt 2 \
--clanin rfam/Rfam.clanin \
rfam/Rfam.cm \
chunk.fasta \
> "${name}_rfam_cmscan.out"
grep -v ' = ' "${name}_rfam_cmscan.tblout" > filtered.txt
infernal-tblout2gff.pl \
--cmscan \
--fmt2 \
--all \
-E "${params.infernal_max_evalue}" \
filtered.txt \
> "cmscan.gff3.unclean"
rm filtered.txt
"""
}
process tidyInfernalMatches {
label "gffpal"
label "small_task"
time "1h"
tag "${name}"
input:
set val(name), file("infernal.gff3") from infernalMatches
file "rfam2go" from rfam2GO
output:
set val(name), file("tidied.gff3") into tidiedInfernalMatches
script:
"""
awk -F '\\t' '
BEGIN {OFS="\\t"}
{\$9=gensub(":", "=", "g", \$9); print}
' infernal.gff3 \
| tidy_infernal_gff.py \
--go rfam2go \
--best \
--source "Rfam" \
--type nucleotide_match \
-o tidied.gff3 \
-
"""
}
/*
* Recombine infernal chunks into a single gff.
*/
process combineInfernal {
label "genometools"
label "small_task"
time "1h"
tag "${name}"
when:
run_infernal
input:
set val(name),
file("unclean/*.gff3") from tidiedInfernalMatches
.groupTuple(by: 0)
output:
set val(name),
val("noncoding"),
val("Rfam"),
val("rfam_cmscan"),
file("rfam_cmscan.gff3") into infernalGFF
script:
"""
mkdir clean
for f in unclean/*.gff3
do
gt gff3 -tidy -sort "\${f}" > "clean/\$(basename \${f})"
done
gt merge -tidy clean/*.gff3 > "rfam_cmscan.gff3"
"""
}
/*
* RNAmmer
* doi: 10.1093/nar/gkm160
* url: http://www.cbs.dtu.dk/services/RNAmmer/
*/
process runRNAmmer {
label "rnammer"
label "small_task"
time "5h"
publishDir "${params.outdir}/${name}/noncoding", saveAs: exclude_unclean
tag "${name}"
when:
params.rnammer
input:
set val(name), file(fasta) from genomes4RunRNAmmer
output:
set val(name), file("rnammer.gff2.unclean") into rnammerResults
file "${name}_rnammer.hmmreport"
"""
rnammer \
-S euk \
-m lsu,ssu,tsu \
-gff "rnammer.gff2.unclean" \
-h "${name}_rnammer.hmmreport" \