-
Notifications
You must be signed in to change notification settings - Fork 2
/
nextflow.config
1248 lines (1129 loc) · 44.7 KB
/
nextflow.config
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
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
phac-nml/mikrokondo Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Default config options for all compute environments
----------------------------------------------------------------------------------------
*/
// Global default params, used in configs
params {
// Input options
input = null
// Index creation output file
output_idx_name = null
// List all allowed platforms
opt_platforms {
// ! WARNING if these are ever spelt wrong you get esoteric errors...
illumina = "illumina"
ont = "nanopore"
pacbio = "pacbio"
hybrid = "hybrid" // assumes illumina and long reads
}
flye_read_type = "hq" // options are hq, corr or raw
platform = params.opt_platforms.illumina
long_read_opt = params.opt_platforms.ont
nanopore_chemistry = null
run_kraken = false // Run kraken if true or mash screen on contigs if false
hybrid_unicycler = false // run alternative assembly workflow
// Filtering options
min_reads = 1000 // The minimum number of reads needed for a sample to continue through the pipeline
// Sub sampling options
target_depth = 100
validate_params = true
show_hidden_params = false
validationS3PathCheck = true
validationShowHiddenParams = false
validationSchemaIgnoreParams = 'locidex_summary,allele_scheme_selected,top_hit_method,abricate,locidex,assembly_status,bakta,bandage,checkm,chopper,contigs_too_short,coreutils,coverage_calc_fields,ectyper,fastp,fastqc,filtered_reads,flye,kat,kleborate,kraken,kraken_bin,kraken_species,lissero,mash,mash_meta,medaka,minimap2,mlst,mobsuite_recon,opt_platforms,pilon,pilon_iterative,pointfinder_db_tag,python3,QCReport,QCReport-fields,QCReportFields,quast,racon,raw_reads,report_aggregate,r_contaminants,samtools,seqkit,seqtk,seqtk_size,shigeifinder,sistr,spades,spatyper,staramr,subtyping_report,top_hit_species,unicycler'
validationFailUnrecognisedParams = false // for the qcreport fields
// SKIP options
// TODO need to add constants section
// TODO investigate usage of template scripts to replace mash modules
skip_report = false
skip_raw_read_metrics = false
skip_version_gathering = false
skip_subtyping = false
skip_bakta = true
skip_abricate = false
skip_checkm = false
skip_depth_sampling = false // TODO have it mentioned that this should be turned off for metagenomic runs
skip_ont_header_cleaning = true // TODO an awk script can likely replace this and be much faster at what it does...
skip_polishing = false // TODO make it clear this does not apply to Hybrid assembly
skip_species_classification = false
skip_mlst = false
skip_mobrecon = false
skip_staramr = false
skip_metagenomic_detection = false // Skip classifying if sample is metagenomic
skip_allele_calling = false
skip_length_filtering_contigs = false
metagenomic_run = false // Label all samples as
// Datasets
dehosting_idx = null // mm2 index
mash_sketch = null // Make sure comments are formatted as taxonomic strings
bakta_db = null
kraken2_db = null
staramr_db = null // Recommended usage is to use the default database in the container
// FastP parameters
fp_average_quality = 25
fp_cut_tail_mean_quality = 15
fp_cut_tail_window_size = 4
fp_complexity_threshold = 20
fp_qualified_phred = 15
fp_unqualified_percent_limit = 40
fp_polyg_min_len = 10
fp_polyx_min_len = 10
fp_illumina_length_min = 35
fp_illumina_length_max = 400
fp_single_end_length_min = 1000 // Affects nanopore only
fp_dedup_reads = false
// Bakta Parmeters
ba_min_contig_length = 200
// Quast parameters
qt_min_contig_length = 1000
// Mash
mh_min_kmer = 10
// ECTyper Parameters
ec_opid = 90 // Minimum percent identity to determine O antigens prescence
ec_opcov = 90 // Minimum percent coverage of O antigen
ec_hpid = 95 // Miniumum percent identity to determine H antigens prescence
ec_hpcov = 50 // Minimum percent coverage of H antigen
ec_enable_verification = true // Enable species verification in ECTyper
// SISTR parameters
sr_full_cgmlst = true // Use full set of cgMLST alleles which can include highly similar alleles
// Allele Scheme Options
override_allele_scheme = "" // Supply an allele scheme that will be used for allele calling of all samples
lx_allele_database = null // A path to the locidex manifest.json file needed for allele calling.
// Locidex Options
lx_min_evalue = 0.0001
lx_min_dna_len = 1
lx_min_aa_len = 1
lx_max_dna_len = 10000000
lx_max_aa_len = 10000000
lx_min_dna_ident = 80.0
lx_min_aa_ident = 80.0
lx_min_dna_match_cov = 80.0
lx_min_aa_match_cov = 80.0
lx_max_target_seqs = 10
lx_extraction_mode = "raw"
lx_report_mode = "normal"
lx_report_prop = "locus_name"
lx_report_max_ambig = 0
lx_report_max_stop = 0
// Boilerplate options
outdir = null
tracedir = "${params.outdir}/pipeline_info"
publish_dir_mode = 'copy'
email = null
email_on_fail = null
plaintext_email = false
monochrome_logs = false
hook_url = null
help = false
version = false
// If a param in camel case is present nextflow automatically creates a kebab case parameter as well
stage_in_mode = 'symlink'
// Config options
custom_config_version = 'master'
custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
config_profile_description = null
config_profile_contact = null
config_profile_url = null
config_profile_name = null
// use slurm executor
// TODO add in max runtime for jobs, as to not run up cloud, local or cluster resources
slurm_p = false
slurm_profile = ""
// Max resource options
// Defaults only, expecting to be overwritten
max_memory = '2000.GB'
max_cpus = 16
max_time = '240.h'
abricate {
singularity = "https://depot.galaxyproject.org/singularity/abricate%3A1.0.1--ha8f3691_1"
docker = "biocontainers/abricate:1.0.1--ha8f3691_1"
args = { "" }
report_tag = "Abricate"
header_p = true
}
raw_reads {
high_precision = false // Makes things really slow
report_tag = "RawReadSummary"
}
// coreutils e.g. cat
coreutils {
singularity = "https://depot.galaxyproject.org/singularity/coreutils%3A8.31--h14c3975_0"
docker = 'biocontainers/coreutils:8.31--h14c3975_0'
}
// Python container, May switch for pypy3
python3 {
singularity = "https://depot.galaxyproject.org/singularity/python:3.12"
docker = "biocontainers/python:3.12"
}
rasusa {
docker = "biocontainers/rasusa:2.1.0--h715e4b3_0"
singularity = "https://depot.galaxyproject.org/singularity/rasusa:2.1.0--h715e4b3_0"
reads_ext = ".sampled.fastq.gz"
seed = 42
}
seqtk {
singularity = 'https://depot.galaxyproject.org/singularity/seqtk%3A1.4--he4a0461_1'
docker = 'biocontainers/seqtk:1.4--he4a0461_1'
seed = 42
reads_ext = ".sampled.fastq.gz"
assembly_fastq = ".fastq.gz"
report_tag = "Seqtk"
}
seqtk_size {
singularity = 'https://depot.galaxyproject.org/singularity/seqtk%3A1.4--he4a0461_1'
docker = 'biocontainers/seqtk:1.4--he4a0461_1'
report_tag = "SeqtkBaseCount"
}
locidex {
// awaiting singluarity image build
singularity = "docker.io/mwells14/locidex:0.2.3"
docker = "docker.io/mwells14/locidex:0.2.3"
private_repository = 'mwells14/locidex:0.2.3'
min_evalue = params.lx_min_evalue
min_dna_len = params.lx_min_dna_len
min_aa_len = params.lx_min_aa_len
max_dna_len = params.lx_max_dna_len
max_aa_len = params.lx_max_aa_len
min_dna_ident = params.lx_min_dna_ident
min_aa_ident = params.lx_min_aa_ident
min_dna_match_cov = params.lx_min_dna_match_cov
min_aa_match_cov = params.lx_min_aa_match_cov
max_target_seqs = params.lx_max_target_seqs
extraction_mode = params.lx_extraction_mode
report_mode = params.lx_report_mode
report_prop = params.lx_report_prop
report_max_ambig = params.lx_report_max_ambig
report_max_stop = params.lx_report_max_stop
allele_database = params.lx_allele_database
date_format_string = "yyyy-MM-dd"
manifest_db_path = "path"
manifest_config_key = "config"
manifest_config_name = "db_name"
manifest_config_version = "db_version"
manifest_name = "manifest.json"
config_data_file = "config.json"
database_config_value_date = "db_date"
extracted_seqs_suffix = ".extracted.seqs.fasta.gz"
seq_store_suffix = ".seq_store.json.gz"
gbk_suffix = ".gbk.gz"
extraction_dir = "extracted"
report_suffix = ".profile.mlst.json.gz"
db_config_output_name = "SelectedLocidexConfig.json"
report_tag = "LocidexDatabaseInformation"
}
locidex_summary {
report_tag = "LocidexSummary"
data_key = "data"
data_profile_key = "profile"
data_sample_key = "sample_name"
missing_allele_value = '-'
reportable_alleles = []
report_exclude_fields = ["MissingAlleles"]
}
allele_scheme_selected {
report_tag = "AlleleSchemeUsed"
}
// FASTP options
fastp {
fastq_ext = ".trimmed.fastq.gz"
singularity = 'https://depot.galaxyproject.org/singularity/fastp%3A0.23.2--hb7a2d85_2'
docker = 'biocontainers/fastp:0.23.2--hb7a2d85_2'
html_ext = ".html"
json_ext = ".json"
report_tag = "FastP"
average_quality_e = params.fp_average_quality // The -e option in fastp for if the average quality is less than specified then read/read-pair is discarded
cut_tail_mean_quality = params.fp_cut_tail_mean_quality
cut_tail_window_size = params.fp_cut_tail_window_size // default is 4
complexity_threshold = params.fp_complexity_threshold // FastP default is 30 not 20
qualified_quality_phred = params.fp_qualified_phred // min quality for a read to contain
unqualified_percent_limit = params.fp_unqualified_percent_limit // if the minimum quality of a read is below 10 that read is discarded
polyg_min_len = params.fp_polyg_min_len
polyx_min_len = params.fp_polyx_min_len
illumina_length_min = params.fp_illumina_length_min
illumina_length_max = params.fp_illumina_length_max
single_end_length_min = params.fp_single_end_length_min
dedup_reads = params.fp_dedup_reads
// -c is used to apply overlap analysis and cut out out adapters
args {
illumina = "--overrepresentation_analysis --trim_poly_g --poly_g_min_len ${params.fastp.polyg_min_len} --trim_poly_x --poly_x_min_len ${params.fastp.polyx_min_len} --cut_tail --cut_tail_window_size ${params.fastp.cut_tail_window_size} --cut_tail_mean_quality ${params.fastp.cut_tail_mean_quality} --low_complexity_filter --complexity_threshold ${params.fastp.complexity_threshold} --average_qual ${params.fastp.average_quality_e} --qualified_quality_phred ${params.fastp.qualified_quality_phred} --unqualified_percent_limit ${params.fastp.unqualified_percent_limit} --length_limit ${params.fastp.illumina_length_max} --length_required ${params.fastp.illumina_length_min} --detect_adapter_for_pe"
single_end = "--overrepresentation_analysis -Q --length_required ${params.fastp.single_end_length_min}"
}
report_exclude_fields = ["content_curves", "quality_curves", "mean", "kmer_count", "histogram", "overrepresented_sequences"]
}
// Nanofilter options
chopper {
singularity = 'https://depot.galaxyproject.org/singularity/chopper%3A0.5.0--hd03093a_0'
quality = 0
minlength = 100
fastq_ext = ".fastq.gz"
}
// Flye options
// TODO figure out if --keep-haplotypes should be enabled
flye {
// TODO add in arg for data type in flye
nanopore {
raw = "--nano-raw"
corr = "--nano-corr"
hq = "--nano-hq"
}
pacbio {
raw = "--pacbio-raw"
corr = "--pacbio-corr"
hq = "--pacbio-hifi" // TODO all reads are marked as hifi
}
singularity = 'https://depot.galaxyproject.org/singularity/flye:2.9--py39h6935b12_1'
docker = 'biocontainers/flye:2.9.2--py39h6935b12_0'
fasta_ext = ".fasta.gz"
gfa_ext = ".gfa.gz"
gv_ext = ".gv.gz"
txt_ext = ".txt"
log_ext = ".log"
json_ext = ".json"
polishing_iterations = 1
args = { "--iterations ${params.flye.polishing_iterations}" } // this is normlly configured through task.ext.args... but idk how I feel about that yet
}
// SPADES options
spades {
singularity = 'https://depot.galaxyproject.org/singularity/spades:3.15.5--h95f258a_1'
docker = 'biocontainers/spades:3.15.5--h95f258a_1'
outdir = "assembly"
scaffolds_ext = ".scaffolds.fasta.gz"
contigs_ext = ".contigs.fasta.gz"
transcripts_ext = ".transcripts.fasta.gz"
gene_clusters_ext = ".gene_clusters.fasta.gz"
assembly_graphs_ext = ".assembly.gfa.gz"
log_ext = ".log"
}
// Fastqc options
fastqc {
html_ext = ".html"
zip_ext = ".zip"
}
// TODO add to docs
seqkit {
singularity = 'https://depot.galaxyproject.org/singularity/seqkit:2.2.0--h9ee0642_0'
docker = 'biocontainers/seqkit:2.2.0--h9ee0642_0'
report_ext = ".tsv"
fasta_ext = ".filtered.fasta.gz"
filter_field = "max_len"
report_tag = "Seqkit_stats"
header_p = true
}
// QUAST args
quast{
singularity = 'https://depot.galaxyproject.org/singularity/quast%3A5.2.0--py39pl5321h4e691d4_3' // not all Quast containers work, might get file system error with BWA, if issue persists reads can be not passed to the module instead
docker = 'biocontainers/quast:5.2.0--py39pl5321h4e691d4_3'
suffix = "quast"
report_base = "report"
report_prefix = "transposed_"
report_ext = ".tsv"
report_tag = "QUAST"
min_contig_length = params.qt_min_contig_length
contigs_field = "# contigs"
// need to add a --min-contig args to set to 0 as at 500 currently add --report-all-metrics
// also need to see if a sam can be published from quast
args = { "--min-contig ${params.quast.min_contig_length} --report-all-metrics" }
header_p = true
}
checkm {
// TODO add to trouble shooting if checkm fails and provides EOF errors, to try changing the container
singularity = 'https://depot.galaxyproject.org/singularity/checkm-genome%3A1.2.2--pyhdfd78af_1'
docker = 'biocontainers/checkm-genome:1.2.2--pyhdfd78af_1'
alignment_ext = ".genes.aln"
results_ext = ".results.txt"
tsv_ext = ".tsv"
folder_name = "checkm"
gzip_ext = ".gz"
lineage_ms = "lineage.ms"
report_tag = "CheckM"
header_p = true
}
// Kraken args
kraken {
singularity = 'https://depot.galaxyproject.org/singularity/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:87fc08d11968d081f3e8a37131c1f1f6715b6542-0'
docker = 'biocontainers/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:941789bd7fe00db16531c26de8bf3c5c985242a5-0'
db = params.kraken2_db
classified_suffix = "classified"
unclassified_suffix = "unclassified"
report_suffix = "report"
output_suffix = "output"
tophit_level = "S" // level to select the samples top-hit based on kraken2
save_output_fastqs = false
save_reads_assignments = true
run_kraken_quick = false
report_tag = "KrakenReport"
header_p = false
headers = ["PercentID", "FragmentsRecovered", "FragmentsAssignmentTaxon", "RankCode", "NCBITaxonID", "ScientificName"]
}
mlst {
singularity = "https://depot.galaxyproject.org/singularity/mlst%3A2.23.0--hdfd78af_1"
docker = "quay.io/biocontainers/mlst:2.23.0--hdfd78af_1"
args = ""
tsv_ext = ".tsv"
json_ext = ".json"
report_tag = "SevenGeneMLSTReport"
}
mash {
singularity = "https://depot.galaxyproject.org/singularity/mash:2.3--he348c14_1"
docker = 'biocontainers/mash:2.3--he348c14_1'
// going forward labeled with _ext include '.'
mash_ext = ".screen" //TODO refactor out of utility workflow
output_reads_ext = ".reads.screen"
output_taxa_ext = ".taxa.screen"
output_dir = "contamination"
mash_sketch = params.mash_sketch
sketch_ext = ".msh"
json_ext = ".json"
sketch_kmer_size = 21 // defualt param in mash
min_kmer = params.mh_min_kmer
final_sketch_name = "GTDB_sketch"
report_tag = "Mash"
header_p = false
headers = ["identity", "Shared Hashes", "Median Multiplicity", "P-Value", "Query ID", "Query Note"]
}
mash_meta {
report_tag = "MashMeta"
}
top_hit_species {
report_tag = "SpeciesTopHit"
}
top_hit_method {
report_tag = "IdentificationMethod"
}
r_contaminants {
// container contains minimap2 and samtools
singularity = "https://depot.galaxyproject.org/singularity/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:3161f532a5ea6f1dec9be5667c9efc2afdac6104-0"
docker = "biocontainers/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:3161f532a5ea6f1dec9be5667c9efc2afdac6104-0"
phix_fa = ""
homo_sapiens_fa = ""
pacbio_mg = ""
output_ext = ".cleaned.fastq.gz"
mega_mm2_idx = params.dehosting_idx
mm2_illumina = "-x sr" // ax outputs sam
mm2_pac = "-x map-pb"
mm2_ont = "-x map-ont"
mm2_output_ext = ".sam"
samtools_output_ext = ".fastq"
samtools_singletons_ext = ".singleton.fq"
samtools_output_suffix = "deconned"
output_ext = "${samtools_output_ext}.gz"
output_dir = "${params.mash.output_dir}/deconned_reads"
}
minimap2 {
// for creation of indices from assemblies
singularity = params.r_contaminants.singularity
docker = params.r_contaminants.docker
index_outdir = "indices"
index_ext = ".idx"
mapped_paf_ext = ".paf"
mapped_sam_ext = ".sam"
mapped_outdir = "mapped"
}
samtools {
singularity = params.r_contaminants.singularity
docker = params.r_contaminants.docker
bam_ext = ".bam"
bai_ext = ".bai"
}
racon {
singularity = 'https://depot.galaxyproject.org/singularity/racon:1.4.20--h9a82719_1'
docker = 'biocontainers/racon:1.4.20--h9a82719_1'
consensus_suffix = "_assembly_consensus.fasta"
consensus_ext = ".fasta.gz"
outdir = "polished"
}
pilon {
singularity = 'https://depot.galaxyproject.org/singularity/pilon%3A1.24--hdfd78af_0'
docker = 'biocontainers/pilon:1.24--hdfd78af_0'
outdir = "pilon"
fasta_ext = ".fasta.gz"
fasta_outdir = "fasta"
vcf_ext = ".vcf"
vcf_outdir = "vcf"
changes_ext = ".changes"
changes_outdir = "changes"
max_memory_multiplier = 3
}
pilon_iterative {
singularity = 'docker.io/mwells14/pilonpolisher:0.0.1' // Docker containers will be converted to singularity
docker = 'docker.io/mwells14/pilonpolisher:0.0.1'
private_repository = 'mwells14/pilonpolisher:0.0.1'
outdir = "pilon"
fasta_ext = ".fasta.gz"
fasta_outdir = "fasta"
vcf_ext = ".vcf"
vcf_outdir = "vcf"
bam_ext = ".bam"
bai_ext = ".bai"
changes_ext = ".changes"
changes_outdir = "changes"
max_memory_multiplier = 3 // how much memory is increased after each run failure
max_polishing_illumina = 3
max_polishing_pacbio = 4
max_polishing_nanopore = 10
}
medaka {
singularity = 'https://depot.galaxyproject.org/singularity/medaka%3A1.8.0--py38hdaa7744_0'
docker = 'biocontainers/medaka:1.8.0--py38hdaa7744_0'
model = params.nanopore_chemistry
fasta_ext = ".fa.gz"
outdir = "medaka"
batch_size = 5
}
unicycler {
singularity = 'https://depot.galaxyproject.org/singularity/unicycler%3A0.5.0--py38h3b68952_2'
docker = 'biocontainers/unicycler:0.5.0--py38h3b68952_2'
scaffolds_ext = ".scaffolds.fa.gz"
assembly_ext = ".assembly.gfa.gz"
log_ext = ".unicycler.log"
outdir = "unicycler"
mem_modifier = 1000 // overly large number to provide more memory for unicycler
threads_increase_factor = 1
}
mobsuite_recon {
singularity = 'https://depot.galaxyproject.org/singularity/mob_suite%3A3.0.3--pyhdfd78af_0'
docker = 'biocontainers/mob_suite:3.0.3--pyhdfd78af_0'
args = { "" }
fasta_ext = ".fasta"
results_ext = ".txt"
mob_results_file = "mobtyper_results.txt"
contig_report = "contig_report.txt"
report_tag = "MobRecon"
header_p = true
}
staramr {
singularity = "biocontainers/staramr:0.10.0--pyhdfd78af_0"
docker = "biocontainers/staramr:0.10.0--pyhdfd78af_0"
point_finder_db_default = null
db = null
tsv_ext = ".tsv"
txt_ext = ".txt"
xlsx_ext = ".xlsx"
args = { "" }
// Approved point finder databases
point_finder_dbs = ['salmonella', 'campylobacter', 'enterococcus_faecalis',
'enterococcus_faecium', 'escherichia_coli', 'helicobacter_pylori']
report_tag = "StarAMR"
header_p = true
}
pointfinder_db_tag {
report_tag = "PointfinderDB"
}
bakta {
// TODO verify bakta version in scripts so that greater than 1.8 exists for force options
singularity = 'https://depot.galaxyproject.org/singularity/bakta%3A1.8.1--pyhdfd78af_0'
docker = 'biocontainers/bakta:1.8.1--pyhdfd78af_0'
db = params.bakta_db
output_dir = "bakta"
embl_ext = ".embl"
faa_ext = ".faa"
ffn_ext = ".ffn"
fna_ext = ".fna"
gbff_ext = ".gbff"
gff_ext = ".gff3"
threads = 12 // default number of threads, more is not always better
hypotheticals_tsv_ext = ".hypotheticals.tsv"
hypotheticals_faa_ext = ".hypotheticals.faa"
tsv_ext = ".tsv"
txt_ext = ".txt"
min_contig_length = params.ba_min_contig_length
args = { "" }
}
bandage {
singularity = 'https://depot.galaxyproject.org/singularity/bandage:0.8.1--hc9558a2_2'
docker = 'biocontainers/bandage:0.8.1--hc9558a2_2'
svg_ext = ".svg"
outdir = "bandage"
}
subtyping_report {
report_tag = "Subtyping"
}
ectyper {
singularity = 'https://depot.galaxyproject.org/singularity/ectyper:1.0.0--pyhdfd78af_1'
docker = 'biocontainers/ectyper:1.0.0--pyhdfd78af_1'
log_ext = ".log"
tsv_ext = ".tsv"
txt_ext = ".txt"
opid = params.ec_opid
opcov = params.ec_opcov
hpid = params.ec_hpid
hpcov = params.ec_hpcov
verify = params.ec_enable_verification ? "--verify" : ""
args = { "${params.ectyper.verify} -opid ${params.ectyper.opid} -opcov ${params.ectyper.opcov} -hpid ${params.ectyper.hpcov} -hpcov ${params.ectyper.hpcov}" }
report_tag = "ECTyper${params.subtyping_report.report_tag}"
header_p = true
}
kleborate {
singularity = 'https://depot.galaxyproject.org/singularity/kleborate:2.1.0--pyhdfd78af_1'
docker = 'biocontainers/kleborate:2.1.0--pyhdfd78af_1'
txt_ext = ".results.txt"
report_tag = "Kleborate${params.subtyping_report.report_tag}"
header_p = true
}
spatyper {
// TODO figure out what repeats input is
singularity = 'https://depot.galaxyproject.org/singularity/spatyper:0.3.3--pyhdfd78af_3'
docker = 'biocontainers/spatyper:0.3.3--pyhdfd78af_3'
tsv_ext = ".tsv"
report_tag = "SpaTyper${params.subtyping_report.report_tag}"
header_p = true
repeats = null
repeat_order = null
}
sistr {
singularity = "https://depot.galaxyproject.org/singularity/sistr_cmd:1.1.1--pyh864c0ab_2"
docker = 'biocontainers/sistr_cmd:1.1.1--pyh864c0ab_2'
tsv_ext = ".tab"
allele_fasta_ext = ".allele.fasta"
allele_json_ext = ".allele.json"
cgmlst_ext = ".cgmlst.csv"
full_cgmlst = params.sr_full_cgmlst
report_tag = "SISTR${params.subtyping_report.report_tag}"
header_p = true
}
lissero {
singularity = 'https://depot.galaxyproject.org/singularity/lissero:0.4.9--py_0'
docker = 'biocontainers/lissero:0.4.9--py_0'
tsv_ext = ".tsv"
report_tag = "LISSERO${params.subtyping_report.report_tag}"
header_p = true
}
shigeifinder {
container_version = '1.3.2' // update version info with containers as it is not included in shigeifinder
singularity = 'https://depot.galaxyproject.org/singularity/shigeifinder:1.3.2--pyhdfd78af_0'
docker = 'biocontainers/shigeifinder:1.3.2--pyhdfd78af_0'
tsv_ext = ".tsv"
report_tag = "Shigeifinder${params.subtyping_report.report_tag}"
header_p = true
}
//shigatyper {
// singularity = 'https://depot.galaxyproject.org/singularity/shigatyper%3A2.0.1--pyhdfd78af_0'
// docker = 'biocontainers/shigatyper:2.0.1--pyhdfd78af_0'
// tsv_ext = ".tsv"
// report_tag = "ShigaTyper${params.subtyping_report.report_tag}"
// //report_tag = params.subtyping_report.report_tag
// header_p = true
//}
coverage_calc_fields {
//bp_field = params.seqtk_size.report_tag // Trimmed base count size
bp_field = [params.raw_reads.report_tag, "combined", "total_bp"]
fixed_cov = "FixedGenomeSizeDepth"
auto_cov = "DetectedGenomeSizeDepth"
}
assembly_status {
report_tag = "AssemblyCompleted"
}
contigs_too_short {
report_tag = "MaxContigToShort"
}
filtered_reads {
threshold = params.min_reads
report_tag = "MeetsReadThreshold"
}
kraken_bin {
// Python only
taxonomic_level = "G"
fasta_ext = ".fasta.gz"
}
report_aggregate {
sample_flat_suffix = ".flat_sample.json"
}
/*
Base fields for an organism for quality control checking
search: The phrase to search for to determine it is a specific organism
average_quality: average quality of bases must be greater than or equal too
min_n50: n50 value to be greater than or equal too
max_n50: n50 value must be less than or equal too
min_nr_contigs: lower bound minimum of conitgs
max_nr_contigs: upper bound for number of contigs
fixed_genome_size = A set genome size to use for naively calculating genome size
min_length: minimum acceptable length
max_length: maximum acceptable genome length
search =
! Need to provide filtering based on original quality score on raw data
! TODO need to determine if this should happen pre-decon
quality_field = FastP.summary.before_filtering.
raw_average_quality =
min_n50 =
max_n50 =
min_nr_contigs =
max_nr_contigs =
fixed_genome_size =
min_length =
max_length =
max_checkm_contamination = 1.0
average_coverage =
TODO add in tag referencing relevant subtyping tool for including results in final summary csv
*/
QCReport {
escherichia {
search = "Escherichia coli"
raw_average_quality = 30
min_n50 = 50000
max_n50 = 6000000
min_nr_contigs = 1
max_nr_contigs = 500
fixed_genome_size = 5000000
min_length = 4500000
max_length = 6000000
max_checkm_contamination = 3.0
min_average_coverage = 40
}
salmonella {
search = "Salmonella"
raw_average_quality = 30
min_n50 = 90000
max_n50 = 6000000
min_nr_contigs = 1
max_nr_contigs = 200
fixed_genome_size = 5000000
min_length = 4400000
max_length = 6000000
max_checkm_contamination = 3.0
min_average_coverage = 40
}
shigella {
search = "Shigella"
raw_average_quality = 30
min_n50 = 18000
max_n50 = 5000000
min_nr_contigs = 1
max_nr_contigs = 500
fixed_genome_size = 5000000
min_length = 4300000
max_length = 5000000
max_checkm_contamination = 3.0
min_average_coverage = 40
}
listeria {
search = "Listeria"
raw_average_quality = 30
min_n50 = 50000
max_n50 = 3200000
min_nr_contigs = 1
max_nr_contigs = 200
fixed_genome_size = 3000000
min_length = 2700000
max_length = 3200000
max_checkm_contamination = 3.0
min_average_coverage = 30
}
campylobacter_jejuni {
search = "Campylobacter jejuni"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 2000000
min_nr_contigs = 1
max_nr_contigs = 150
fixed_genome_size = 1800000
min_length = 1400000
max_length = 2000000
max_checkm_contamination = 3.0
min_average_coverage = 30
}
campylobacter_coli {
search = "Campylobacter coli"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 2000000
min_nr_contigs = 1
max_nr_contigs = 150
fixed_genome_size = 1800000
min_length = 1400000
max_length = 2000000
max_checkm_contamination = 3.0
min_average_coverage = 30
}
vibrio_cholerae {
search = "Vibrio cholerae"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 4300000
min_nr_contigs = 1
max_nr_contigs = 150
fixed_genome_size = 4000000
min_length = 3800000
max_length = 4300000
max_checkm_contamination = 3.0
min_average_coverage = 40
}
// Some of these defaults are made up
klebsiella {
search = "Klebsiella"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 6500000
min_nr_contigs = 1
max_nr_contigs = 500
min_length = 4500000
max_length = 6500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
staphylococcus {
search = "Staphylococcus"
raw_average_quality = 30
min_n50 = 30000
max_n50 = 3500000
min_nr_contigs = 1
max_nr_contigs = 250
min_length = 2500000
max_length = 3500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
enterobacter {
search = "Enterobacter"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 6500000
min_nr_contigs = 1
max_nr_contigs = 500
min_length = 4500000
max_length = 6500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
citrobacter {
search = "Citrobacter"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 6500000
min_nr_contigs = 1
max_nr_contigs = 500
min_length = 4500000
max_length = 6500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
acinetobacter {
search = "Acinetobacter"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 6500000
min_nr_contigs = 1
max_nr_contigs = 500
min_length = 4500000
max_length = 6500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
pseudomonas {
search = "Pseudomonas"
raw_average_quality = 30
min_n50 = 100000
max_n50 = 7000000
min_nr_contigs = 1
max_nr_contigs = 500
min_length = 5000000
max_length = 7000000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
enterococcus {
search = "Enterococcus"
raw_average_quality = 30
min_n50 = 15000
max_n50 = 3500000
min_nr_contigs = 1
max_nr_contigs = 550
min_length = 2500000
max_length = 3500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
clostridioides {
search = "Clostridioides"
raw_average_quality = 30
min_n50 = 20000
max_n50 = 4500000
min_nr_contigs = 1
max_nr_contigs = 600
min_length = 4000000
max_length = 4500000
max_checkm_contamination = 3.0
min_average_coverage = 50
}
fallthrough {
search = "No organism specific QC data available."
raw_average_quality = 30
min_n50 = null
max_n50 = null
min_nr_contigs = null
max_nr_contigs = null
fixed_genome_size = null
min_length = null
max_length = null
max_checkm_contamination = 3.0
min_average_coverage = 30
}
}
QCReportFields {
// Configure paths if final report where relevant data is required
raw_average_quality {
path = [params.raw_reads.report_tag, "combined", "qual_mean"]
coerce_type = 'Float'
compare_fields = ['raw_average_quality']
comp_type = "ge"
on = true
low_msg = "Base quality is poor, resequencing is recommended."
}
average_coverage {
/*
* Example path below can be used for qaust coverage
path = [params.quast.report_tag, "0", "Avg. coverage depth"]
* Use the path below to use quasts base_pairs/genome length for coverage
path = [params.coverage_calc_fields.auto_cov]
*/
path = [params.coverage_calc_fields.fixed_cov]
coerce_type = 'Float'
compare_fields = ['min_average_coverage']
comp_type = 'ge'
on = true
low_msg = "Depth of coverage from assembly is lower than than expected. A top-up run is likely needed."
}
metagenomic {
path = [params.mash_meta.report_tag]
coerce_type = 'Bool'
compare_fields = []
comp_type = "bool"
on = false
}
n50_value {
path = [params.quast.report_tag, "0", "N50"]
coerce_type = 'Integer'
compare_fields = ['min_n50', 'max_n50']
comp_type = "range"
on = true
low_msg = "N50 value is low, this could be due to many reasons involving contamination, poor template quality or insufficient template quantity. Reisolation and reseqeuncing may be needed."
high_msg = "N50 value is high, this is likely a good thing if you have fewer contigs than expected."
}
nr_contigs {
path = [params.quast.report_tag, "0", params.quast.contigs_field]