-
Notifications
You must be signed in to change notification settings - Fork 5
/
config
executable file
·290 lines (254 loc) · 8.47 KB
/
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
# Set which tools to use in pipeline:
[pipeline]
# Options for Aligner:bwa / bowtie
aligner: bwa
# Options for variant_caller: samtools / gatkhaplotypecaller / freebayes
variant_caller: samtools
[scheduler]
resources: nodes=1:ppn=4,pmem=4000mb,walltime=250:00:00
large_resources: nodes=1:ppn=12,mem=47gb,walltime=250:00:00
email: apirani@med.umich.edu
queue: flux
flux_account: esnitkin_flux
notification: a
[pbs]
resources: nodes=1:ppn=4,pmem=4000mb,walltime=250:00:00
large_resources: nodes=1:ppn=12,mem=47gb,walltime=250:00:00
email: apirani@med.umich.edu
queue: flux
flux_account: esnitkin0
notification: a,b,e
[slurm]
resources: --nodes=1 --ntasks=1 --cpus-per-task=1 --mem=5g --time=125:00:00
large_resources: --nodes=1 --ntasks-per-node=12 --mem=47000mb --time=250:00:00
email: apirani@med.umich.edu
partition: standard
flux_account: esnitkin99
notification: FAIL,REQUEUE
# Set command line Parameters for individual tools used by snpkit
# Trimmomatic
[Trimmomatic]
trimmomatic_bin: //
adaptor_filepath: /home/apirani/.conda/envs/variantcalling_clone/share/trimmomatic-0.39-1/adapters/combined_Adaptors.fa
seed_mismatches: 2
palindrome_clipthreshold: 30
simple_clipthreshold: 10
minadapterlength: 8
#change this to true and see the effect on alignment
keep_both_reads: true
window_size: 4
window_size_quality: 20
minlength: 40
headcrop_length: 0
colon: :
targetlength: 125
crop_length: 40
f_p: forward_paired.fq.gz
f_up: forward_unpaired.fq.gz
r_p: reverse_paired.fq.gz
r_up: reverse_unpaired.fq.gz
[bwa]
bwa_bin: //
cores: 8
base_cmd: bwa
algorithm: mem
index: index
RG_header: -R
Mark_splithits: -M
[bowtie]
bowtie_bin: //
cores: 8
build_cmd: bowtie2-build
align_cmd: bowtie2
parameters: -k 1 --non-deterministic --end-to-end
[samtools]
samtools_bin: //
base_cmd: samtools
#minimum mapping quality
#change parameter S to -t SP and D to -t DP
mpileup_parameters: -ug -f
faiindex: faidx
#-q30 -B -E -C50
[bcftools]
bcftools_bin: //
base_cmd: bcftools
call_parameters: -vg
[picard]
picard_bin: //
base_cmd: picard
[gatk]
gatk_bin: //
base_cmd: gatk
haplotype_parameters: HaplotypeCaller
[vcftools]
vcftools_bin: //
tabix_bin: //
[qualimap]
qualimap_bin: //
base_cmd: qualimap
[bedtools]
bedtools_bin: //
base_cmd: bedtools
version_for_coverage: /version_for_coverage/
[bioawk]
bioawk_bin: //
base_cmd: bioawk
[fasttree]
fasttree_bin: //
#For Multithread fasttree; use FastTreeMP executable file
base_cmd: FastTree
[raxml]
raxml_bin: //
openmpi_bin: //
# Other raxml executable available to use: raxmlHPC-PTHREADS,raxmlHPC-PTHREADS-SSE3,raxmlHPC-SSE3
base_cmd: raxmlHPC-HYBRID-SSE3
parameters: -f a -x 12345 -p 12345 -N autoMRE -m GTRCAT -T 20
[iqtree]
iqtree_bin: //
base_cmd: iqtree
parameters: -nt AUTO -bb 1000 -m GTR+G+ASC
[gubbins]
# Change this path to wherever gubbins is located/installed. Right now, installed using conda from anaconda3 package installed in bin_group.
gubbins_bin: //
base_cmd: run_gubbins.py
[mummer]
mummer_bin: //
nucmer_base_cmd: nucmer
min_tandem_repeat_length: 20
percent_id: 95
[SNP_filters]
filter_criteria: snpkit
[snpkit]
avg_depth: no
# If AVG_DEPTH is yes, the below DP threshold will be ignored. Instead, LOW_DEPTH and HIGH_DEPTH filter parameter will be used.
# Filter variants with Depth less than the below threshold
dp: 9
# A value of 2 means that regions with less than half of the average coverage of the entire genome will fail
low_depth: 2
# A value of 5 means that regions with 5x depth greater than the average coverage will fail
high_depth: 5
# Filter variants with FQ(Consensus Quality) greater than the below threshold
fq: 0.025
fq2: 0.025
# Filter variants with MQ(Root Mean Square Quality) less than the below threshold
mq: 50
# Filter variants with Variant QUAL less than the below threshold
qual: 100
# Filter variants with GATK QualbyDepth QD parameter; filter less than the below threshold. Currently, being used for Indel SNPS only.
qd: 2.00
# Filter variants with AF1 less than the below threshold
af: 0.900
# Filter Variants that are proximate to each other within this number of range. To turn this off, use 0(zero).
prox: 0
[gatk_haplotypecaller_filters]
avg_depth: no
# If AVG_DEPTH is yes, the below DP threshold will be ignored. Instead, LOW_DEPTH and HIGH_DEPTH filter parameter will be used.
# Filter variants with Depth less than the below threshold
dp: 9
# A value of 2 means that regions with less than half of the average coverage of the entire genome will fail
low_depth: 2
# A value of 5 means that regions with 5x depth greater than the average coverage will fail
high_depth: 5
# FQ not represented in GATK Haplotype caller vcf format. Instead use AF.
# Filter variants with MQ(Root Mean Square Quality) less than the below threshold
mq: 50
# Filter variants with Variant QUAL less than the below threshold
qual: 2
# Filter variants with AF1 less than the below threshold
af: 0.9
# Filter Variants that are proximate to each other within this number of range. To turn this off, use 0(zero).
prox: 0
[rna_filters]
avg_depth: no
# If AVG_DEPTH is yes, the below DP threshold will be ignored. Instead, LOW_DEPTH and HIGH_DEPTH filter parameter will be used.
# Filter variants with Depth less than the below threshold
dp: 3
# A value of 2 means that regions with less than half of the average coverage of the entire genome will fail
low_depth: 2
# A value of 5 means that regions with 5x depth greater than the average coverage will fail
high_depth: 5
# Filter variants with FQ(Consensus Quality) greater than the below threshold
fq: 0.00
fq2: 0.00
# Filter variants with MQ(Root Mean Square Quality) less than the below threshold
mq: 50
# Filter variants with Variant QUAL less than the below threshold
qual: 0
# Filter variants with AF1 less than the below threshold
af: 0.9
# Filter Variants that are proximate to each other
prox: 1
[contamination_filters]
avg_depth: no
# If AVG_DEPTH is yes, the below DP threshold will be ignored. Instead, LOW_DEPTH and HIGH_DEPTH filter parameter will be used.
# Filter variants with Depth less than the below threshold
dp: 3
# A value of 2 means that regions with less than half of the average coverage of the entire genome will fail
low_depth: 2
# A value of 5 means that regions with 5x depth greater than the average coverage will fail
high_depth: 5
# Filter variants with FQ(Consensus Quality) greater than the below threshold
fq: -20.00
fq2: -20.00
# Filter variants with MQ(Root Mean Square Quality) less than the below threshold
mq: 50
# Filter variants with Variant QUAL less than the below threshold
qual: 0
# Filter variants with AF1 less than the below threshold
af: 1
# Filter Variants that are proximate to each other
prox: 1
[functional_filters]
apply_functional_filters: yes
find_phage_region: yes
find_repetitive_region: yes
mask_region: no
mask_file: mask.txt
mobile_elements: yes
apply_to_calls: yes
##SNP annotations
[snpeff]
snpeff_bin: //
base_cmd: snpEff
snpeff_parameters: -d -no-downstream -no-upstream
prebuild: no
db:
dataDir: /data/
########################################################################################################################
# Reference Genome to be used for pipeline
# Set path for already indexed reference genome
[index]
# Name of reference genome fasta file.
Ref_Name: index.fasta
# path to the reference genome fasta file.
Ref_Path: /path-to/reference/index/
# Name of the reference genome. Provide this value with -index_name argument.
[KPNIH1]
# Name of reference genome fasta file.
Ref_Name: KPNIH1.fasta
# path to the reference genome fasta file.
Ref_Path: /nfs/turbo/umms-esnitkin/data_sharing/reference/KPNIH1/
[MRSA_USA_300]
# Name of reference genome fasta file.
Ref_Name: MRSA_USA_300.fasta
# path to the reference genome fasta file.
Ref_Path: /nfs/turbo/umms-esnitkin/data_sharing/reference/MRSA_USA_300/
[CDIFF_630_ncbi]
# Name of reference genome fasta file.
Ref_Name: cdiff_630.fasta
# path to the reference genome fasta file.
Ref_Path: /nfs/turbo/umms-esnitkin/data_sharing/reference/CDIFF_630_ncbi/
[Ecoli_NCTC13441_ST131]
# Name of reference genome fasta file.
Ref_Name: Ecoli_NCTC13441_ST131.fasta
# path to the reference genome fasta file.
Ref_Path: /nfs/turbo/umms-esnitkin/data_sharing/reference/Ecoli_NCTC13441_ST131/
[cdiff_630]
# Name of reference genome fasta file.
Ref_Name: cdiff_630.fasta
# path to the reference genome fasta file.
Ref_Path: /nfs/turbo/umms-esnitkin/data_sharing/reference/CDIFF_630/
# This setting is deprecated. snpkit uses conda environments for
# Set bin folder path. Please make sure all the executables are placed in bin folder. Also make sure the path for individual tools are correct.
[bin_path]
binbase: