-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathconfig.cfg
265 lines (220 loc) · 10.5 KB
/
config.cfg
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
## Config file of iseq. Comments lines start with. I suggested you just copy and modify this file ##
[tools_path]
# Java Environment, download from http://www.oracle.com/technetwork/java/javase/downloads/,
# Mutect need use 1.7, gatk(>=3.7) use 1.8
java=/path/jdk1.8.0_101/bin/java
jdk_17=/path/jdk1.7.0_79
jdk_18=/path/jdk1.8.0_101
# Perl Environment, download from https://www.perl.org/get.html
perl=/path/perl
# R Environment, download from https://www.r-project.org/
R=/path/R
Rscript=/path/Rscript
# GATK, Genome Analysis Toolkit,
# download from https://software.broadinstitute.org/gatk/ or
# use BioInstaller::install.bioinfo('gatk', '/path/gatk')
gatk=/home/ljf/opt/caller/gatk/gatk3.7/GenomeAnalysisTK.jar
# Torrent caller, a ion torrent platform variant caller,
# download from http://updates.iontorrent.com/tvc_standalone/ or
# use BioInstaller::install.bioinfo('tvc', '/path/tvc')
tvc=/path/tvc-5.0.3-CentOS_7.1.1503_x86_64-binary/bin/variant_caller_pipeline.py
# LoFreq, a fast and sensitive variant caller, download from http://csb5.github.io/lofreq/installation/ or
# use BioInstaller::install.bioinfo('lofreq', '/path/lofreq')
lofreq=/path/lofreq_star-2.1.2/bin/lofreq
# LoFreq, a fast and sensitive variant caller, download from http://csb5.github.io/lofreq/installation/ or
# use BioInstaller::install.bioinfo('pindel', '/path/pindel')
pindel_dir=/path/pindel/
# Bwa, a software package for mapping low-divergent sequences against a large reference genome,
# download from http://bio-bwa.sourceforge.net/ or
# use BioInstaller::install.bioinfo('bwa', '/path/bwa')
bwa=/path/bwa
# STAR, a RNA-seq aligner,
# download from https://github.com/alexdobin/STAR or
# use BioInstaller::install.bioinfo('star', '/path/star')
star=/opt/bin/STAR/bin/Linux_x86_64/STAR
# Bowtie, an ultrafast, memory-efficient short read aligner,
# download from http://bowtie-bio.sourceforge.net/index.shtml or
# conda install bowtie or
# use BioInstaller::install.bioinfo('bowtie', '/path/bowtie')
bowtie=/path/bowtie/bowtie1.1.2/bowtie
bowtie_build=/path/bowtie/bowtie1.1.2/bowtie-build
bowtie2=/path/bowtie/bowtie2-2.2.6/bowtie2
bowtie2build=/path/bowtie/bowtie2-2.2.6/bowtie2-build
# Tophat, a fast splice junction mapper for RNA-Seq reads,
# download from http://ccb.jhu.edu/software/tophat/index.shtml or
# conda install tophat or
# use BioInstaller::install.bioinfo('tophat', '/path/tophat')
tophat=/path/tophat-2.1.0.Linux_x86_64/tophat
# TMAP, torrent mapping alignment program, download from https://github.com/iontorrent/TS/tree/master/Analysis/TMAP or
# use BioInstaller::install.bioinfo('tmap', '/path/tmap')
tmap=/path/TMAP/tmap
# samtools, tools (written in C using htslib) for manipulating next-generation sequencing data,
# download from https://github.com/samtools/samtools or
# use BioInstaller::install.bioinfo('samtools', '/path/samtools')
samtools=/opt/bin/samtools/samtools
# Picard, A set of command line tools (in Java) for manipulating
# high-throughput sequencing (HTS) data and formats such as SAM/BAM/CRAM and VCF,
# download from https://github.com/broadinstitute/picard or
# use BioInstaller::install.bioinfo('picard', '/path/picard')
picard=/path/picard/build/libs/picard.jar
# Mutect, a method developed at the Broad Institute for the reliable and
# accurate identification of somatic point mutations in next generation sequencing data of cancer genomes,
#download from http://archive.broadinstitute.org/cancer/cga/mutect or
# use BioInstaller::install.bioinfo('mutect', '/path/Mutect')
mutect=/path/muTect-1.1.7.jar
# VarScan, a tool that detects variants (SNPs and indels) in next-generation sequencing data,
# download from http://massgenomics.org/varscan or
# use BioInstaller::install.bioinfo('varscan2', '/path/VarScan')
varscan=/path/VarScan.v2.4.3.jar
# freebayes, bayesian haplotype-based genetic polymorphism discovery and genotyping,
# download from https://github.com/ekg/freebayes or
# conda install freebayes or
# use BioInstaller::install.bioinfo('VarScan', '/path/VarScan')
freebayes=/opt/bin/freebayes/bin/freebayes
# bcftools, containing all the vcf* commands which previously lived in the htslib repository,
# download from https://github.com/samtools/bcftools or
# conda install bcftools or
# use BioInstaller::install.bioinfo('bcftools', '/path/bcftools')
bcftools=/path/bcftools
# tabix, part of htslib, fast retrieval of sequence features from generic TAB-delimited files
# conda install htslib or
# use BioInstaller::install.bioinfo('htslib', '/path/htslib')
tabix=/path/htslib/tabix
# ANNOVAR, an efficient software tool to utilize update-to-date information to
# functionally annotate genetic variants detected from diverse genomes,
# download from http://annovar.openbioinformatics.org/en/latest/ or
# use BioInstaller::install.bioinfo('annovar', '/path/annovar_dir')
annovar_dir=/path/annovar/
# vcftools, a program package designed for working with VCF files,
# such as those generated by the 1000 Genomes Project,
# download from https://github.com/vcftools/vcftools or
# conda install vcftools or
# use BioInstaller::install.bioinfo('vcftools', '/path/vcftools')
vcftools=/path/vcftools/bin/vcftools
# fastqc, a quality control tool for high throughput sequence data,
# download from http://www.bioinformatics.babraham.ac.uk/projects/fastqc/ or
# use BioInstaller::install.bioinfo('fastqc', '/path/fastqc')
fastqc=/path/fastqc/fastqc
# prinseq,
# download from http://edwards.sdsu.edu/cgi-bin/prinseq/prinseq.cgi or
# use BioInstaller::install.bioinfo('prinseq', '/path/prinseq')
prinseq=/path/prinseq-lite-0.20.4/
[extra_files]
# reference genome, such as hg19.fa, mm10.fa
reffa=/path/hg19.fa
# intervals is a bed format file to be analysis
intervals=/path/cds_final_hg19.bed
# cosmic is a VCF format file that be download from http://archive.broadinstitute.org/cancer/cga/mutect
cosmic=/path/b37_cosmic_v54_120711_chr.vcf
# known_transcript is a GTF format file indicating known transcript
known_transcript=/u1/sd/annotation/refseq_hg19_07292013.gtf
# known_sites_vcf is GATK bundle files
known_sites_vcf=/path/reference/broad/dbsnp_138.hg19.vcf:/path/reference/broad/Mills_and_1000G_gold_standard.indels.hg19.sites.vcf
# tvc_params_json is the tvc JSON format parameters file
tvc_params_json=/opt/bin/tvc-5.0.3-CentOS_7.1.1503_x86_64-binary/share/TVC/pluginMedia/parameter_sets/ocp_somatic_lowstringency_pgm_parameters.json
# lofreq_dbsnp and dbnsnp file is the common SNP file (lofreq_dbsnp is gzip format)
lofreq_dbsnp=/u6/home/ljf/db/dbsnp_147.hg19.common.vcf.gz
dbsnp=/u6/home/ljf/db/dbsnp_147.hg19.common.vcf
[preprocess]
# genome_indexer can be used to control the genomeindex mode behaviour
# supported: bwa, star, bowtie, bowtie2, tmap
# only exists in mapper be run
genome_indexer=bwa,star,bowtie,bowtie2
# mapper can be used to control the mapping softwares using in analysis
mapper=bwa
[variantcaller]
# caller can be used to control the mutation calling softwares using in analysis
caller=tvc,varscan,mutect,HaplotypeCaller,UnifiedGenotyper,lofreq
# *_filtration can be used to control the filter function for caller
unifiedgenotyper_filtration=common_filter
lofreq_filtration=
varscan_filtration=
haplotypecaller_filtration=common_filter
mutect_filtration=
[reffa_class_sets]
# reffa_class_sets can be used to control the class ReffaFile method
reffafile_generate_dict_extra=
reffafile_tmap_index_extra=
reffafile_bowtie2_index_extra=
reffafile_bowtie_index_extra=
reffafile_star_index_pass1_extra=
reffafile_star_index_pass2_extra=
reffafile_bwa_index_extra=
reffafile_bwa_index_thread=30
reffafile_star_index_thread=30
reffafile_bowtie_index_thread=30
reffafile_bowtie2_index_thread=30
reffafile_tophat_index_thread=30
[fastq_class_sets]
# fastq_class_sets can be used to control the class FastqFile method
fastqfile_bwa_mapping_extra=
fastqfile_star_mapping_extra=
fastqfile_bowtie2_mapping_extra=--chunkmbs 2000 -n 2 -l 28 -e 70
fastqfile_bowtie_mapping_extra=
fastqfile_tophat_mapping_extra=
fastqfile_tmap_mapping_extra=-v stage1 map1 map2 map3
fastqfile_fastqc_extra=
fastqfile_bwa_mapping_thread=30
fastqfile_star_mapping_thread=30
fastqfile_bowtie2_mapping_thread=30
fastqfile_bowtie_mapping_thread=30
fastqfile_tophat_mapping_thread=30
fastqfile_tmap_mapping_thread=30
[bam_class_sets]
# bam_class_sets can be used to control the class BamFile method
bamfile_mpileup_extra=-q 1
bamfile_index_extra=
bamfile_sort_extra=
bamfile_RGID=1
bamfile_RGLB=Jhuanglab
bamfile_RGPL=ILLUMINA
bamfile_RGPU=Hiseq
bamfile_split_ntrim_extra=-RMQF 255 -RMQT 60 -rf ReassignOneMappingQuality -U ALLOW_N_CIGAR_READS
bamfile_contig_reorder_extra=
bamfile_add_read_group_extra=
bamfile_mark_duplicates_extra=
bamfile_recalibration_extra=
bamfile_indel_realigner_extra=
bamfile_realigner_target_creator_extra=
bamfile_print_reads_extra=
bamfile_haplotype_caller_extra_rna=--unsafe -stand_call_conf 20.0 -stand_emit_conf 20.0 -dontUseSoftClippedBases
bamfile_haplotype_caller_extra_dna=--unsafe
bamfile_unifiedgenotyper_caller_extra=-dcov 1000 --unsafe -glm BOTH
bamfile_mutect_caller_extra=--unsafe
bamfile_varscan_caller_extra_somatic=
bamfile_varscan_caller_extra_germline=--min-var-freq 0.01
bamfile_torrent_caller_extra=
bamfile_lofreq_caller_extra_germline=
bamfile_lofreq_caller_extra_somatic=
bamfile_freebayes_caller_extra=
bamfile_index_thread=30
bamfile_sort_thread=30
bamfile_unifiedgenotyper_caller_thread=30
bamfile_realigner_target_creator_thread=30
bamfile_torrent_caller_thread=30
bamfile_lofreq_caller_thread=30
bamfile_pindel_caller_thread=30
bamfile_pindel_genome_name=hg19
bamfile_pindel_genome_date=2012
bamfile_pindel_insertsize=400
[vcf_class_sets]
# vcf_class_sets can be used to control the class VcfFile method
vcffile_annovar_extra=-nastring . -csvout
[csv_class_sets]
# csv_class_sets can be used to control the class CsvFile method
csvfile_mpileup_extra=-q 1
[annovar_sets]
annovar_buildver=hg19
annovar_flag=-protocol refGene,cytoBand,genomicSuperDups,esp6500siv2_all,1000g2015aug_all,1000g2015aug_afr,1000g2015aug_eas,1000g2015aug_eur,snp138,avsnp142,avsnp144,avsnp147,ljb26_all,cosmic70,cosmic81 -operation g,r,r,f,f,f,f,f,f,f,f,f,f,f,f
annovar_colnames=Chr,Start,End,Ref,Alt,Func.refGene,Gene.refGene,GeneDetail.refGene,ExonicFunc.refGene,AAChange.refGene,cytoBand,snp138,avsnp142,avsnp144,avsnp147,SIFT_score,SIFT_pred,Polyphen2_HDIV_score,Polyphen2_HDIV_pred,cosmic70,cosmic81
[others]
# gatk tmp dir
gatk_tmp_dir=~/tmp/gatk_tmp
# tvc tmp dir
tvc_tmp_dir=~/tmp/tvc_tmp
# java_max_mem can be used control the java max memory be used
java_max_mem=128g
# freq_exon_only can be used to control the mutation stat step
# 1, only stat exon region mutation sites
# 0, stat all sites
freq_exon_only=1