forked from LANL-Bioinformatics/EDGE
-
Notifications
You must be signed in to change notification settings - Fork 3
/
config_template.txt
executable file
·142 lines (124 loc) · 3.22 KB
/
config_template.txt
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
[Download SRA]
DoSRADownload=0
## SRA accessions ByrRun, ByExp, BySample, ByStudy
SRA_id=SRX674271
[Count Fastq]
DoCountFastq=auto
[Quality Trim and Filter]
## boolean, 1=yes, 0=no
DoQC=1
##Targets quality level for trimming
q=5
##Trimmed sequence length will have at least minimum length
min_L=50
##Average quality cutoff
avg_q=0
##"N" base cutoff. Trimmed read has more than this number of continuous base "N" will be discarded.
n=1
##Low complexity filter ratio, Maximum fraction of mono-/di-nucleotide sequence
lc=0.85
## Trim reads with adapters or contamination sequences
adapter=/PATH/adapter.fasta
## phiX filter, boolean, 1=yes, 0=no
phiX=0
## Cut # bp from 5 end before quality trimming/filtering
5end=0
## Cut # bp from 3 end before quality trimming/filtering
3end=0
[Host Removal]
## boolean, 1=yes, 0=no
DoHostRemoval=1
## Use more Host= to remove multiple host reads
Host=/PATH/all_chromosome.fasta
similarity=90
[Assembly]
## boolean, 1=yes, 0=no
DoAssembly=1
#Bypass assembly and use pre-assembled contigs
assembledContigs=
minContigSize=200
## spades or idba_ud
assembler=idba_ud
idbaOptions="--pre_correction --mink 31"
## for spades
singleCellMode=
pacbioFile=
nanoporeFile=
[Reads Mapping To Contigs]
# Reads mapping to contigs
DoReadsMappingContigs=auto
[Reads Mapping To Reference]
# Reads mapping to reference
DoReadsMappingReference=0
bowtieOptions=
# reference genbank or fasta file
reference=
MapUnmappedReads=0
[Reads Taxonomy Classification]
## boolean, 1=yes, 0=no
DoReadsTaxonomy=1
## If reference genome exists, only use unmapped reads to do Taxonomy Classification. Turn on AllReads=1 will use all reads instead.
AllReads=0
enabledTools=gottcha-genDB-b,gottcha-speDB-b,gottcha-strDB-b,gottcha-genDB-v,gottcha-speDB-v,gottcha-strDB-v,metaphlan,bwa,kraken_mini
[Contigs Mapping To Reference]
# Contig mapping to reference
DoContigMapping=auto
## identity cutoff
identity=85
MapUnmappedContigs=0
[Variant Analysis]
DoVariantAnalysis=auto
[Contigs Taxonomy Classification]
DoContigsTaxonomy=1
[Contigs Blast]
DoBlast=0
BLAST_nr_DB=/PATH/nr/
BLAST_nt_DB=/PATH/nt/
[Contigs Annotation]
## boolean, 1=yes, 0=no
DoAnnotation=1
# kingdom: Archaea Bacteria Mitochondria Viruses
kingdom=Bacteria
contig_size_cut_for_annotation=700
## support tools: Prokka or RATT
annotateProgram=Prokka
annotateSourceGBK=
[ProPhage Detection]
DoProPhageDetection=1
[SNP Phylogeny]
DoSNPtree=1
## Availabe choices are Ecoli, Yersinia, Francisella, Brucella, Bacillus
SNPdbName=Ecoli
## List of genome name from NCBI genomes see $EDGE/edge_ui/data/Ref_list.json
SNPGenomes=
SNPGenomesFiles=
## A refrence genoem from above two options for reads/contigs mapping
SNPrefGenome=<TMPL_VAR NAME=edge-phylo-ref-select-ref>
## FastTree or RAxML
treeMaker=FastTree
## SRA accessions ByrRun, ByExp, BySample, ByStudy
SNP_SRA_ids=
[Primer Validation]
DoPrimerValidation=1
maxMismatch=1
# primer fasta file
primer=
[Primer Adjudication]
## boolean, 1=yes, 0=no
DoPrimerDesign=0
## desired primer tm
tm_opt=59
tm_min=57
tm_max=63
## desired primer length
len_opt=18
len_min=20
len_max=27
## reject primer having Tm < tm_diff difference with background Tm
tm_diff=5
## display # top results for each target
top=5
[Generate JBrowse Tracks]
DoJBrowse=1
[HTML Report]
DoHTMLReport=1