forked from bmds-lab/Crackling
-
Notifications
You must be signed in to change notification settings - Fork 0
/
config.ini
177 lines (138 loc) · 5.1 KB
/
config.ini
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
; Welcome to the sample configuration file for HaploCrackling.
; https://github.com/bmds-lab/Crackling-phased
[general]
; Provide an identifier for this configuration. HaploCrackling will use it to
; prefix file names.
name = marmoset
; Indicate which level of optimisations that you wish to use.
; Options are:
; - ultralow Assess everything.
;
; - low: All efficiency and specificity results are calculated for those
; guides detected as unique via the initial regex test.
;
; - medium: All efficiency and specificity results are calculated for those
; guides detected as unique via the initial regex test.
; Specificity is only assessed for efficient guides.
;
; - high: Minimal results are calculated.
; Default: high
optimisation = high
[consensus]
; How many methods need to agree to deem that a guide is efficient?
; Ensure that this value is less than or equal to the number of methods
; that you enable below.
; Default: 2;
n = 2
; Enable/disable methods below. Use True or False.
; Default: True, True, True
mm10db = True
sgrnascorer2 = True
chopchop = True
[input]
; The input sequences to analyse.
; This is parsed using glob.
; https://docs.python.org/3/library/glob.html
; You can provide
; - A filename
; - A directory
; - A path using wildcards
exon-sequences = /mnt/c/git/Crackling-phased/data/K562/chromosomes/
; VCF file
vcf-file = /mnt/c/git/Crackling-phased/data/K562/phased_variants.vcf
; The ISSL index
offtarget-sites = /mnt/c/git/Crackling-phased/data/K562/offtargets.issl
; A GFF annotation for the input genome
; This is used as in an optional post-processing step.
gff-annotation = /sample.gff
; A Bowtie2 index for the input genome
bowtie2-index = /mnt/c/git/Crackling-phased/data/K562/bt.idx
; Batch size to split the input file.
; Extracting the initial list of guides can quickly exhaust the available memory.
; To address this issues we process the guides in batches.
; Default = 5000000; (5 million)
batch-size = 5000000
[output]
; A directory to write output and temporary files to. Ensure this dir exists.
dir = /mnt/c/git/Crackling-phased/data/output
; The default name for the final results file.
; This is prefixed with the name specified in General.
; Default: guides.txt
filename = guides.txt
; The delimiter to use in the results file.
; Default: ,
delimiter = ,
[offtargetscore]
; Enable or disable specificity evaluation (Bowtie2 and ISSL)
; Default: True
enabled = True
; ISSL executable path
; Default: ./isslScoreOfftargets
binary = /mnt/c/git/Crackling-phased/bin/isslScoreOfftargets
; Which scoring method to use?
; Options: mit, cfd, and, or, avg
; mit - Fail when MIT drops below score-threshold
; cfd - Fail when CFD drops below score-threshold
; and - Fail when CFD and MIT drops below score-threshold
; or - Fail when CFD or MIT drops below score-threshold
; avg - Fail when the average of CFD and MIT drops below score-threshold
; Default: and
method = and
; Number of threads to allocate ISSL
; Default: 128
threads = 128
; ISSL can consume a large volume of memory when processing millions of
; sequences. Specify how many guides to assess for each instance of ISSL
; that we call. Note: we run ISSL in multi-threaded mode but only call one
; ISSL process at a time.
; Setting this to zero causes all guides to be processed at once.
; Default: 5000000 (5 million)
page-length = 5000000
; The lower-bound threshold for the off-target score. If the score drops below
; this value, then we stop.
; Default: 75
score-threshold = 75
; The maximum number of mismatches. The index must be built with the same value.
; Default 4
max-distance = 4
[sgrnascorer2]
; The sgRNAScorer 2.0 model.
; If you experience an error, try retraining the model. There are scripts to do
; this; found in the supplementary folder of the GitHub repository.
; Default: model-py3.txt
model = /mnt/c/git/Crackling-phased/src/crackling/utils/data/model-py3.txt
; A positive score indicates the guide is efficient.
; Default: 0
score-threshold = 0
[bowtie2]
; Bowtie2 executable path
binary = bowtie2
; Number of threads to allocate Bowtie2
; Default: 128
threads = 128
; Bowtie can consume a large volume of memory when processing millions of
; sequences. Specify how many guides to assess for each instance of Bowtie that
; we call. Note: we run Bowtie in multi-threaded mode but only call one Bowtie
; process at a time.
; Setting this to zero causes all guides to be processed at once.
; Default: 5000000 (5 million)
page-length = 5000000
[rnafold]
; RNAfold executable path
binary = RNAfold
; Number of threads to allocate RNAfold
; Default: 128
threads = 128
; RNAfold can consume a large volume of memory when processing millions of
; sequences. Specify how many guides to assess for each instance of RNAfold
; that we call. Note: we run RNAfold in multi-threaded mode but only call one
; RNAfold process at a time.
; Setting this to zero causes all guides to be processed at once.
; Default: 5000000 (5 million)
page-length = 5000000
; Secondary structure lower-bound energy threshold
; Default: -30
low_energy_threshold = -30
; Secondary structure upper-bound energy threshold
; Default: -18
high_energy_threshold = -18