-
Notifications
You must be signed in to change notification settings - Fork 4
/
config.yaml
88 lines (77 loc) · 2.84 KB
/
config.yaml
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
### default args ###
# keep run mapping bam file and reference index files.
# cache these files, so you do not need to re-run some analysis when you add more sequening reads
keep_internal: false
# keep dicarded reads (untrimmed, too-short, unmapped...), for debugging purpose.
# Most of the time, you do not need these files. Set it as `false` to save storage.
keep_discarded: false
# only keep reads that have a p7 adapter in the read1, which is important for inline barcode detection
# If inline barcode is added, this arg will be true, otherwise it will be false
trimmed_only: auto
# Whether remove atypical adapter
trim_p5: false
# Whether remove long polyA sequence
trim_polyA: false
# Whether clip match on contamination / gene reference
greedy_mapping: false
# speed up bowtie2 mapping, might lead to some FP, but can speed up significantly
speedy_mapping: false
# defualt barcode scheme
barcode: '-NNNNN'
# If the library is forward_stranded, true mean the R1 is in the same orientation as RNA
forward_stranded: true
### build in args ###
# if you change build in args, add the whole block rather than some records!!
cutoff:
## processing reads
# STAR `outFilterMatchNminOverLread`
min_match_prop: 0.8
## calling sites
# prefilter sites show >= x gaps in total among all samples in each group
min_group_gap: 5
# prefilter sites show >= x sequencing coverage in total among all samples in each group
min_group_depth: 10
# prefilter sites show >= x deletion ratio among all samples in each group
min_group_ratio: 0.01
# only analysis putative sites that show pass prefilter in >= x groups
min_group_num: 1
calibration_curves: /pipeline/calibration_curves.tsv
# only call gap sites within selected region
select_region:
- genes
- genome
# All the cutoff in these filter are **greater or equal to**
group_filter:
combine_group_input: true
min_passed_group: 1
min_treated_depth: 20
min_input_depth: 20
min_treated_gap: 5
min_treated_ratio: 0.02
min_treated_fraction: 0.02
min_fold_ratio: 2
max_p_value: 0.0001
adapter:
# 20nt
p7: AGATCGGAAGAGCACACGTC
p5: AGTTCTACAGTCCGACGATC
path:
fastp: /pipeline/micromamba/bin/fastp
cutadapt: /pipeline/micromamba/bin/cutadapt
bgzip: /pipeline/micromamba/bin/bgzip
bowtie2: /pipeline/micromamba/bin/bowtie2
bowtie2Build: /pipeline/micromamba/bin/bowtie2-build
star: /pipeline/micromamba/bin/STAR
samtools: /pipeline/micromamba/bin/samtools
bedtools: /pipeline/micromamba/bin/bedtools
multiqc: /pipeline/micromamba/bin/multiqc
umicollapse: /bin/umicollapse.jar
joinFastq: /pipeline/bin/joinFastq
rcFastq: /pipeline/bin/rcFastq
delfilter: /pipeline/bin/deletionFilter
samfilter: /pipeline/bin/samFilter
cpup: /pipeline/bin/cpup
adjustGap: /pipeline/bin/adjustGap
realignGap: /pipeline/bin/realignGap
filterGap: /pipeline/bin/filterGap
pickSites: /pipeline/bin/pickSites.py