-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathconfig.yaml
53 lines (46 loc) · 2.1 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
# This file allows you to configure the workflow to suit your needs.
# Some things you can customize are:
# - Fill in the name of your reference genome [required]
# - Parameters for splitting the reference genome into regions to process in parallel
# - Filename for those regions to be stored
# - How many threads to use for fastq-dumping, trimming, aligning, and variant calling
# - How much memory samtools sort is allowed to use
# Tab-delimited file of unit and sample info [required]
# See README for how to create this file.
units: "units.tsv"
# Please fill in the path to your reference genome assembly [required].
genome: "data/genome/yourgenome.fa"
# In order to speed up variant calling, the reference genome will be
# split into small chunks that can be processed in parallel.
# To avoid splitting in the middle of a contig, we want to split where there are
# gaps in the assembly -- for example, 4000 or more N's in a row.
intervals:
# Minimum number of N's in a row to split into separate regions
gap_length: 4000
# Filename for the workflow should store list of regions
file: "data/intervals/intervals.bed"
# If you have raw .sra files from NCBI Sequence Read Archive (e.g., from prefetch),
# the workflow can convert them to fastq for you.
# If you already have fastq files, put them in data/reads/ and this step will be skipped.
fastq_dump:
threads: 8
# Folder where you downloaded .sra files
sra_location: "data/sra/"
# Parameters for cutadapt and cutadapt_pe rules.
cutadapt:
threads: 8
# 3' adapter sequence to remove from all reads.
# See cutadapt documentation for -a and -A options.
adapter: "AGATCGGAAGAGC"
# Base quality trimming cutoff. See cutadapt documentation for -q option.
qual: 10
# Parameters for align rule.
align:
# Cores that BWA will use for each instance of rule align
threads: 12
# Maximum memory per thread for samtools sort; suffix K/M/G recognized
sort_mem: 2G
# Parameters for call_variants rule.
freebayes:
# Freebayes command-line options
options: "--hwe-priors-off --min-mapping-quality 41 --min-base-quality 20 --genotype-qualities"