Skip to content
Snippets Groups Projects
Commit 7d13fd2c authored by Valentina Galata's avatar Valentina Galata
Browse files

updated ganges config.yaml

parent ee9d2237
No related branches found
No related tags found
1 merge request!76Merge "cleanup" branch with "master" branch
############################################################
# STEPS
# Pipeline steps to be done: ["preprocessing", "assembly", "mapping", "annotation", "analysis", "taxonomy"]
steps: ["preprocessing", "assembly", "mapping", "annotation", "analysis", "taxonomy"]
############################################################
# INPUT
# working directory: will contain the results (should be writeable)
work_dir: "/scratch/users/sbusi/ONT/ganges"
# Paths WITHIN the working directory
# directory containing required DBs (should be writeable)
db_dir: "dbs"
# results directory (will be created in work_dir)
results_dir: "results"
# Data paths: Use absolute paths or paths relative to the working directory !!!
data:
# Meta-genomics
metag:
sr:
r1: "data/sr/ERR2612536/ERR2612536_1.fastq.gz"
r2: "data/sr/ERR2612536/ERR2612536_2.fastq.gz"
ont:
# List of directories containing FAST5 files
dirs: ["data/lr/SO_6051_metagenome"] # leave empty if no data, i.e. []
# List of FAST5 files
files: [] # leave empty if no data, i.e. []
# FastQ: if given NO basecalling will be done !!!
fastq: "" # leave empty if no data, i.e. ""
# Meta-transcriptomics
metat:
sr:
r1: "" # leave empty if no data, i.e. ""
r2: "" # leave empty if no data, i.e. ""
# Meta-proteomics
metap:
# TODO
############################################################
# TOOLS
##############################
# Preprocessing
# TODO: installation
# Preprocessing: LR: Basecalling
# XXX
guppy:
config: "dna_r9.4.1_450bps_modbases_dam-dcm-cpg_hac.cfg"
gpu:
path: "/home/users/sbusi/apps/ont-guppy/bin"
bin: "set +u; source ~/.bashrc; set -u; ml compiler/LLVM system/CUDA && /home/users/sbusi/apps/ont-guppy/bin/guppy_basecaller"
version: "3.6.0+98ff765"
records_per_fastq: 8000
chunk_size: 1000
chunks_per_runner: 1000
num_callers: 4
runners_per_device: 2
gpu_device: "cuda:0"
threads: 20
# Preprocessing: SR
# XXX
fastp:
threads: 10
min_length: 40
# FastQ QC
# https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
fastqc:
threads: 10
params: "-q -f fastq"
##############################
# Assembly
# List of assemblers for different read types
assemblers:
sr: ["megahit", "metaspades"]
lr: ["flye"]
hy: ["metaspadeshybrid", "operams"]
# XXX
flye:
threads: 10
genome_size: "1g"
# XXX
metaspades:
threads: 10
# XXX
megahit:
threads: 10
# TODO: installation
# https://github.com/CSB5/OPERA-MS
operams:
threads: 10
bin: "/home/users/sbusi/apps/miniconda3/envs/operams/OPERA-MS/OPERA-MS.pl"
##############################
# Long-read assembly polishing
# XXX
medaka:
threads: 10 # do NOT set to large value (e.g. using 30 did not work)
model: r941_min_high # the MinION model, high accuarcy
# XXX
racon:
threads: 30
##############################
# Mapping
# Mapper
# http://bio-bwa.sourceforge.net/
bwa:
threads: 10
long_reads_index:
opts: "-aY -A 5 -B 11 -O 2,1 -E 4,3 -k 8 -W 16 -w 40 -r 1 -D 0 -y 20 -L 30,30 -T 2.5"
# SAM utils
# http://www.htslib.org/doc/samtools.html
samtools:
sort:
# threads: 10
chunk_size: "4G"
view:
# threads: 10
##############################
# Annotation
# TODO: data download
# Sequence search
# XXX
diamond:
threads: 20
#db: "/mnt/isilon/projects/ecosystem_biology/NOMIS/DIAMOND/new_nr.dmnd"
db: "/work/projects/ecosystem_biology/local_tools/databases/nr_uniprot_trembl.dmnd"
# CRISPR
# https://github.com/dnasko/CASC
casc:
threads: 10
# path: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin"
# perl5lib: "/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl"
# CRISPR
# https://github.com/ctSkennerton/minced
minced:
# path: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/minced/"
# Plasmid prediction
# https://github.com/smaegol/PlasFlow
plasflow:
threshold: 0.7 # class. prob. threshold
minlen: 1000 # rm contigs with length below this threshold
# AMR prediction
# https://github.com/arpcard/rgi
rgi:
threads: 5
db_url: "https://card.mcmaster.ca/latest/data"
alignment_tool: "DIAMOND" # DIAMOND or BLAST
##############################
# Analysis
# XXX
bbmap:
threads: 10
# Assembly quality
# XXX
quast:
threads: 10
# Sequence search and clustering
# https://github.com/soedinglab/MMseqs2
mmseqs2:
threads: 30
# path: "/home/users/sbusi/apps/mmseqs/bin"
# createdb: "/home/users/sbusi/apps/mmseqs/bin/mmseqs createdb"
# rbh: "/home/users/sbusi/apps/mmseqs/bin/mmseqs rbh"
# convertalis: "/home/users/sbusi/apps/mmseqs/bin/mmseqs convertalis"
# Seq. alignment
# https://mummer4.github.io/
# mummer:
# path: "/mnt/irisgpfs/projects/ecosystem_biology/local_tools/mummer/mummer-3.9.4alpha/bin"
##############################
# Taxonomy
# https://ccb.jhu.edu/software/kraken2/
# https://github.com/DerrickWood/kraken2
kraken2:
threads: 10
db:
maxikraken: "/scratch/users/bkunath/Kraken2/maxikraken2_1903_140GB/"
class:
sr: "--gzip-compressed --paired"
lr: "" # TODO
contigs: "" # TODO
# # XXX
# GTDBTK:
# DATA: "/home/users/sbusi/apps/db/gtdbtk/release89"
##############################
# MISC
# https://github.com/marbl/mash
mash:
threads: 10
##############################
# Binning
# DAS_Tool:
# path: "/home/users/sbusi/apps/DAS_Tool-master"
# bin: "/home/users/sbusi/apps/DAS_Tool-master/src/"
# db: "/home/users/sbusi/apps/DAS_Tool-master/db/"
# Rscript: "/home/users/sbusi/apps/miniconda3/envs/dastool/bin/"
# # Rscript: "/home/users/sbusi/apps/miniconda3/envs/dastool/bin/"
# # dastool_database: "/home/users/sbusi/apps/DAS_Tool-master/db/"
##############################
# ???
# nonpareil:
# memory: 4096
# threads: 14
# rebaler:
# threads: 28
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment