Testing V-pipe SARS-CoV-2

vpipe-sarsvoc2-tut.sh

mkdir V-test
cd V-test


######################
###                ###
###   Miniconda3   ###
###                ###
######################


wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

# -b for batch (no question asked)
bash Miniconda3-latest-Linux-x86_64.sh -b -p ~/V-test/miniconda3


## Mac OS X:
#curl -O https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
#sh Miniconda3-latest-MacOSX-x86_64.sh -b -p ~/miniconda3

# mind the dot (=source)
. ~/V-test/miniconda3/bin/activate 

conda create -n V-pipe -c bioconda snakemake conda
conda activate V-pipe
# We will let snakemake --use-conda handle 
# installation and download of V-pipe dependencies


##################
###            ###
###   V-pipe   ###
###            ###
##################

git clone -b sars-cov2 https://github.com/cbg-ethz/V-pipe.git
cd V-pipe



################
###          ###
###   test   ###
###          ###
################


# Go to NCBI SRA and download the runs with references SRR10903401 and SRR10903402
# Create a directory samples and store them inside
mkdir -p samples/{SRR10903401,SRR10903402]/raw_data

tree samples
## verfify that the samples have the following directory structure,
## the _R1 and _R2 suffixes on paired-ends are important:
# samples
# ├── SRR10903401
# │   └── 20200102
# │       └── raw_data
# │           ├── wuhan2_R1.fastq
# │           └── wuhan2_R2.fastq
# └── SRR10903402
#     └── 20200102
#         └── raw_data
#             ├── wuhan1_R1.fastq
#             └── wuhan1_R2.fastq

### SNV + local (shorah)

nano vpipe.config

#[input]
#reference = references/NC_045512.2.fasta
#
#[output]
#snv = True 
#local = False
#global = False
#
#[general]
#aligner = bwa


# Check task that will be run:
snakemake -s vpipe.snake --dryrun -p --cores 2

# on the first run V-pipe will also generate the sample collection table
nano samples.tsv

## V-pipe's defaults for reads length of 200 ; add other reads lengths in third column:
SRR10903401	20200102	150
SRR11092063	20191230	150

# run analysis:
snakemake -s vpipe.snake --use-conda -p --cores 2
## the necessary dependencies will be downloaded and installed in conda environments managed by snakemake


### Results:

## Data in: variants/minority_variants.tsv

## Shorah data in: {sample}/variants/SNVs/REGION_1/



###################
###             ###
###   Cluster   ###
###             ###
###################

# https://snakemake.readthedocs.io/en/stable/executing/cluster-cloud.html#cluster-execution
# https://scicomp.ethz.ch/wiki/Using_the_batch_system


wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh -b -p ~/miniconda3

~/miniconda3/bin/conda install -c bioconda snakemake
# beware of occasional version conflict...

# ...update an outdated miniconda base installation
~/miniconda3/bin/conda update conda

# ...and/or install elsewhere
~/miniconda3/bin/conda create -p ~/V-pipe_conda -c bioconda conda snakemake
~/V-pipe_conda/bin/snakemake --version

git clone -b sars-cov2 https://github.com/cbg-ethz/V-pipe.git
cd V-pipe

# Useful storage tricks:
#
# --create-envs-only
# only download and install dependencies, do not run yet
#
# --conda-prefix	DIR
# store the conda environments of dependencies in that directory
# (thus possible to share re-use between multiple instances of V-pipe)
~/miniconda3/bin/snakemake -s vpipe.snake --use-conda --conda-prefix ~/snake-envs --create-envs-only

# cluster LSF dispatching
~/miniconda3/bin/snakemake -s vpipe.snake --use-conda --conda-prefix ~/snake-envs -p --cluster 'bsub' --jobs 2