# # This is the Snakemake configuration file that specifies paths and # and options for the Combined Haplotype Pipeline # { # py2 is a bit of a hack so that python2 scripts can be called # by snakemake (which is written in python3). The value should # do whatever is needed to setup a python2 environment and # call the python2 interpreter. Depending on your system configuration, # this might involve setting the PATH environment variable or # just calling python2 "py2" : "PATH=$HOME/anaconda2/bin:$PATH; python ", # Rscript should set environment as appropriate and call Rscript interpreter "Rscript" : "PATH=$HOME/anaconda2/bin:$PATH; Rscript ", # WASP directory "wasp_dir" : "/iblm/netapp/home/gmcvicker/proj/WASP", # directory to write all output data files to "base_dir" : "/iblm/netapp/home/gmcvicker/proj/WASP/CHT/output", # minimum number of allele-specific reads (combined across individuals) # required to perform combined test on a region "min_as_count" : "10", # location of chromInfo file containing chromosome names and lengths # (can be downloaded from UCSC genome browser) "chrom_info" : "/iblm/netapp/home/gmcvicker/proj/WASP/examples/example_data/chromInfo.hg19.txt", # directory containing impute or VCF SNP files "snp_dir" : "/iblm/netapp/home/gmcvicker/proj/WASP/examples/example_data/genotypes", # file containing sample identifiers for impute or VCF SNP file "snp_samples" : "/iblm/netapp/home/gmcvicker/proj/WASP/examples/example_data/genotypes/YRI_samples.txt", # directory containing bowtie2 index # one file per chromosome "fasta_dir" : "/iblm/netapp/data1/external/GRC37/chroms", # text file containing sample identifiers for the subset of # samples that are used in study (one per line) "samples_file" : "/iblm/netapp/home/gmcvicker/proj/WASP/examples/example_data/H3K27ac/samples.txt", # directory containing BAM files "bam_dir" : "/iblm/netapp/home/gmcvicker/proj/WASP/examples/example_data/H3K27ac", # postfix of BAM files "bam_postfix" : ".keep.rmdup.bam" }