config.yaml

# This is the Snakemake configuration file that specifies paths and 
# and options for both the prepare and classify pipelines when they are run
# together. Anybody wishing to use the provided snakemake pipeline should first
# fill out this file with paths to their own data, as the Snakefile requires it.
# Every config option has reasonable defaults unless it is labeled as "required."
# Any of the config options in configs/prepare.yaml can be used here.
# All paths are relative to the directory that Snakemake is executed in.
# Note: this file is written in the YAML syntax (https://learnxinyminutes.com/docs/yaml/)


# The path to a text file specifying where to find read information for each sample
# Each row in the sample file should represent a different sample.
# The sample file should have 3 columns (each separated by a single tab):
#       <unique_sample_name> <fastq1_path> <fastq2_path>
# Alternatively, if you don't have FASTQ files, but you have BAM files, each
# row can have just two columns (where, again, each are separated by a tab):
#       <unique_sample_name> <bam_path>
# If a BAM file is provided, PCR duplicates will not be removed as they usually
# are. If you'd like to skip the peak calling step as well, you must provide a
# third column:
#       <unique_sample_name> <bam_path> <bed_path>
# Note that if you provide a BAM file, it must have read group information and
# no PCR duplicates. There must be an index (.bam.bai) file in the same
# directory as the BAM file. And the BAM file itself must have a .bam file
# extension, while the BED file must have a .bed file extension.
# this is a required input!
sample_file: data/samples.tsv

# Which samples from the samples_file should we execute the pipeline on?
# Comment out this line or set it to a falsey value if you want to run all samples in the sample file
SAMP_NAMES: [molt4_chr1, jurkat_chr1]

# The path to a reference genome
# The BWA index files, samtools index file (.fa.fai), and samtools dictionary file (.dict) must be stored in the same directory
# required!
genome: data/hg38.chr1.fa

# The path to the directory in which to place all of the output files
# Defined relative to whatever directory you execute the snakemake command in
# Defaults to "out" if this line is commented out or set to a falsey value
out: out

# Which callers do you want to run to find SNVs?
# If you don't want to run the snp pipeline, set this to a falsey value or comment out the line
# The order of the callers listed here will determine the order in which each
# callers' ALT allele is considered for inclusion in the final VCF output.
# If you decide to change the callers listed here, you should also make sure to
# change the trained classification model (ie "snp_model" below), since the
# model we provided in the example data only works with these callers. To create
# a new model, run the classify subworkflow separately using the example
# training data we provided. Make sure to set the appropriate callers in the
# "subset_callers" config value of classify.yaml
snp_callers: [gatk-snp, varscan-snp, vardict-snp]

# Which callers do you want to run to find indels?
# If you don't want to run the indel pipeline, set this to a falsey value or comment out the line
# The order of the callers listed here will determine the order in which each
# callers' ALT allele is considered for inclusion in the final VCF output.
# If you decide to change the callers listed here, you should also make sure to
# change the trained classification model (ie "indel_model" below), since the
# model we provided in the example data only works with these callers. To create
# a new model, run the classify subworkflow separately using the example
# training data we provided. Make sure to set the appropriate callers in the
# "subset_callers" config value of classify.yaml
indel_callers: [gatk-indel, varscan-indel, vardict-indel, pindel, illumina-strelka]

# A list of filtering expressions for filtering the sites before making variant predictions
# A filtering expression consists of the following concatenated together:
#   - the caller id
#   - a tilde ~
#   - one of awk's comparison operators (the following are currently supported: >, <, ==)
#   - a value to filter on
# Comment out these lines to disable filtering
# Note that we recommend keeping these settings, which filter sites with read depth (DP)
# greater than 10, since the results are likely to be inaccurate otherwise.
snp_filter: ['gatk-snp~DP>10']
indel_filter: ['gatk-indel~DP>10']

# The path to a trained, ensemble classifier, which can be used for calling SNVs
# Unless you have created your own, we recommend using the pre-trained models provided
# in the example data.
# required!
snp_model: data/snp.rda

# The path to a trained, ensemble classifier, which can be used for calling indels
# Unless you have created your own, we recommend using the pre-trained models provided
# in the example data.
# required!
indel_model: data/indel.rda