config.yaml

# Folders containing imputed genotype data (vcf format). I used the Michigan Imputation Server for this
runs:
    Imputation3: Genotypes/Imputation3
    Imputation4: Genotypes/Imputation4
   
# Human genome reference files. I downloaded these from Illumina iGenomes
reference:
    chain_file: /c8000xd3/rnaseq-heath/Ref/Homo_sapiens/GRCh38/hg19ToHg38.over.chain
    genome: /c8000xd3/rnaseq-heath/Ref/Homo_sapiens/GRCh38/NCBI/GRCh38Alt/genome.fa
    rsID: /c8000xd3/rnaseq-heath/Ref/Homo_sapiens/hg19/All_20161121.vcf.gz
    gtf: /c8000xd3/rnaseq-heath/Ref/Homo_sapiens/GRCh38/NCBI/GRCh38Decoy/Annotation/Genes.gencode/genes.gtf
    splice_sites: /c8000xd3/rnaseq-heath/Ref/Homo_sapiens/GRCh38/NCBI/GRCh38Decoy/Annotation/Genes.gencode/splicesites.txt
    index: /c8000xd3/rnaseq-heath/Ref/Homo_sapiens/GRCh38/NCBI/GRCh38Decoy/Sequence/WholeGenomeFasta/genome

# Count data from mapping RNAseq data to reference genome, I got this from the workflow at https://github.com/hobrien/GENEX-FB1
count_data: 
    gene: Data/counts_vst.txt
    transcript: Data/counts_tr_vst.txt
# tab delimited file with info about each sample. I think the columns are Sample, Sex, PCW, RIN, and ReadLength
sample_info: Data/SampleInfo.txt

# tab delimited file with info about fastq files. Columns are filename, library (sampleID-run_number), Batch, and location
seqfile: Data/sequences.txt

# tab delimited file with info about genotyping files. Columns are Sample, FID, IID, VCF_name, and Column_number_in_vcf
genotyping_info: Data/GenotypingInfo.txt