added config file

final/config/config.yaml

@@ -0,0 +1,110 @@
+### Contains needed sample names and file locations for various input, intermediate, and output files, as well as parameters for certain computational steps
+
+input: "input/"
+
+input_beds: "input/beds/"
+
+input_vcfs: "input/vcfs/"
+
+input_genomes: "input/genomes/"
+
+input_lists: "input/lists/"
+
+input_reads: "input/reads/"
+
+output: "output/"
+
+config: "config/config.yaml"
+
+prop: "0.6"  #percent of samples that must meet the coverage threshold to include a given genomic window
+
+cov_filter: "5" #depth of coverage an window must have in order for orthologs within to be included in analysis
+
+all_triple_orthos: "all_pf-poc-pow_orthologs.tsv"
+
+pf_triple_orthos_masked: "ortholog_beds/pf3d7_pf-poc-pow_orthologs_masked.tsv"
+
+poc_triple_orthos_masked: "ortholog_beds/curtisigh01_pf-poc-pow_orthologs_masked.tsv"
+
+pow_triple_orthos_masked: "ortholog_beds/wallikericr01_pf-poc-pow_orthologs_masked.tsv"
+
+pf_triple_orthos_unfiltered: "ortholog_beds/pf3d7_pf-poc-pow_orthologs_unfiltered.tsv"
+
+poc_triple_orthos_unfiltered: "ortholog_beds/curtisigh01_pf-poc-pow_orthologs_unfiltered.tsv"
+
+pow_triple_orthos_unfiltered: "ortholog_beds/wallikericr01_pf-poc-pow_orthologs_unfiltered.tsv"
+
+all_ovale_orthos: "all_poc-pow_orthologs.tsv"
+
+poc_ovale_orthos_masked: "ortholog_beds/curtisigh01_poc-pow_orthologs_masked.tsv"
+
+pow_ovale_orthos_masked: "ortholog_beds/wallikericr01_poc-pow_orthologs_masked.tsv"
+
+poc_ovale_orthos_unfiltered: "ortholog_beds/curtisigh01_poc-pow_orthologs_unfiltered.tsv"
+
+pow_ovale_orthos_unfiltered: "ortholog_beds/wallikericr01_poc-pow_orthologs_unfiltered.tsv"
+
+curtisigh01_genes: "beds/curtisigh01_genes_sorted.bed"
+
+curtisigh01_exons: "beds/curtisigh01_exons_sorted.bed"
+
+wallikericr01_exons: "beds/wallikericr01_exons_sorted.bed"
+
+wallikericr01_genes: "beds/wallikericr01_genes_sorted.bed"
+
+pf3d7_genes: "beds/pf3d7_genes_sorted.bed"
+
+pf3d7_exons: "beds/pf3d7_exons_sorted.bed"
+
+tajima_window: "300"
+
+general_java_opts:                        # ram and threads for less memory intensive gatk tools
+  - "-Xms4G"                       # initial heap size
+  - "-Xmx4G"                       # maximum heap size
+  - "-XX:ParallelGCThreads=2"
+
+gatk_haplotypecaller:
+  extra:                                                 # extra options to pass to gatk
+    - "--emit-ref-confidence GVCF"                          # mode for emitting reference confidence scores, possible values: {NONE, BP_RESOLUTION, GVCF}
+    - "--sample-ploidy 2"                                   # ploidy (no# of chromosomes per sample), for pooled data, set to number of samples in each pool * ploidy) {Default value: 2}
+    - "--assembly-region-padding 100"                       # amount of padding (in bp) to add to each side of the active region {Default value: 100}
+    - "--min-assembly-region-size 100"                      # minimum size of an assembly region {Default value: 50}
+    - "--max-num-haplotypes-in-population 128"              # maximum number of haplotypes in population {Default value: 128}
+    - "--kmer-size 10"                                      # kmer size to use in the read threading assembler {Default value: 10}
+    - "--kmer-size 25"                                      # kmer size to use in the read threading assembler {Default value: 25}
+    - "--min-dangling-branch-length 4"                      # minimum length of a dangling branch to try to recover {Default value: 4}
+    - "--heterozygosity 0.001"                             # heterozygosity for SNP and indel calling {Default value: 0.001, Kevin Wamae uses 0.0029 in Pf variant calling}
+    - "--indel-heterozygosity 1.25E-4"                       # heterozygosity for indel calling {Default value: 1.25E-4, Kevin Wamae uses 0.0017 for Pf}
+    - "--disable-read-filter null"                          # read filters to be disabled before analysis
+    - "--min-base-quality-score 10"                         # minimum base quality required to consider a base for calling {Default value: 10}
+    - "--base-quality-score-threshold 18"                   # base qualities below this threshold will be reduced to the minimum {Default value: 18}
+  java:
+    - "-Xms20G"                       # optimal mem=20G
+    - "-Xmx20G"                       # optimal mem=20G
+    - "-XX:ParallelGCThreads=2"      # optimal threads=2
+
+gatk_genotypegvcfs:
+  java:
+    - "-Xms2G"                       # optimal mem=2G
+    - "-Xmx2G"                       # optimal mem=2G
+    - "-XX:ParallelGCThreads=2"      # optimal threads=2
+
+gatk_hardfiltersnps:
+  - '--filter-name "QD3" --filter-expression "QD<3.0"'
+  - '--filter-name "FS50" --filter-expression "FS>50.0"'
+  - '--filter-name "SOR3" --filter-expression "SOR > 3.0"'
+  - '--filter-name "MQ50" --filter-expression "MQ<50.0"'
+  - '--filter-name "MQRS-2.5" --filter-expression "MQRankSum<-2.5"'
+  - '--filter-name "RPRS-3" --filter-expression "ReadPosRankSum<-3.0"'
+
+realmccoilr:
+  maxcoi: "25"
+  threshold_ind: "10"
+  threshold_site: "10"
+  totalrun: "1000"
+  burnin: "100"
+
+plink:
+  window: "50" #in number of variants
+  step: "5" #number of variants
+  r2: "0.3"