diff --git a/gust b/gust index 901806f..434342b 100755 --- a/gust +++ b/gust @@ -32,6 +32,7 @@ if [[ -z "$2" ]]; then echo "and outgroup genomes, then run gust again. You can also modify" echo "parameters before running." cat <config.yml +# #=======================================================# # gust config file # # most of this file is comments, which you can delete # @@ -52,15 +53,16 @@ bwa_parameters: "-a -k 19" # -a outputs all alignments # -k 19 is a kmer size of 19 -freebayes_parameters: "-C 2 --min-coverage 5 --standard-filter --ploidy 1" -# -C 2 means at least 2 samples need to have alt alleles for a site to be kept +freebayes_parameters: "-C 1 --min-coverage 5 --standard-filter --ploidy 1" +# -C 1 means at least 1 sample needs to have alt allele for a site to be kept # --min-coverage 5 means at least 5 aligments to score a site -# --standard-filter is to add more stringency +# --standard-filter is equivalent to -m 30 -q 20 -R 0 -S 0 # --ploidy 1 because these are typically haploid assemblies window_size: 50000 +sites_per_window: 10 # window size in base pairs for LD pruning snp data -# bigger window = fewer snps +# number of sites to keep per window musclev5_parameters: "-replicates 100" # if runtime is important, you may want to reduce replicates @@ -69,10 +71,10 @@ raxml_model: "GTR+G" # the phylogenetic model you would like to use see for options: # https://isu-molphyl.github.io/EEOB563/computer_labs/lab4/models.html -raxml_parameters: "--bs-trees 100 --tree pars\{25\},rand\{25\} -brlen scaled" +raxml_parameters: '--bs-trees 100 --tree pars\{25\},rand\{25\} -brlen scaled' # --bs-trees 100 is 100 bootstrapped trees # --tree pars{25},rand{25} is to use 25 parsimonious trees and 25 random trees -# the curly braces need to be escaped with \ for snakemake +# the curly braces need to be escaped with \ for snakemake and note the single quotes # -brlen scaled is the model for branch linkage EOF exit 1