Merge pull request #42 from NBISweden/dev

Bug fix to ensure functionality

.test/config/config_mitogenomes.yaml

@@ -1,6 +1,6 @@
 #################################################################
 #################################################################
-# Configuration settings for the GenErode pipeline 0.5.0        #
+# Configuration settings for the GenErode pipeline 0.5.1        #
 # for ancient or historical samples, and modern samples         #
 #################################################################
 #################################################################

.test/config/config_mlRho_options.yaml

@@ -1,6 +1,6 @@
 #################################################################
 #################################################################
-# Configuration settings for the GenErode pipeline 0.5.0        #
+# Configuration settings for the GenErode pipeline 0.5.1        #
 # for ancient or historical samples, and modern samples         #
 #################################################################
 #################################################################

.test/config/config_pca_roh.yaml

@@ -1,6 +1,6 @@
 #################################################################
 #################################################################
-# Configuration settings for the GenErode pipeline 0.5.0        #
+# Configuration settings for the GenErode pipeline 0.5.1        #
 # for ancient or historical samples, and modern samples         #
 #################################################################
 #################################################################

.test/config/config_snpeff_gerp.yaml

@@ -1,6 +1,6 @@
 #################################################################
 #################################################################
-# Configuration settings for the GenErode pipeline 0.5.0        #
+# Configuration settings for the GenErode pipeline 0.5.1        #
 # for ancient or historical samples, and modern samples         #
 #################################################################
 #################################################################

Snakefile

@@ -2,7 +2,7 @@
 # This is the Snakefile of the GenErode pipeline for historical or       #
 # ancient and modern samples to study patterns of genome erosion         #
 #                                                                        #
-# Pipeline version 0.5.0                                                 #
+# Pipeline version 0.5.1                                                 #
 #                                                                        #
 # Written by Verena Kutschera, Marcin Kierczak and Tom van der Valk      #
 # Email: generode@nbis.se                                                #

config/config.yaml

@@ -1,6 +1,6 @@
 #################################################################
 #################################################################
-# Configuration settings for the GenErode pipeline 0.5.0        #
+# Configuration settings for the GenErode pipeline 0.5.1        #
 # for ancient or historical samples, and modern samples         #
 #################################################################
 #################################################################
@@ -371,7 +371,9 @@ merge_vcfs_per_dataset: False
 
 # Maximum allowed fraction of missing genotypes across all samples for a 
 # site to be kept in the BCF and BED file, to ensure that the same sites 
-# are compared between historical and modern samples.
+# are compared between historical and modern samples. Has to be a floating
+# point number between 0.0 (no missing data allowed) and 1.0 (sites are 
+# allowed that are completely missing).
 f_missing: 0.1 # default: 0.1 (i.e. maximum 10% missing genotypes per site)
 #####
 

workflow/rules/0.2_repeat_identification.smk

@@ -177,7 +177,7 @@ rule repeatmasker:
         RepeatMasker -pa {threads} -a -xsmall -gccalc -dir ./ -lib {params.repmo} {params.ref_upper} 2> {log} &&
 
         # Check if *.cat file is compressed or uncompressed
-        if [ ! -f {output.rep_cat} ] # check if there are at least 2 files for merging. If there is only one file, copy the sorted bam file.
+        if [ ! -f {output.rep_cat} ]
         then
           gzip {params.rep_cat_unzip}
         fi

workflow/rules/3.1_bam_rmdup_realign_indels.smk

@@ -544,7 +544,7 @@ rule indel_realigner:
 
 rule index_realigned_bams:
     input:
-        bam="results/{dataset}/mapping/" + REF_NAME + "/{sample}.merged.rmdup.merged.bam",
+        bam="results/{dataset}/mapping/" + REF_NAME + "/{sample}.merged.rmdup.merged.realn.bam",
     output:
         index=temp("results/{dataset}/mapping/" + REF_NAME + "/{sample}.merged.rmdup.merged.realn.bam.bai"),
     log:

workflow/rules/9_merge_vcfs.smk

@@ -326,7 +326,20 @@ rule filter_vcf_missing:
         "docker://quay.io/biocontainers/bcftools:1.9--h68d8f2e_9"
     shell:
         """
-        bcftools view -i 'F_MISSING < {params.fmiss}' -Oz -o {output.vcf} {input.bcf} 2> {log} &&
+        # only include sites with zero missing data
+        if [[ `echo 0.0 {params.fmiss} | awk '{{print ($1 == $2)}}'` == 1 ]]
+        then
+          bcftools view -i 'F_MISSING = {params.fmiss}' -Oz -o {output.vcf} {input.bcf} 2> {log}
+        # include all sites
+        elif [[ `echo 1.0 {params.fmiss} | awk '{{print ($1 == $2)}}'` == 1 ]]
+        then
+          bcftools view -i 'F_MISSING <= {params.fmiss}' -Oz -o {output.vcf} {input.bcf} 2> {log}
+        # include sites with less than the fraction f_missing of missing data
+        elif [[ `echo 0.0 {params.fmiss} 1.0 | awk '{{print ($1 < $2 && $2 < $3)}}'` == 1 ]]
+        then 
+          bcftools view -i 'F_MISSING < {params.fmiss}' -Oz -o {output.vcf} {input.bcf} 2> {log}
+        fi
+        
         bcftools index -f {output.vcf} 2>> {log}
         """
 

workflow/rules/common.smk

@@ -10,7 +10,7 @@ import pandas as pd
 
 min_version("5.19.0")
 
-generode_version = "0.5.0"
+generode_version = "0.5.1"
 
 configfile: "config/config.yaml"