release_v1.0.0

Author: yjx1217

Manual_20220403.docx Manual_20220507.docxManual_20220403.docx renamed to Manual_20220507.docx

@@ -8,8 +8,8 @@ source ./../../env.sh
 ###########################################
 # set project-specific variables
 reference_genome_assembly="./../00.Reference_Genome/SGDref.genome.fa.gz" # The input reference genome assembly in FASTA format with or without gz compression (e.g. *.fa, *.fasta, *.fa.gz, *.fasta.gz). Default = "./../00.Reference_Genome/SGDref.genome.fa.gz".
-use_centromere_annotation="yes" # Whether to use the centromere annotation information. When set to "yes" (default), you need to also provide the path to the centromere GFF file in the "centromere_gff=" option below. Default = "yes".
-centromere_gff="./../00.Reference_Genome/SGDref.centromere.gff" # Path to the centromere annotation GFF3 file. Required when "use_centromere_annotation="yes". Otherwise, leave it empty. Default = "./../00.Reference_Genome/SGDref.centromere.gff".
+use_centromere_annotation="yes" # Whether to use the centromere annotation information. When set to "yes" (default), you need to also provide the path to the centromere GFF file in the "centromere_gff=" option below. Set this option to "no" when running RecombineX for the mitochondrial genome. Default = "yes".
+centromere_gff="./../00.Reference_Genome/SGDref.centromere.gff" # Path to the centromere annotation GFF3 file. Required when "use_centromere_annotation="yes". Otherwise, leave it empty. Set this option to "" when running RecombineX for the mitochondrial genome. Default = "./../00.Reference_Genome/SGDref.centromere.gff".
 window_size=250 # The window size for the non-overlapping sliding-window-based CNV profiling. Default = 250 (i.e. 250 bp). 
 threads=4 # The number of threads to use. Default = "4".
 debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefer to keep intermediate files, otherwise use "no". Default = "no".
@@ -23,11 +23,13 @@ debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefe
 lower_quantile=15
 upper_quantile=85
 min_mappability=0.85 # The minimal mappability for sliding-window-based CNV profiling. Default = "0.85".
-excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs to be exclued for CNV profiling. We strongly recommend to exclude the organelle (e.g. Mitochondria and Choloraplast) genomes and plasmids if exists. Use "" if there is no chromosome/scaffold/contig for exclusion. Default = "". 
+
 raw_read_length=100 # RecombineX will fix this value for simplicity. There is no need to adjust it for the actual lengths of your Illumina reads. 
 check_duplicates_by_windowmasker="no" # Whether to mark duplicated regions using windowmasker. Default = "no". 
 ram_for_windowmasker="1536" # Accessible RAM (in MB) for windowmasker. Default = 1536.
 
+excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs to be exclued for CNV profiling. Default = "".
+
 test_file_existence () {
     filename=$1
     if [[ ! -f $filename ]]

Project_Template/01.Reference_Genome_Preprocessing/RecombineX.01.Reference_Genome_Preprocessing.sh

@@ -13,7 +13,8 @@ parent1_reads_R1="./../00.Parent_Reads/$parent1_tag.R1.fq.gz" # The path to the
 parent1_reads_R2="./../00.Parent_Reads/$parent1_tag.R2.fq.gz" # The path to the paired-end R2 reads of the parental genome 1. Default = "./../00.Parent_Reads/$parent1_tag.R2.fq.gz".
 parent2_reads_R1="./../00.Parent_Reads/$parent2_tag.R1.fq.gz" # The path to the paired-end R1 reads of the parental genome 2. Default = "./../00.Parent_Reads/$parent2_tag.R1.fq.gz".
 parent2_reads_R2="./../00.Parent_Reads/$parent2_tag.R2.fq.gz" # The path to the paired-end R2 reads of the parental genome 2. Default = "./../00.Parent_Reads/$parent2_tag.R2.fq.gz".
-use_centromere_annotation="yes" # Whether to use the centromere annotation information. Please note that enabling this option requires that you have the parent1_tag.centromere.relabel.gff and parent2_tag.centromere.relabel.gff files ready in the "./../01.Reference_Genome_Preprocessing" directory. Default = "yes".
+use_centromere_annotation="yes" # Whether to use the centromere annotation information. Please note that enabling this option requires that you have the parent1_tag.centromere.relabel.gff and parent2_tag.centromere.relabel.gff files ready in the "./../01.Reference_Genome_Preprocessing" directory. Set this option to "no" when running RecombineX for the mitochondrial genome. Default = "yes".
+apply_CNV_filter="yes" # Whether to apply CNV filter marker candidates. Set this option to "no" when running RecombineX for the mitochondrial genome due to its substantial GC% bias and highly repetitive content. Default = "yes". 
 ploidy=1 # The ploidy of the parental genome. (e.g. "1" for haploid and "2" for diploid). For diploid parents, only homozygous SNPs will be used as markers. If the parental genome is purely homozygous, it is recommended to set "ploidy=1" to maximize the power of CNV profiling. Default = "1".
 window_size=250 # The window size for the non-overlapping sliding-window-based CNV profiling. Default = 250 (i.e. 250 bp). 
 threads=4 # The number of threads to use. Default = "4".
@@ -27,12 +28,14 @@ debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefe
 reference_genome_preprocessing_dir="./../01.Reference_Genome_Preprocessing" # The path to the 01.Reference_Genome_Preprocessing directory.
 reference_raw_assembly="$reference_genome_preprocessing_dir/ref.genome.raw.relabel.fa" # The relabeled reference genome raw assembly generated in the 01.Reference_Genome_Preprocessing directory.
 reference_hardmask_bed="$reference_genome_preprocessing_dir/ref.genome.hardmask.relabel.masking_details.bed" # The masking details bed file for the relabeled and hardmasked reference genome assembly file generated in the 01.Reference_Genome_Preprocessing directory.
-excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs to be exclued for CNV profiling. We strongly recommend to exclude the organelle (e.g. Mitochondria and Choloraplast) genomes and plasmids if exists. Use "" if there is no chromosome/scaffold/contig for exclusion. Default = "". 
+
 mapping_quality_cutoff=30 # The minimal mapping quality to be considered. Default = "30".
 variant_calling_quality_cutoff=30 # The minimal variant calling quality to be considered. Default = "30".
 
 min_mappability=0.85 # The minimal mappability for sliding-window-based CNV profiling. Default = "0.85".
 cluster_window_size=10 # Adjacent variants within the specified window (unit: bp) will be both filtered out if any of them is INDEL. Default = "10".
+
+excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs to be exclued for CNV profiling. Default = "".
 #######################################
 
 
@@ -345,7 +348,7 @@ $bedtools_dir/bedtools subtract -a ${parent1_tag}-ref.ref.caller.annotate.vcf -b
 cat ${parent1_tag}-ref.ref.caller.annotate.vcf.header ${parent1_tag}-ref.ref.caller.annotate_hardmask.vcf.content > ${parent1_tag}-ref.ref.caller.annotate_hardmask.vcf
 
 parent1_based_CNV_bed_line_count=$(cat ${parent1_tag}-ref.ref.significant_CNV.bed |sed '/^\s*$/d' | wc -l)
-if [[ "$parent1_based_CNV_bed_line_count" > 0 ]]
+if [[ $apply_CNV_filter == "yes" && "$parent1_based_CNV_bed_line_count" > 0 ]]
 then
     $bedtools_dir/bedtools subtract -a ${parent1_tag}-ref.ref.caller.annotate_hardmask.vcf -b ${parent1_tag}-ref.ref.significant_CNV.bed > ${parent1_tag}-ref.ref.caller.annotate_hardmask_CNVmask.vcf.content
     cat ${parent1_tag}-ref.ref.caller.annotate.vcf.header ${parent1_tag}-ref.ref.caller.annotate_hardmask_CNVmask.vcf.content > ${parent1_tag}-ref.ref.caller.annotate_hardmask_CNVmask.vcf
@@ -631,7 +634,7 @@ $bedtools_dir/bedtools subtract -a ${parent2_tag}-ref.ref.caller.annotate.vcf -b
 cat ${parent2_tag}-ref.ref.caller.annotate.vcf.header ${parent2_tag}-ref.ref.caller.annotate_hardmask.vcf.content > ${parent2_tag}-ref.ref.caller.annotate_hardmask.vcf
 
 parent2_based_CNV_bed_line_count=$(cat ${parent2_tag}-ref.ref.significant_CNV.bed |sed '/^\s*$/d' | wc -l)
-if [[ "$parent2_based_CNV_bed_line_count" > 0 ]]
+if [[ $apply_CNV_filter == "yes" && "$parent2_based_CNV_bed_line_count" > 0 ]]
 then
     $bedtools_dir/bedtools subtract -a ${parent2_tag}-ref.ref.caller.annotate_hardmask.vcf -b ${parent2_tag}-ref.ref.significant_CNV.bed > ${parent2_tag}-ref.ref.caller.annotate_hardmask_CNVmask.vcf.content
     cat ${parent2_tag}-ref.ref.caller.annotate.vcf.header ${parent2_tag}-ref.ref.caller.annotate_hardmask_CNVmask.vcf.content >${parent2_tag}-ref.ref.caller.annotate_hardmask_CNVmask.vcf
@@ -700,6 +703,7 @@ perl $RECOMBINEX_HOME/scripts/extract_polymorphic_markers_by_reference_based_vcf
 
 perl $RECOMBINEX_HOME/scripts/filter_reference_based_markers_by_mpileup_and_depth.pl \
      -i $reference_based_prefix.depth_filter.SNP.markers.txt.gz \
+     -filter_by_depth_variation $apply_cnv_filter \
      -ref_depth_summary ${parent1_tag}-ref.ref.coverage_summary.txt \
      -query_depth_summary ${parent2_tag}-ref.ref.coverage_summary.txt \
      -ref_mpileup ${parent1_tag}-ref.ref.mpileup.gz \
@@ -708,6 +712,7 @@ perl $RECOMBINEX_HOME/scripts/filter_reference_based_markers_by_mpileup_and_dept
 
 # perl $RECOMBINEX_HOME/scripts/filter_reference_based_markers_by_mpileup_and_depth.pl \
 #      -i $reference_based_prefix.depth_filter.INDEL.markers.txt.gz \
+#      -filter_by_depth_variation $apply_cnv_filter \
 #      -ref_depth_summary ${parent1_tag}-ref.ref.coverage_summary.txt \
 #      -query_depth_summary ${parent2_tag}-ref.ref.coverage_summary.txt \
 #      -ref_mpileup ${parent1_tag}-ref.ref.mpileup.gz \

Project_Template/02.Polymorphic_Markers_by_Reference_based_Read_Mapping/RecombineX.02.Polymorphic_Markers_by_Reference_based_Read_Mapping.sh

@@ -23,7 +23,7 @@ gamete_reads_dir="./../00.Gamete_Reads" # The relative path to 00.Gamete_Reads.
 output_dir="$batch_id" # The output directory. Default = "$batch_id".
 mapping_quality_cutoff_for_mpileup=30 # The mapping quality cutoff for filtering the resulting bam file. Default = "30".
 min_mappability=0.85 # The minimal mappability for sliding-window-based CNV profiling. Default = "0.85".
-excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs in relabeled parental genomes (in ./../01.Reference_Genome_Preprocessing) to be exclued for CNV profiling. We strongly recommend to exclude the organelle (e.g. Mitochondria and Choloraplast) genomes and plasmids if they have not been previously excluded. Use "" if there is no chromosome/scaffold/contig for exclusion. Default = "" (since S288C_chrMT and SK1_chrMT have been previously excluded for the testing example). 
+excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs in relabeled parental genomes (in ./../01.Reference_Genome_Preprocessing) to be exclued for CNV profiling. Default = "".
 ##################################
 
 perl $RECOMBINEX_HOME/scripts/batch_read_mapping_to_reference_genome.pl \

Project_Template/03.Gamete_Read_Mapping_to_Reference_Genome/RecombineX.03.Gamete_Read_Mapping_to_Reference_Genome.sh

@@ -10,11 +10,11 @@ source ./../../env.sh
 batch_id="Batch_S288C-SK1" # The batch id used for the gamete read mapping analysis. Default = "Batch_S288C-SK1" 
 master_sample_table="Master_Sample_Table.${batch_id}.txt" # The master sample table for this batch. Default = "Master_Sample_Table.${batch_id}.txt".
 net_quality_cutoff=50 # The net quality cutoff for genotyping. Default = "50".
-apply_cnv_filter="yes" # Whether to set gamete genotype to NA for potential CNV regions in gametes. Set this option to "no" if the gamete sequencing depth is very low (e.g. <= 1). Default = "yes".
+apply_cnv_filter="yes" # Whether to set gamete genotype to NA for potential CNV regions in gametes. Set this option to "no" if the gamete sequencing depth is very low (e.g., <= 1) or when running RecombineX for the mitochondrial genome. Default = "yes".
 allow_heteroduplex="no" # Whether to consider the possibility of heteroduplex formation. Default = "no".
 chr_list="$RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.chr_list.txt" # The included chromosome list for the analyzed genome. Default = "$RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.chr_list.txt".
 color_scheme="$RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.color_scheme.txt" # The color scheme to use for plotting genotypes. This file is a tab-delimited two column list file in which the first column is parent_id and the second column is the hex color code. Default = "$RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.color_scheme.txt". 
-plot_centromere="yes" # Whether to plot centromere in the generated genotyping plots. Please note that enable this option requires that you have the ref.centromere.relabel.gff file ready in the "./../01.Reference_Genome_Preprocessing" directory. Default = "yes". 
+plot_centromere="yes" # Whether to plot centromere in the generated genotyping plots. Please note that enable this option requires that you have the ref.centromere.relabel.gff file ready in the "./../01.Reference_Genome_Preprocessing" directory. Set this option to "no" when running RecombineX for the mitochondrial genome. Default = "yes". 
 same_cross_combination_for_the_batch="yes" # Wether all the samples in the current batch come from the same cross combination (i.e. shared the same parents): "yes" or "no". When "yes", RecombineX will automatically profle and plot the parental allele frequency for every markers. Default = "yes".
 debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefer to keep intermediate files, otherwise use "no". Default = "no".
 ###########################################

Project_Template/04.Gamete_Genotyping_by_Reference_Genome/RecombineX.04.Gamete_Genotyping_by_Reference_Genome.sh

@@ -9,8 +9,8 @@ source ./../../env.sh
 # set project-specific variables
 parent_tag="S288C" # The unique tag (preferably containing only letters and numbers) for this specific parental genome. This tag will be used throughout this project. Default = "S288C".
 parent_genome_assembly="./../00.Parent_Genomes/$parent_tag.genome.fa" # Input parental genome assembly in FASTA format with or without gz compression (e.g. *.fa, *.fasta, *.fa.gz, *.fasta.gz). Default = "./../00.Parent_Genomes/$parent_tag.genome.fa".
-use_centromere_annotation="yes" # Whether to use the centromere annotation information. When set to "yes" (default), you need to also provide the path to the centromere GFF file in the "centromere_gff=" option below. Default = "yes".
-centromere_gff="./../00.Parent_Genomes/$parent_tag.centromere.gff" # Path to the centromere annotation GFF3 file. Required when use_centromere_annotation="yes". Default = "./../00.Parent_Genomes/$parent_tag.centromere.gff".
+use_centromere_annotation="yes" # Whether to use the centromere annotation information. When set to "yes" (default), you need to also provide the path to the centromere GFF file in the "centromere_gff=" option below. Set this option to "" when running RecombineX for the mitochondrial genome. Default = "yes".
+centromere_gff="./../00.Parent_Genomes/$parent_tag.centromere.gff" # Path to the centromere annotation GFF3 file. Required when use_centromere_annotation="yes". Set this option to "" when running RecombineX for the mitochondrial genome. Default = "./../00.Parent_Genomes/$parent_tag.centromere.gff".
 window_size=250 # The window size for the non-overlapping sliding-window-based CNV profiling. Default = 250 (i.e. 250 bp). 
 threads=4 # The number of threads to use. Default = "4".
 debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefer to keep intermediate files, otherwise use "no". Default = "no".
@@ -24,11 +24,13 @@ debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefe
 lower_quantile=15
 upper_quantile=85
 min_mappability=0.85 # The minimal mappability for sliding-window-based CNV profiling. Default = "0.85".
-excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs to be exclued for CNV profiling. We strongly recommend to exclude the organelle (e.g. Mitochondria and Choloraplast) genomes and plasmids if exists. Use "" if there is no chromosome/scaffold/contig for exclusion. Default = "". 
+
 raw_read_length=100 # RecombineX will fix this value for simplicity. There is no need to adjust it for the actual lengths of your Illumina reads.
 check_duplicates_by_windowmasker="no" # Whether to mark duplicated regions using windowmasker. Default = "no". 
 ram_for_windowmasker="1536" # Accessible RAM (in MB) for windowmasker. Default = 1536.
 
+excluded_chr_list_for_cnv_profiling="" # The relative path to the list for specifying chromosomes/scaffolds/contigs to be exclued for CNV profiling. Default = "".
+
 test_file_existence () {
     filename=$1
     if [[ ! -f $filename ]]

Project_Template/11.Parent_Genome_Preprocessing/RecombineX.11.Parent_Genome_Preprocessing.sh

@@ -11,7 +11,7 @@ parent1_tag="S288C" # The relabeling tag of genome 1 used in 11.Parent_Genome_Pr
 parent2_tag="SK1" # The relabeling tag of genome 2 used in 11.Parent_Genome_Preprocessing. Default = "SK1".
 genome_aln_mode="by_chromosome" # The mode for running whole genome alignment, can be "by_chromosome" (default) or "by_genome" (when interchromosomal rearrangements are involved, e.g. translocations). Default = "by_chromosome".
 chr_list="$RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.chr_list.txt" # The chromosome list for whole-genome alignment by chromosome, only needed when genome_aln_mode="by_chromosome". Default = "$RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.chr_list.txt".
-use_centromere_annotation="yes" # whether to use the centromere annotation information. Please note that enabling this option requires that you have the parent1_tag.centromere.relabel.gff and parent2_tag.centromere.relabel.gff files ready in the "./../11.Parent_Genome_Preprocessing" directory. Default = "yes".
+use_centromere_annotation="yes" # whether to use the centromere annotation information. Please note that enabling this option requires that you have the parent1_tag.centromere.relabel.gff and parent2_tag.centromere.relabel.gff files ready in the "./../11.Parent_Genome_Preprocessing" directory. Set this option to "no" when running RecombineX for the mitochondrial genome. Default = "yes".
 threads=4 # The number of threads to use. Default = "4".
 debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefer to keep intermediate files, otherwise use "no". Default = "no".
 ###########################################