release candidate 20210310

LICENSE → LICENSE.md

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2018 Jia-Xing Yue
+Copyright (c) 2021 Jia-Xing Yue
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

Project_Template/00.Gamete_Reads/RecombineX.00.Retrieve_SRA_Reads.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+set -e -o pipefail
+
+#######################################
+# load environment variables for RecombineX
+source ./../../env.sh
+
+#######################################
+# set project-specific variables
+sra_run_list="sample2reads_map.txt" # A simple tab separated file with two columns, in which the first column contains the sample name and the sencond column contains the corresponding SRR id. Lines started with "#" will be ignored. Default = "sample2reads_map.txt".  
+#######################################
+
+
+
+
+
+#######################################
+# process the pipeline
+
+while read -r line
+do
+    [[ $line == \#* ]] && continue
+    [[ $line == "" ]] && continue
+    IFS=$'\t' read -r sample_id srr_id <<<"$line"
+    echo "retrieve reads by the SRR_id: $srr_id for the sample $sample_id ..."
+    $sra_dir/fastq-dump --defline-seq '@$sn[_$rn]/$ri' --defline-qual '+$sn[_$rn]/$ri' \
+    	--gzip --split-files -skip-technical --dumpbase --read-filter pass --clip $srr_id
+    mv ${srr_id}_pass_1.fastq.gz $sample_id.R1.fq.gz
+    mv ${srr_id}_pass_2.fastq.gz $sample_id.R2.fq.gz
+done < $sra_run_list
+
+############################
+# checking bash exit status
+if [[ $? -eq 0 ]]
+then
+    echo ""
+    echo "RecombineX message: This bash script has been successfully processed! :)"
+    echo ""
+    echo ""
+    exit 0
+fi
+############################

Project_Template/00.Gamete_Reads/sample2reads_map.txt

@@ -0,0 +1,23 @@
+## data source: https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA309059
+## https://www.ncbi.nlm.nih.gov/sra?linkname=bioproject_sra_all&from_uid=309059
+# sample_id  SRR_id
+AND1702-8A	SRR2984859
+AND1702-8B	SRR2984860
+AND1702-8C	SRR2984861
+AND1702-8D	SRR2984862
+AND1702-9A	SRR2984863
+AND1702-9B	SRR2984864
+AND1702-9C	SRR2984865
+AND1702-9D	SRR2984866
+AND1702-10A	SRR2984867
+AND1702-10B	SRR2984868
+AND1702-10C	SRR2984869
+AND1702-10D	SRR2984870
+AND1702-11A	SRR2984871
+AND1702-11B	SRR2984872
+AND1702-11C	SRR2984873
+AND1702-11D	SRR2984874
+AND1702-12A	SRR2984875
+AND1702-12B	SRR2984876
+AND1702-12C	SRR2984877
+AND1702-12D	SRR2984878

Project_Template/00.Parent_Genomes/RecombineX.00.Prepare_Sample_Parent_Genomes.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+set -e -o pipefail
+
+#######################################
+# load environment variables for RecombineX
+source ./../../env.sh
+
+#######################################
+# set project-specific variables
+
+# none
+
+#######################################
+# process the pipeline
+
+echo "retrieve sample parental genome data ..."
+for i in S288C SK1
+do
+    cp $RECOMBINEX_HOME/data/$i.genome.fa .
+    cp $RECOMBINEX_HOME/data/$i.all_feature.gff .
+    perl $RECOMBINEX_HOME/scripts/filter_gff_by_feature.pl -i $i.all_feature.gff -o $i.centromere.gff -f centromere -m keep
+done
+
+# echo "retrieve sample subtelomere GFF files ..."
+# for i in S288C SK1
+# do
+#     cp $RECOMBINEX_HOME/data/Saccharomyces_cerevisiae_subtelomere_gff3/$i.subtelomere.gff .
+# done
+
+echo ""
+echo "removing intermediate files and directories ..."
+for i in S288C SK1
+do
+    rm $i.all_feature.gff
+done
+
+
+############################
+# checking bash exit status
+if [[ $? -eq 0 ]]
+then
+    echo ""
+    echo "RecombineX message: This bash script has been successfully processed! :)"
+    echo ""
+    echo ""
+    exit 0
+fi
+############################

Project_Template/00.Parent_Reads/RecombineX.00.Retrieve_SRA_Reads.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+set -e -o pipefail
+
+#######################################
+# load environment variables for RecombineX
+source ./../../env.sh
+
+#######################################
+# set project-specific variables
+sra_run_list="sample2reads_map.txt" # A simple tab separated file with two columns, in which the first column contains the sample name and the sencond column contains the corresponding SRR id. Lines started with "#" will be ignored. Default = "sample2reads_map.txt".
+#######################################
+
+
+
+#######################################
+# process the pipeline
+
+while read -r line
+do
+    [[ $line == \#* ]] && continue
+    [[ $line == "" ]] && continue
+    IFS=$'\t' read -r sample_id srr_id <<<"$line"
+    echo "retrieve reads by the SRR_id: $srr_id for the sample $sample_id ..."
+    $sra_dir/fastq-dump --defline-seq '@$sn[_$rn]/$ri' --defline-qual '+$sn[_$rn]/$ri' \
+    	--gzip --split-files -skip-technical --dumpbase --read-filter pass --clip $srr_id
+    mv ${srr_id}_pass_1.fastq.gz $sample_id.R1.fq.gz
+    mv ${srr_id}_pass_2.fastq.gz $sample_id.R2.fq.gz
+done < $sra_run_list
+
+############################
+# checking bash exit status
+if [[ $? -eq 0 ]]
+then
+    echo ""
+    echo "RecombineX message: This bash script has been successfully processed! :)"
+    echo ""
+    echo ""
+    exit 0
+fi
+############################

Project_Template/00.Parent_Reads/sample2reads_map.txt

@@ -0,0 +1,5 @@
+## data source: https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA300835
+## https://www.ncbi.nlm.nih.gov/sra?linkname=bioproject_sra_all&from_uid=300835
+# sample_id	SRR_id
+SK1	SRR2984786
+S288C	SRR2984785

Project_Template/00.Reference_Genome/RecombineX.00.Prepare_Reference_Genome_for_Chlamydomonas_reinhardtii.sh

@@ -0,0 +1,65 @@
+#!/bin/bash
+set -e -o pipefail
+
+#######################################
+# load environment variables for Varathon
+source ./../../env.sh
+
+#######################################
+# set project-specific variables
+ref_genome_prefix="Chlamydomonas_reinhardtii" # The file name prefix of the reference genome. Default = "Chlamydomonas_reinhardtii". 
+ref_genome_download_URL="ftp://ftp.ensemblgenomes.org/pub/plants/release-49/fasta/chlamydomonas_reinhardtii/dna/Chlamydomonas_reinhardtii.Chlamydomonas_reinhardtii_v5.5.dna_sm.toplevel.fa.gz" # The URL for downloading the reference genome. Default = "ftp://ftp.ensemblgenomes.org/pub/plants/release-49/fasta/chlamydomonas_reinhardtii/dna/Chlamydomonas_reinhardtii.Chlamydomonas_reinhardtii_v5.5.dna_sm.toplevel.fa.gz".
+chr_list="./../../data/Chlamydomonas_reinhardtii.chr_list.txt" # The single-column list defining chromosomes/scaffolds/contigs to be included. Default = ./../../data/Chlamydomonas_reinhardtii.chr_list.txt".
+debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefer to keep intermediate files, otherwise use "no". Default = "no".
+#######################################
+
+
+
+
+#######################################
+# process the pipeline
+
+download_and_extract() {
+    url=$1
+    echo "Downloading $url"
+    if [[ $url =~ \.gz$ ]]; 
+    #if [[ $url =~ \.fa.gz$ || $url =~ \.fasta.gz$ ]]; 
+    then
+	download_location="$ref_genome_prefix.raw.fa.gz"
+        extract_command="gunzip"
+	wget -c --no-check-certificate $url -O $download_location
+	gunzip $download_location
+    else
+	download_location="$ref_genome_prefix.raw.fa"
+	wget -c --no-check-certificate $url -O $download_location
+    fi
+}
+
+echo ""
+echo "Retrieve the sample reference genome assembly ..."
+download_and_extract $ref_genome_download_URL 
+echo ""
+echo "Tidy the sample reference genome assembly ..."
+$RECOMBINEX_HOME/scripts/tidy_fasta.pl -i $ref_genome_prefix.raw.fa -o $ref_genome_prefix.tidy.fa
+sed -i "s/>/>chr/gi" $ref_genome_prefix.tidy.fa
+$RECOMBINEX_HOME/scripts/select_fasta_by_list.pl -i $ref_genome_prefix.tidy.fa -l $chr_list -m normal -o $ref_genome_prefix.tidy.lite.fa.gz
+
+if [[ $debug = "no" ]]
+then
+    echo ""
+    echo "Removing intermediate files ..."
+    rm $ref_genome_prefix.raw.fa
+    rm $ref_genome_prefix.tidy.fa
+fi
+
+############################
+# checking bash exit status
+if [[ $? -eq 0 ]]
+then
+    echo ""
+    echo "RecombineX message: This bash script has been successfully processed! :)"
+    echo ""
+    echo ""
+    exit 0
+fi
+############################

Project_Template/00.Reference_Genome/RecombineX.00.Prepare_Reference_Genome_for_Saccharomyces_cerevisiae.sh

@@ -0,0 +1,53 @@
+#!/bin/bash
+set -e -o pipefail
+
+#######################################
+# load environment variables for RecombineX
+source ./../../env.sh
+
+#######################################
+# set project-specific variables
+
+debug="no" # Whether to keep intermediate files for debuging. Use "yes" if prefer to keep intermediate files, otherwise use "no". Default = "no".
+
+#######################################
+
+
+
+######################################
+# process the pipeline
+echo "retrieve sample reference genome data ..."
+wget -c https://downloads.yeastgenome.org/sequence/S288C_reference/genome_releases/S288C_reference_genome_R64-2-1_20150113.tgz
+tar -xvzf S288C_reference_genome_R64-2-1_20150113.tgz
+cp ./S288C_reference_genome_R64-2-1_20150113/S288C_reference_sequence_R64-2-1_20150113.fsa  SGDref.genome.raw.fa
+cp ./S288C_reference_genome_R64-2-1_20150113/saccharomyces_cerevisiae_R64-2-1_20150113.gff SGDref.all_feature.gff
+perl $RECOMBINEX_HOME/scripts/tidy_SGDref_genome.pl -i SGDref.genome.raw.fa -o SGDref.genome.tidy.fa
+perl $RECOMBINEX_HOME/scripts/select_fasta_by_list.pl -i SGDref.genome.tidy.fa -l $RECOMBINEX_HOME/data/Saccharomyces_cerevisiae.chr_list.txt -o SGDref.genome.fa -m normal
+gzip SGDref.genome.fa
+perl $RECOMBINEX_HOME/scripts/filter_gff_by_feature.pl -i SGDref.all_feature.gff -o SGDref.centromere.gff -f centromere -m keep
+
+# echo "retrieve sample subtelomere GFF files ..."
+# cp $RECOMBINEX_HOME/data/Saccharomyces_cerevisiae_subtelomere_gff3/SGDref.subtelomere.gff .
+
+if [[ $debug = "no" ]]
+then
+    echo ""
+    echo "removing intermediate files and directories ..."
+
+    rm -rf S288C_reference_genome_R64-2-1_20150113*
+    rm SGDref.genome.raw.fa
+    rm SGDref.genome.tidy.fa
+    rm SGDref.all_feature.gff
+fi
+
+############################
+# checking bash exit status
+if [[ $? -eq 0 ]]
+then
+    echo ""
+    echo "RecombineX message: This bash script has been successfully processed! :)"
+    echo ""
+    echo ""
+    exit 0
+fi
+############################