manual updates and minor improvements

README.md

@@ -54,8 +54,11 @@ Under the hood, a series of task-specific modules are provided to carry out the
 * **20.Recombinant_Tetrad_Simulation**
   * simulating recombinant tetrads with defined numbers of COs and NCOs.
 
+## Citation
+Jing Li, Bertrand Llorente, Gianni Liti, Jia-Xing Yue. (2022) RecombineX: a computational framework for high-throughput gamete genotyping and tetrad-based meiotic recombination profiling. BioRxiv. (https://doi.org/10.1101/2022.01.24.477452) 
+
 ## License
-RecombineX is distributed under the MIT license.
+RecombineX itself is distributed under the MIT license but some of its dependencies might have more strict license for commercial use. Please check the licensing details of those dependencies.
 
 ## Installation
 ```sh
@@ -66,7 +69,7 @@ bash ./install_dependencies.sh
 
 ## Requirements
 ### Hardware, operating system and network requirements
-RecombineX is designed for a desktop or computing server running an x86-64-bit Linux operating system. Multithreaded processors are preferred to speed up the process since many modules support multithreaded processing. 
+RecombineX is designed for a desktop or computing server running an x86-64-bit Linux operating system. Multithreaded processors are preferred to speed up the process since many modules support multithreaded processing. A stable internet connection is required for its installation. 
 
 ### Software requirements
 * bash (https://www.gnu.org/software/bash/)

data/Saccharomyces_cerevisiae.color_scheme.txt

@@ -1,9 +1,11 @@
 NA	"#e5e5e5"
 heteroduplex	"#ffa500"
-#P1	"#ff3300"
-#P2	"#0099ff"
 S288C	"#ff3300"
 SK1	"#0099ff"
+
+#P1	"#ff3300"
+#P2	"#0099ff"
+
 #DBVPG6044	"#ff3300"
 #DBVPG6765	"#66cc33"
 #Y12	"#0099ff"

install_dependencies.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# last update: 2021/12/07
+# last update: 2022/04/03
 
 set -e -o pipefail
 
@@ -103,8 +103,8 @@ MUMMER3_DOWNLOAD_URL="https://sourceforge.net/projects/mummer/files/mummer/${MUM
 # ASSEMBLYTICS_GITHUB_COMMIT_VERSION="df5361f" # committed on 2017.11.02
 # ASSEMBLYTICS_DOWNLOAD_URL="https://github.com/MariaNattestad/Assemblytics.git"
 
-GNUPLOT_VERSION="4.6.6"
-GNUPLOT_DOWNLOAD_URL="https://sourceforge.net/projects/gnuplot/files/gnuplot/${GNUPLOT_VERSION}/gnuplot-${GNUPLOT_VERSION}.tar.gz"
+# GNUPLOT_VERSION="4.6.6"
+# GNUPLOT_DOWNLOAD_URL="https://sourceforge.net/projects/gnuplot/files/gnuplot/${GNUPLOT_VERSION}/gnuplot-${GNUPLOT_VERSION}.tar.gz"
 
 BEDTOOLS_VERSION="2.27.1" # released on 2017.12.14
 BEDTOOLS_DOWNLOAD_URL="https://github.com/arq5x/bedtools2/releases/download/v${BEDTOOLS_VERSION}/bedtools-${BEDTOOLS_VERSION}.tar.gz"
@@ -125,7 +125,7 @@ SAMTOOLS_VERSION="1.9" # released on 2018.07.18
 SAMTOOLS_DOWNLOAD_URL="https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VERSION}/samtools-${SAMTOOLS_VERSION}.tar.bz2"
 
 GATK3_VERSION="3.6-6" #
-GATK3_DOWNLOAD_URL="git://github.com/yjx1217/GATK3_Archive.git"
+GATK3_DOWNLOAD_URL="https://github.com/yjx1217/GATK3_Archive.git"
 # GATK3_DOWNLOAD_URL="https://ftp-trace.ncbi.nlm.nih.gov/sra/sdk/${SRA_VERSION}/GenomeAnalysisTK.jar"
 
 # GATK4_VERSION="4.0.11.0" # released on 2018.10.23
@@ -149,7 +149,7 @@ VCFLIB_DOWNLOAD_URL="https://github.com/vcflib/vcflib/releases/download/v${VCFLI
 
 VT_VERSION="" # 
 VT_GITHUB_COMMIT_VERSION="f6d2b5d" # committed on 2018.08.01
-VT_DOWNLOAD_URL="git://github.com/atks/vt"
+VT_DOWNLOAD_URL="https://github.com/atks/vt"
 
 FREEC_VERSION="11.4" # released on 2018.04.27
 FREEC_DOWNLOAD_URL="https://github.com/BoevaLab/FREEC/archive/v${FREEC_VERSION}.tar.gz"
@@ -184,7 +184,13 @@ echo "[$(timestamp)] Download and install all the dependencies ..."
 #PYTHONPATH="$build_dir"
 PERL5LIB="$build_dir:$PERL5LIB"
 PERL5LIB="$build_dir/cpanm/perlmods/lib/perl5:$PERL5LIB"
-R_LIBS="$build_dir/R_libs:$R_LIBS"
+R_LIBS="$build_dir/R_libs"
+R_LIBS_USER="$build_dir/R_libs"
+echo ""
+echo "PERL5LIB=$PERL5LIB"
+echo "R_LIBS=$R_LIBS"
+echo "R_LIBS_USER=$R_LIBS_USER"
+
 echo ""
 echo "[$(timestamp)] Installing Perl modules ..."
 cpanm_dir="$build_dir/cpanm"
@@ -245,10 +251,10 @@ if [ -z $(check_installed "$rlib_dir/DNAcopy") ]; then
     if [ $(tidy_version "$R_VERSION") -ge $(tidy_version "3.6.0") ]
     then
 	echo "R_VERSION=$R_VERSION, use the new bioconductor installation protocol"
-	R -e ".libPaths(\"$build_dir/R_libs/\");install.packages(\"BiocManager\", repos=\"http://cran.rstudio.com/\", lib=\"$build_dir/R_libs/\");BiocManager::install(\"DNAcopy\")"
+	R -e ".libPaths(\"$build_dir/R_libs/\");install.packages(\"BiocManager\", repos=\"http://cran.rstudio.com/\", lib=\"$build_dir/R_libs/\");BiocManager::install(\"DNAcopy\", lib=\"$build_dir/R_libs/\")"
     else
 	echo "R_VERSION=$R_VERSION, use the old bioconductor installation protocol"
-	R -e ".libPaths(\"$build_dir/R_libs/\");source(\"https://bioconductor.org/biocLite.R\");biocLite(\"DNAcopy\", type = \"source\")"
+	R -e ".libPaths(\"$build_dir/R_libs/\");source(\"https://bioconductor.org/biocLite.R\");biocLite(\"DNAcopy\", lib=\"$build_dir/R_libs/\", type = \"source\")"
     fi
     note_installed "$rlib_dir/DNAcopy"
 fi

scripts/plot_parental_allele_frequency_in_tetrads.R

@@ -2,7 +2,7 @@
 ##############################################################
 #  script: plot_parental_allele_frequency_in_tetrads.R
 #  author: Jia-Xing Yue (GitHub ID: yjx1217)
-#  last edited: 2019.09.22
+#  last edited: 2022.04.03
 #  description: plot genome-wide parental allele frequency in tetrads
 #  example: Rscript --vanilla --slave plot_parental_allele_frequency_in_tetrads.R --input input.parental_allele_frequency.txt.gz --color color_scheme.txt --output output.parental_allele_frequency.plot.pdf  
 ##############################################################
@@ -25,7 +25,7 @@ opt <- parse_args(opt_parser)
 data <- read.table(opt$input, header = TRUE, sep = "\t", na.strings = "")
 
 # read color scheme
-color_scheme <- read.table(opt$color_scheme, header = FALSE, sep = "\t", na.strings = "")
+color_scheme <- read.table(opt$color_scheme, header = FALSE, sep = "\t", comment.char = "", na.strings = "")
 colnames(color_scheme) <- c("genotype", "color")
 color_palette <- as.character(color_scheme$color)
 names(color_palette) <- as.character(color_scheme$genotype)
@@ -39,7 +39,7 @@ for (c in chr_list) {
     	geom_point(shape = 3, size = 0.5) +
     	scale_color_manual(values = color_palette) +
 	scale_x_continuous(name=paste(c, " (kb)"), breaks=seq(0,tail(subdata$pos,1),50000), labels=seq(0,tail(subdata$pos,1)/1000,50)) + 
-	scale_y_continuous("Parental allele frequency") +
+        scale_y_continuous("Parental allele frequency", limits = c(0, 1), breaks = seq(0, 1, by=0.1)) +
 	facet_wrap(~chr, ncol = 1, scale = "free_x") +
     	theme_bw() +
 	theme(axis.text.x = element_text(angle=45,hjust=1)))