updated documentation and scripts

AllRice.def

@@ -0,0 +1,309 @@
+bootstrap: docker
+From: fedora:35
+
+%help
+    This container provides working software versions for the AllRice project.
+
+%post
+    dnf -y update
+    dnf -y install bc bzip2 findutils git lftp mlocate tcsh unzip zip wget which
+    dnf -y install gcc-c++ make automake cmake ruby
+    dnf -y install glibc-static
+    dnf -y install boost boost-devel
+    dnf -y install cairo-devel pango-devel zlib-devel
+    dnf -y install libnsl
+    dnf -y install python python-biopython python3-wheel python-wheel-wheel python3-virtualenv python3-pip
+    dnf -y install python3-h5py python3-devel
+    dnf -y install pandoc
+    dnf -y install java-11-openjdk java-11-openjdk-devel ant
+    dnf -y install perl-App-cpanminus
+    dnf -y install curl libcurl libcurl-devel ncurses ncurses-devel
+    dnf -y install openssl openssl-devel
+
+
+### Read quality control
+
+    echo 'Installing FastQC from http://www.bioinformatics.babraham.ac.uk/projects/fastqc/ '
+    cd /opt
+    wget http://www.bioinformatics.babraham.ac.uk/projects/fastqc/fastqc_v0.11.9.zip
+    cpanm install FindBin
+    unzip fastqc_v0.11.9.zip
+    chmod +x FastQC/fastqc
+    \rm fastqc_v0.11.9.zip
+
+    echo 'Installing Trimmomatic from http://www.usadellab.org/cms/index.php?page=trimmomatic '
+    cd /opt
+    wget http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-0.39.zip
+    unzip Trimmomatic-0.39.zip
+    \rm Trimmomatic-0.39.zip
+# To run Trimmomatic, use the following alias on the host:
+#
+#alias trimmomatic="singularity exec -e -B${PWD} AllRice.sif java -Xmx16G -jar /opt/Trimmomatic-0.39/trimmomatic-0.39.jar"
+
+
+### Read manipulation
+
+    echo 'Installing SRAtoolkit from http://www.ncbi.nlm.nih.gov/books/NBK158900/ '
+    cd /opt
+    wget http://ftp-trace.ncbi.nlm.nih.gov/sra/sdk/2.11.3/sratoolkit.2.11.3-ubuntu64.tar.gz
+    tar -xzf sratoolkit.2.11.3-ubuntu64.tar.gz
+    \rm  sratoolkit.2.11.3-ubuntu64.tar.gz
+
+    echo 'Installing UMI-tools from https://github.com/CGATOxford/UMI-tools '
+    pip3 install --upgrade umi-tools
+
+    echo 'Installing HTSlib from http://www.htslib.org/ '
+    cd /opt
+    git clone https://github.com/samtools/htslib.git htslib
+    cd htslib
+    git submodule update --init --recursive
+    make && make install && make clean
+
+    echo 'Installing Samtools from http://www.htslib.org/ '
+    cd /opt
+    git clone https://github.com/samtools/samtools.git samtools
+    cd samtools
+    make && make install && make clean
+
+    echo 'Installing SeqKit from https://github.com/shenwei356/seqkit '
+    cd /opt
+    wget https://github.com/shenwei356/seqkit/releases/download/v2.1.0/seqkit_linux_amd64.tar.gz
+    tar -xzf seqkit_linux_amd64.tar.gz 
+    chmod a+x seqkit
+    mv seqkit /usr/local/bin
+    \rm seqkit_linux_amd64.tar.gz
+
+
+### Genome assembly tools:
+
+    echo 'Installing Flye from https://github.com/fenderglass/Flye '
+    cd /opt
+    git clone https://github.com/fenderglass/Flye.git
+    cd Flye/
+    python setup.py install
+
+    echo 'Installing Pilon, described at https://github.com/broadinstitute/pilon/wiki '
+    cd /opt
+    wget https://github.com/broadinstitute/pilon/releases/download/v1.24/pilon-1.24.jar
+# To run pilon, use the following alias on the host (adjust memory as needed):
+#
+#alias pilon="singularity exec -e -B${PWD} AllRice.sif java -Xmx16G -jar /opt/pilon-1.24.jar"
+
+    echo 'Installing MaSuRCA from https://github.com/alekseyzimin/masurca '
+    cd /opt
+    wget https://github.com/alekseyzimin/masurca/releases/download/v4.0.7/MaSuRCA-4.0.7.tar.gz
+    tar -xzf MaSuRCA-4.0.7.tar.gz
+    cd MaSuRCA-4.0.7
+    sed -i -e "\$d" install.sh 
+    \rm -rf Flye/
+    cd global-1/
+    sed -i -e "s#jellyfish samtools prepare ufasta quorum SuperReads SOAPdenovo2 PacBio MUMmer CA8 eugene#jellyfish ufasta quorum SuperReads MUMmer#"  Makefile.am
+    autoreconf
+    cd ..
+    ./install.sh 
+
+    echo 'Installing Wengan from https://github.com/adigenova/wengan '
+    cd /opt
+    wget https://github.com/adigenova/wengan/releases/download/v0.2/wengan-v0.2-bin-Linux.tar.gz
+    tar -xzf wengan-v0.2-bin-Linux.tar.gz
+    chmod a+x /opt/wengan-v0.2-bin-Linux/wengan.pl
+
+
+### Read mapping
+
+    echo 'Installing BWA '
+    cd /opt
+    git clone https://github.com/lh3/bwa.git
+    cd bwa
+    make
+    cp bwa /usr/local/bin/
+
+    echo 'Installing minimap2 from https://github.com/lh3/minimap2 '
+    cd /opt
+    wget https://github.com/lh3/minimap2/releases/download/v2.24/minimap2-2.24_x64-linux.tar.bz2
+    tar -jxvf minimap2-2.24_x64-linux.tar.bz2
+    cp minimap2-2.24_x64-linux/minimap2 /usr/local/bin
+
+    echo 'Installing Bowtie2 version 2.4.5 '
+    cd /opt
+    wget https://github.com/BenLangmead/bowtie2/releases/download/v2.4.5/bowtie2-2.4.5-linux-x86_64.zip
+    unzip bowtie2-2.4.5-linux-x86_64.zip 
+    \rm bowtie2-2.4.5-linux-x86_64.zip
+
+    echo 'Installing hisat2 '
+    cd /opt
+    wget https://cloud.biohpc.swmed.edu/index.php/s/oTtGWbWjaxsQ2Ho/download
+    mv download hisat2-2.2.1.zip
+    unzip hisat2-2.2.1.zip 
+    \rm hisat2-2.2.1.zip 
+
+    echo 'Installing STAR from https://github.com/alexdobin/STAR '
+    cd /opt
+    git clone https://github.com/alexdobin/STAR
+
+
+### Scaffolding tools
+
+    echo 'Installing RagTag '
+    cd /opt
+    git clone https://github.com/malonge/RagTag
+    cd RagTag
+    python3 setup.py install
+
+
+### Repeat masking tools
+
+    echo 'Installing RMBlast from http://www.repeatmasker.org/ '
+    cd /opt
+    wget http://www.repeatmasker.org/rmblast-2.10.0+-x64-linux.tar.gz
+    tar -xzf rmblast-2.10.0+-x64-linux.tar.gz
+    \rm rmblast-2.10.0+-x64-linux.tar.gz
+
+    echo 'Installing TRF '
+    cd /opt
+    git clone https://github.com/Benson-Genomics-Lab/TRF.git
+    cd TRF
+    mkdir build && cd build
+    ../configure
+    make
+    make install
+    make clean
+    cd ../..
+
+    echo 'Installing RepeatMasker from http://www.repeatmasker.org/ '
+    cd /opt
+    wget http://repeatmasker.org/RepeatMasker/RepeatMasker-4.1.1.tar.gz
+    tar -xzf RepeatMasker-4.1.1.tar.gz 
+    echo "/usr/local/bin/trf" > rmcnf
+    echo "2" >> rmcnf
+    echo "/opt/rmblast-2.10.0/bin" >> rmcnf
+    echo "Y" >> rmcnf
+    echo "5" >> rmcnf
+    cd RepeatMasker
+    perl ./configure < ../rmcnf
+    cd Libraries
+    wget https://github.com/BrendelGroup/AllRice/raw/main/data/RITE-12-10-2020.tgz
+    tar -xzf RITE-12-10-2020.tgz
+    \rm RITE-12-10-2020.tgz
+# ... obtained by download from https://www.genome.arizona.edu/cgi-bin/rite/index.cgi (selecting all Oryza entries)
+    cd ../..
+    \rm RepeatMasker-4.1.1.tar.gz rmcnf
+
+
+### R, EBSeq, DESeq2, RSEM
+
+    echo 'Installing R '
+    cd /opt
+    dnf -y install R
+    echo 'repo <- "http://ftp.ussg.iu.edu/CRAN"' > R2install
+    echo 'install.packages("pafr", repos = repo)' >> R2install
+    echo 'install.packages("BiocManager", repos = repo)' >> R2install
+    echo 'BiocManager::install(c("EBSeq","DESeq2","R2HTML"), ask=FALSE)' >> R2install
+    Rscript R2install
+
+    echo 'Installing RSEM '
+    cd /opt
+    git clone https://github.com/deweylab/RSEM
+    cd RSEM/
+    # ... we do not want the unaligned reads showing up in the BAM file when using bowtie2, thus:
+    sed -i -e "s#--dpad 0#--no-unal --dpad 0#g" rsem-calculate-expression
+    make
+    make ebseq
+
+
+### Alignment software
+
+    echo 'Installing BLAST+ version 2.12.0 from NCBI '
+    cd /opt
+    wget ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/2.12.0/ncbi-blast-2.12.0+-x64-linux.tar.gz
+    tar -xzf ncbi-blast-2.12.0+-x64-linux.tar.gz
+    cd ncbi-blast-2.12.0+/bin
+    cp * /usr/local/bin/
+    cd ../..
+    rm ncbi-blast-2.12.0+-x64-linux.tar.gz
+    cd ..
+
+    echo 'Installing MuSeqBox version 5.7 from BrendelGroup '
+    cd /opt
+    wget http://www.brendelgroup.org/bioinformatics2go/Download/MuSeqBox-5-7-2021.tar.gz
+    tar -xzf MuSeqBox-5-7-2021.tar.gz
+    cd MUSEQBOX5.7/src/
+    make linux
+    make install
+    make clean
+    cd ../..
+
+    echo 'Installing Vmatch aligner version 2.3.1 from http://vmatch.de '
+    #### Prerequisites
+    #### Install
+    cd /opt
+    wget http://vmatch.de/distributions/vmatch-2.3.1-Linux_x86_64-64bit.tar.gz
+    tar -xzf vmatch-2.3.1-Linux_x86_64-64bit.tar.gz
+    rm vmatch-2.3.1-Linux_x86_64-64bit.tar.gz
+    ln -s vmatch-2.3.1-Linux_x86_64-64bit VMATCH
+
+    echo 'Installing GenomeThreader version 1.7.3 spliced aligner '
+    cd /opt
+    wget http://genomethreader.org/distributions/gth-1.7.3-Linux_x86_64-64bit.tar.gz
+    tar -xzf gth-1.7.3-Linux_x86_64-64bit.tar.gz
+    rm gth-1.7.3-Linux_x86_64-64bit.tar.gz
+    ln -s gth-1.7.3-Linux_x86_64-64bit GENOMETHREADER
+
+
+### Utilities
+
+    echo 'Installing the GenomeTools package: '
+    cd /opt
+    git clone https://github.com/genometools/genometools.git
+    cd genometools
+    make
+    make install
+    make clean
+    sh -c 'echo "/usr/local/lib" > /etc/ld.so.conf.d/genometools-x86_64.conf'
+    ldconfig
+    cd ..
+
+    echo 'Installing ngsutilsj from https://github.com/compgen-io/ngsutilsj.git '
+    cd /opt
+    git clone https://github.com/compgen-io/ngsutilsj
+    cd ngsutilsj
+    ant jar
+    ln -s /opt/ngsutilsj/dist/ngsutilsj /usr/local/bin/ngsutilsj
+    cd ../..
+
+    echo 'Installing assembly-stats from https://github.com/sanger-pathogens/assembly-stats '
+    cd /opt
+    git clone https://github.com/sanger-pathogens/assembly-stats.git
+    cd assembly-stats/
+    mkdir build
+    cd build 
+    cmake ..
+    make
+    make install
+
+    echo 'Installing the AllRice package: '
+    cd /opt
+    git clone https://github.com/BrendelGroup/AllRice
+    cd ..
+
+
+%environment
+    export LC_ALL=C
+    export PATH=$PATH:/opt/FastQC
+    export PATH=$PATH:/opt/sratoolkit.2.11.3-ubuntu64/bin
+    export PATH=$PATH:/opt/MaSuRCA-4.0.7/bin
+    export PATH=$PATH:/opt/wengan-v0.2-bin-Linux:/opt/wengan-v0.2-bin-Linux/bin
+    export PATH=$PATH:/opt/bowtie2-2.4.5-linux-x86_64
+    export PATH=$PATH:/opt/hisat2-2.2.1
+    export PATH=$PATH:/opt/STAR/bin/Linux_x86_64
+    export PATH=$PATH:/opt/RSEM
+    export PATH=$PATH:/opt/GENOMETHREADER/bin
+    export PATH=$PATH:/opt/RepeatMasker
+    export PATH=$PATH:/opt/AllRice/bin
+    export PATH=$PATH:/opt/VMATCH
+    export BSSMDIR="/opt/GENOMETHREADER/bin/bssm"
+    export GTHDATADIR="/opt/GENOMETHREADER/bin/gthdata"
+
+%labels
+    Maintainer vpbrendel
+    Version v1.2

README.md

@@ -1,31 +1,53 @@
 # AllRice
 Code for rice genome analyses (but not necessarily only rice)
 
-## Quick Start [![https://www.singularity-hub.org/static/img/hosted-singularity--hub-%23e32929.svg](https://www.singularity-hub.org/static/img/hosted-singularity--hub-%23e32929.svg)](https://singularity-hub.org/collections/5032)
+## Quick Start
+
+The simplest way to get going is to use the AllRice
+[Singularity](https://apptainer.org/) container available from our
+[Singularity Hub](http://BrendelGroup.org/SingularityHub/) site; e.g.:
 
-The easiest way to access the code is via the
-[Singularity](https://www.sylabs.io/docs/) containers available from
-[Singularity Hub](https://singularity-hub.org/).
-Thus, once you know what you are doing, execution could be as simple as
 
 ```bash
-singularity pull --name AllRice.sif shub://BrendelGroup/AllRice:latest
-singularity pull --name DDN.sif     shub://BrendelGroup/AllRice:ddn
+cd
+git clone https://github.com/BrendelGroup/AllRice
+cd AllRice
+wget https://BrendelGroup.org/SingularityHub/AllRice.sif
+alias rws="singularity exec -e -B ~/AllRice/prj/LHRWBY2021  ~/AllRice/AllRice.sif"
+rws ngsutilsj help
+rws umi_tools --help
+rws flye --help
+wget https://BrendelGroup.org/SingularityHub/DDN.sif
+singularity exec -e -B ~/AllRice/prj/LHRWBY2021  ~/AllRice/DDN.sif  DiscovarDeNovo -h
 ```
 
-which provides, for example:
+In the above example, you clone this repository into your Linux home directory,
+go into the thus created AllRice directory, download the AllRice Singularity
+container, define the bash alias _rws_ ("run with singularity"), and check that
+everything works by showing help information on some of the installed programs.
+You then also download the DDN.sif image and show that you have the DiscoverDeNovo
+assembler accessible.
+For a listing of included software, see our [CATALOG](https://github.com/BrendelGroup/bgSingularityHub/blob/main/CATALOG.md).
+
+Of course this assumes that you have [Apptainer/Singularity](https://apptainer.org/) installed on your system.
+Check whether there is package built for your system.
+Otherwise, follow the instructions to [install Singularity from source code](https://apptainer.org/user-docs/master/quick_start.html#quick-installation-steps).
 
-```bash
-singularity exec -e -B ${PWD} AllRice.sif  ngsutilsj help
-singularity exec -e -B ${PWD} AllRice.sif  umi_tools --help
-singularity exec -e -B ${PWD} DDN.sif      DiscovarDeNovo -h
-```
 
 ## Projects
 
 * [LHRWBY2021](./prj/LHRWBY2021) Computational analyses discussed in
 
-__Dangping Luo, Jose C. Huguet-Tapia, R. Taylor Raborn, Frank F. White, Volker P. Brendel & Bing Yang (2021)__
 __Luo, D., Huguet-Tapia, J.C., Raborn, R.T., White, F.F., Brendel, V.P. & Yang, B. (2021)__
 _The Xa7 resistance gene guards the rice susceptibility gene SWEET14 against exploitation by the bacterial blight pathogen._
 [Plant Communications 2, 100164](https://www.sciencedirect.com/science/article/pii/S2590346221000390). 
+
+Follow the instructions in [0README](https://github.com/BrendelGroup/AllRice/blob/main/prj/LHRWBY2021/0README)
+to reproduce the work (or use the workflow as a template for analysis of your own data sets).
+
+
+## Contact
+
+Please direct all comments and suggestions to
+[Volker Brendel](<mailto:[email protected]>)
+at [Indiana University](http://brendelgroup.org/).