====== Bioinfo Server Configuration ======

===== compiler =====

<code bash>
chkuo@koa[~]$ sudo apt install gcc
chkuo@koa[~]$ sudo apt install g++
chkuo@koa[~]$ sudo apt install build-essential
</code>

===== openmpi =====
<code bash>
# installation
chkuo@koa[~]$ sudo apt install openmpi-bin openmpi-doc libopenmpi-dev

# to use mpi
# 1. prepare '~/.mpd.conf' in the home directory
#    This file must has the permission set to 600
#    and contains one line: MPD_SECRETWORD=<secret>
#    <secret> is a string (for example, your username)
# 2. prepare a command script that contains the instruction to run the program
# 3. use 'mpirun' to execute the .sh file
#    the '-np' option specifies the number of processors to use
mpirun -np 8 PROGRAM < COMMAND > LOG &
</code>

===== Perl =====
<code bash>
# perl-doc
chkuo@koa[~]$ sudo apt-get install perl-doc
# bioperl
chkuo@koa[~]$ sudo apt install bioperl
# 2018/12/19; ubuntu 18.04.1
# install missing module
chkuo@koa[~]$ sudo perl -e shell -MCPAN
cpan[1]> install Bio::SearchIO::blastxml
chkuo@koa[~]$ perldoc -l Bio::SearchIO::blastxml
/usr/local/share/perl/5.26.1/Bio/SearchIO/blastxml.pm
</code>


===== Python =====
<code bash>
# 2018/12/18; Ubuntu 18.04.1
# python2
chkuo@koa[~]$ python --version
Python 2.7.15rc1
# install pip for python package management
chkuo@koa[~]$ sudo apt install python-pip
chkuo@koa[~]$ pip -V
pip 9.0.1 from /usr/lib/python2.7/dist-packages (python 2.7)
# install NumPy; required for biopython
chkuo@koa[~]$ sudo pip install numpy
chkuo@koa[~]$ sudo pip show numpy
Name: numpy
Version: 1.15.4
Summary: NumPy: array processing for numbers, strings, records, and objects.
Home-page: http://www.numpy.org
Author: Travis E. Oliphant et al.
Author-email: None
License: BSD
Location: /usr/local/lib/python2.7/dist-packages
Requires: 
# install biopython
chkuo@koa[~]$ sudo pip install biopython
chkuo@koa[~]$ sudo pip show biopython
Name: biopython
Version: 1.72
Summary: Freely available tools for computational molecular biology.
Home-page: https://biopython.org/
Author: The Biopython Contributors
Author-email: biopython@biopython.org
License: UNKNOWN
Location: /usr/local/lib/python2.7/dist-packages
Requires: numpy
# PyVCF
# https://pyvcf.readthedocs.io/en/latest/index.html
chkuo@koa[~]$ sudo pip install pyvcf
chkuo@koa[~]$ sudo pip show pyvcf
Name: PyVCF
Version: 0.6.8
Summary: Variant Call Format (VCF) parser for Python
Home-page: https://github.com/jamescasbon/PyVCF
Author: James Casbon and @jdoughertyii
Author-email: casbon@gmail.com
License: UNKNOWN
Location: /usr/local/lib/python2.7/dist-packages
Requires: setuptools
# python3
chkuo@koa[~]$ python3 --version
Python 3.6.7
chkuo@koa[~]$ sudo apt install python3-pip
chkuo@koa[~]$ pip3 -V
pip 9.0.1 from /usr/lib/python3/dist-packages (python 3.6)
chkuo@koa[~]$ sudo pip3 install numpy
Successfully installed numpy-1.15.4
chkuo@koa[~]$ sudo pip3 install biopython
Successfully installed biopython-1.72
chkuo@koa[~]$ sudo pip3 install pyvcf
Successfully installed pyvcf-0.6.8
# seqmagick
# https://github.com/fhcrc/seqmagick
chkuo@koa[~]$ sudo pip3 install seqmagick
Successfully installed seqmagick-0.7.0

# install panda package on 2024/07/29
hychang@koa[~]$ sudo pip3 install pandas
Successfully installed pandas-1.3.5 pytz-2024.1
hychang@koa[~]$ sudo pip3 -V
pip 22.2.2 from /usr/local/lib/python3.7/dist-packages/pip (python 3.7)

</code>

===== R =====
  * [[http://www.r-project.org/]]

<code bash>
# installation on koa, 2018/12/14, Ubuntu 18.04
# install r-base
chkuo@koa[~]$ sudo apt install r-base
# check version
chkuo@koa[~]$ R --version
R version 3.4.4 (2018-03-15) -- "Someone to Lean On"
</code>

  * R version 3.6.3
<code bash>
chuan@koa[/usr/local]$ sudo wget https://cran.r-project.org/src/base/R-3/R-3.6.3.tar.gz
chuan@koa[/usr/local]$ sudo tar -zxf R-3.6.3.tar.gz
chuan@koa[/usr/local]$ cd R-3.6.3
chuan@koa[/usr/local/R-3.6.3]$ sudo ./configure
chuan@koa[/usr/local/R-3.6.3]$ sudo make
chuan@koa[/usr/local/R-3.6.3]$ bin/R --version
R version 3.6.3 (2020-02-29) -- "Holding the Windsock"
</code>
==== Bioconductor ====
  * [[http://master.bioconductor.org/install/]]
<code bash>
chkuo@koa[~]$ sudo R
> source("http://bioconductor.org/biocLite.R")
> biocLite()
> biocLite("NOISeq")
> biocLite("ShortRead")
</code>

===== NCBI db =====
  * use crontab to run the following script as frequently as necessary (e.g., once a week)

<file bash>
#!/bin/bash
# 
# ncbi_tax.3.sh; 2021/06/25; chkuo
# 
# download NCBI taxonomy db
# 
# prefix: data dir
prefix='/data/ncbi'
# suffix: date (YYYYMMDD)
suffix="$(date +%Y%m%d)"
taxonomy_dir="${prefix}/taxonomy_${suffix}"
taxonomy_log="${prefix}/taxonomy_${suffix}.log"
taxonomy_err="${prefix}/taxonomy_${suffix}.err"
date > $taxonomy_log
mkdir -p $taxonomy_dir
cd $taxonomy_dir
rsync --copy-links --times --verbose rsync://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz.md5 $taxonomy_dir 1>> $taxonomy_log 2>> $taxonomy_err
rsync --copy-links --times --verbose rsync://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz $taxonomy_dir 1>> $taxonomy_log 2>> $taxonomy_err
md5sum -c taxdump.tar.gz.md5 1>> $taxonomy_log 2>> $taxonomy_err
tar -xzvf taxdump.tar.gz 1>> $taxonomy_log 2>> $taxonomy_err
rm taxdump.tar.gz.md5
rm taxdump.tar.gz
date >> $taxonomy_log
exit
</file>

<file bash>
#!/bin/bash
# 
# ncbi_nt.3.sh; 2021/06/25; chkuo
# 
# download NCBI nt db
# 
# prefix: data dir
prefix='/data/ncbi'
# suffix: date (YYYYMMDD)
suffix="$(date +%Y%m%d)"
nt_dir="${prefix}/nt_${suffix}"
nt_log="${prefix}/nt_${suffix}.log"
nt_err="${prefix}/nt_${suffix}.err"
date > $nt_log
mkdir -p $nt_dir
cd $nt_dir
rsync --copy-links --times --verbose rsync://ftp.ncbi.nlm.nih.gov/blast/db/nt.*.tar.gz.md5 $nt_dir 1>> $nt_log 2>> $nt_err
rsync --copy-links --times --verbose rsync://ftp.ncbi.nlm.nih.gov/blast/db/nt.*.tar.gz $nt_dir 1>> $nt_log 2>> $nt_err
md5sum -c *.md5 1>> $nt_log 2>> $nt_err
for i in *.tar.gz; do tar -xzvf $i 1>> $nt_log 2>> $nt_err; done
rm *.tar.gz.md5
rm *.tar.gz
date >> $nt_log
exit
</file>

<file bash>
#!/bin/bash
# 
# ncbi_nr.3.sh; 2021/06/25; chkuo
# 
# download NCBI nr db
# 
# prefix: data dir
prefix='/data/ncbi'
# suffix: date (YYYYMMDD)
suffix="$(date +%Y%m%d)"
nr_dir="${prefix}/nr_${suffix}"
nr_log="${prefix}/nr_${suffix}.log"
nr_err="${prefix}/nr_${suffix}.err"
date > $nr_log
mkdir -p $nr_dir
cd $nr_dir
rsync --copy-links --times --verbose rsync://ftp.ncbi.nlm.nih.gov/blast/db/nr.*.tar.gz.md5 $nr_dir 1>> $nr_log 2>> $nr_err
rsync --copy-links --times --verbose rsync://ftp.ncbi.nlm.nih.gov/blast/db/nr.*.tar.gz $nr_dir 1>> $nr_log 2>> $nr_err
md5sum -c *.md5 1>> $nr_log 2>> $nr_err
for i in *.tar.gz; do tar -xzvf $i 1>> $nr_log 2>> $nr_err; done
rm *.tar.gz.md5
rm *.tar.gz
date >> $nr_log
exit
</file>

===== ffq =====
  * [[https://github.com/pachterlab/ffq]]

<code bash>
# 2022/09/19; chkuo
chkuo@koa[/usr/local]$ sudo pip install ffq
</code>

===== NCBI SRA Toolkit =====
  * [[https://github.com/ncbi/sra-tools/wiki/]]

<code bash>
# 2022/09/19; chkuo
chkuo@koa[/usr/local]$ sudo wget --output-document sratoolkit.tar.gz https://ftp-trace.ncbi.nlm.nih.gov/sra/sdk/current/sratoolkit.current-ubuntu64.tar.gz
chkuo@koa[/usr/local]$ sudo tar -vxzf sratoolkit.tar.gz
# set "/data/tmp" as the repository directory
</code>

===== BLAST+ =====
<code bash>
# 2021/06/22; chkuo
chkuo@koa[/usr/local]$ sudo wget ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/2.11.0/ncbi-blast-2.11.0+-x64-linux.tar.gz
chkuo@koa[/usr/local]$ sudo wget ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/2.11.0/ncbi-blast-2.11.0+-x64-linux.tar.gz.md5
chkuo@koa[/usr/local]$ md5sum -c ncbi-blast-2.11.0+-x64-linux.tar.gz.md5
chkuo@koa[/usr/local]$ sudo tar -xzf ncbi-blast-2.11.0+-x64-linux.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root ncbi-blast-2.11.0+/
</code>


===== BLAT =====
  * [[http://genome.ucsc.edu/goldenPath/help/blatSpec.html]]

<code bash>
chkuo@koa[/usr/local/bin]$ sudo wget http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/blat/blat
chkuo@koa[/usr/local/bin]$ sudo chmod 755 blat 
</code>


===== USEARCH =====
  * Sequence search and clustering.
  * [[http://www.drive5.com/usearch/]]
  * The program is not available for direct download. Need to register on the website and obtain downloading link by email.
  * Edgar (2010) Search and clustering orders of magnitude faster than BLAST. Bioinformatics 26: 2460-1. [[http://dx.doi.org/10.1093/bioinformatics/btq461|10.1093/bioinformatics/btq461]].
  * Edgar (2013) UPARSE: highly accurate OTU sequences from microbial amplicon reads. Nat Methods 10:996-8. [[http://dx.doi.org/10.1038/nmeth.2604|10.1038/nmeth.2604]]

===== MCL =====
Markov cluster algorithm, or MCL, is a clustering algorithm designed by Stijn van Dongen (see the official website here: [[http://www.micans.org/mcl/]]).

In bioinformatics, it is useful for defining orthologs based on a similarity graph generated by all-against-all BLAST search.

The installation is quite straightforward:
<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.micans.org/mcl/src/mcl-latest.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf mcl-latest.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root mcl-14-137
chkuo@koa[/usr/local]$ sudo chmod 755 mcl-14-137
chkuo@koa[/usr/local]$ cd mcl-14-137/
chkuo@koa[/usr/local/mcl-14-137]$ sudo ./configure
chkuo@koa[/usr/local/mcl-14-137]$ sudo make
chkuo@koa[/usr/local/mcl-14-137]$ sudo make check
chkuo@koa[/usr/local/mcl-14-137]$ sudo make install
chkuo@koa[/usr/local/mcl-14-137]$ which mcl
/usr/local/bin/mcl
</code>

===== Orthofisher =====
  *Orthofisher conducts automated and high-throughout identification of a predetermined set of orthologs, which can be used for phylgenomics, gene family copy number determination and more!
<code bash>
chuan@koa[/usr/local]$ sudo git clone https://github.com/JLSteenwyk/orthofisher.git
chuan@koa[/usr/local]$ cd orthofisher
chuan@koa[/usr/local]$ sudo update-alternatives --install /usr/bin/python python /usr/bin/python3 1  # change python2 to python3 as default
chuan@koa[/usr/local]$ sudo make install
</code>

===== MUMmer =====
  * [[http://mummer.sourceforge.net/]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://downloads.sourceforge.net/project/mummer/mummer/3.23/MUMmer3.23.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf MUMmer3.23.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root MUMmer3.23
chkuo@koa[/usr/local]$ cd MUMmer3.23/
chkuo@koa[/usr/local/MUMmer3.23]$ sudo make
chkuo@koa[/usr/local/MUMmer3.23]$ sudo make check
chkuo@koa[/usr/local/MUMmer3.23]$ sudo make install
chkuo@koa[/usr/local/MUMmer3.23]$ sudo ln -s /usr/local/MUMmer3.23/delta-filter /usr/local/bin/delta-filter
chkuo@koa[/usr/local/MUMmer3.23]$ sudo ln -s /usr/local/MUMmer3.23/mummer /usr/local/bin/mummer
chkuo@koa[/usr/local/MUMmer3.23]$ sudo ln -s /usr/local/MUMmer3.23/nucmer /usr/local/bin/nucmer
chkuo@koa[/usr/local/MUMmer3.23]$ sudo ln -s /usr/local/MUMmer3.23/show-coords /usr/local/bin/show-coords
chkuo@koa[/usr/local/MUMmer3.23]$ sudo ln -s /usr/local/MUMmer3.23/mummerplot /usr/local/bin/mummerplot
</code>

===== gnuplot =====
  * [[http://www.gnuplot.info/]]
<code bash>
chkuo@koa[/usr/local]$ sudo wget http://downloads.sourceforge.net/project/gnuplot/gnuplot/5.2.5/gnuplot-5.2.5.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf gnuplot-5.2.5.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root gnuplot-5.2.5
chkuo@koa[/usr/local]$ cd gnuplot-5.2.5/
chkuo@koa[/usr/local/gnuplot-5.2.5]$ sudo ./configure
chkuo@koa[/usr/local/gnuplot-5.2.5]$ sudo make
chkuo@koa[/usr/local/gnuplot-5.2.5]$ sudo make install
</code>

===== MUSCLE =====
  * Multiple sequence alignment. 
  * Edgar R (2004) MUSCLE: multiple sequence alignment with high accuracy and high throughput. Nucleic Acids Res. 32: 1792-7. [[http://dx.doi.org/10.1093/nar/gkh340|10.1093/nar/gkh340]].
  * [[http://www.drive5.com/muscle/]]

<code bash>
chkuo@koa[/usr/local/bin]$ sudo wget http://www.drive5.com/muscle/downloads3.8.31/muscle3.8.31_i86linux64
chkuo@koa[/usr/local/bin]$ sudo chmod 755 muscle3.8.31_i86linux64
chkuo@koa[/usr/local/bin]$ sudo ln -s muscle3.8.31_i86linux64 muscle
</code>

===== GBLOCKS =====
  * Alignment filtering. 
  * Talavera G, Castresana J (2007) Improvement of phylogenies after removing divergent and ambiguously aligned blocks from protein sequence alignments. Systematic Biology 56, 564-577.
  * Castresana J (2000). Selection of conserved blocks from multiple alignments for their use in phylogenetic analysis. Molecular Biology and Evolution 17, 540-552. 
  * [[http://molevol.cmima.csic.es/castresana/Gblocks.html]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://molevol.cmima.csic.es/castresana/Gblocks/Gblocks_Linux64_0.91b.tar.Z
chkuo@koa[/usr/local]$ sudo gunzip Gblocks_Linux64_0.91b.tar.Z 
chkuo@koa[/usr/local]$ sudo tar -xvf Gblocks_Linux64_0.91b.tar 
chkuo@koa[/usr/local]$ sudo chown -R root:root Gblocks_0.91b/
chkuo@koa[/usr/local]$ sudo chmod -R a+rx Gblocks_0.91b/
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/Gblocks_0.91b/Gblocks /usr/local/bin/Gblocks
</code>

===== PAL2NAL =====
  * PAL2NAL is a program that converts a multiple sequence alignment of proteins and the corresponding DNA (or mRNA) sequences into a codon alignment.
  * [[http://www.bork.embl.de/pal2nal/]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.bork.embl.de/pal2nal/distribution/pal2nal.v14.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf pal2nal.v14.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root pal2nal.v14
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/pal2nal.v14 /usr/local/pal2nal
</code>

===== PAML =====
  * Phylogenetic Analysis by Maximum Likelihood (PAML)
  * [[http://abacus.gene.ucl.ac.uk/software/]]

<code bash>
# 2023/05/19
chkuo@koa[/usr/local]$ sudo wget https://github.com/abacus-gene/paml/releases/download/v4.10.6/paml-4.10.6-linux-X86_64.tgz
chkuo@koa[/usr/local]$ sudo tar xzf paml-4.10.6-linux-X86_64.tgz
chkuo@koa[/usr/local]$ sudo chown -R root:root paml-4.10.6
chkuo@koa[/usr/local]$ sudo chmod -R 755 paml-4.10.6
chkuo@koa[/usr/local]$ cd paml-4.10.6/src
chkuo@koa[/usr/local/paml-4.10.6/src]$ sudo make -f Makefile
chkuo@koa[/usr/local/paml-4.10.6/src]$ sudo rm *.o
chkuo@koa[/usr/local/paml-4.10.6/src]$ sudo mv baseml basemlg chi2 codeml evolver infinitesites mcmctree pamp yn00 ../bin
</code>

===== jModelTest =====
  * [[http://code.google.com/p/jmodeltest2/]]

<code bash>
# required packages
chkuo@koa[~]$ sudo apt install default-jdk
chkuo@koa[~]$ sudo apt install ant
# installation
chkuo@koa[/usr/local]$ sudo wget https://github.com/ddarriba/jmodeltest2/files/157117/jmodeltest-2.1.10.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf jmodeltest-2.1.10.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root jmodeltest-2.1.10
</code>

===== PHYLIP =====
  * A free package of programs for inferring phylogenies.
    * Note: Phylip requires X11 library to compile the drawing programs. Need to install the X11 dev packages first:
<code bash>
sudo apt install libx11-dev
sudo apt install libxaw7-dev
</code>

Phylip installation:
<code bash>
chkuo@koa[/usr/local]$ sudo wget http://evolution.gs.washington.edu/phylip/download/phylip-3.697.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf phylip-3.697.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root phylip-3.697
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/phylip-3.697 /usr/local/phylip
chkuo@koa[/usr/local]$ cd /usr/local/phylip/src
chkuo@koa[/usr/local/phylip/src]$ sudo make -f Makefile.unx install
</code>

After installation, prepare 3 empty files (''outdist'', ''outfile'', and ''outtree'') in the home directory (''~/''). These are the default output files used by PHYLIP. By having these files in the home directory, PHYLIP will ask for custom output filenames, which will be answered by our command scripts.
===== PhyML =====
  * A simple, fast, and accurate algorithm to estimate large phylogenies by maximum likelihood.
  * [[https://github.com/stephaneguindon/phyml/]]
<code bash>
chkuo@koa[/usr/local]$ sudo wget https://github.com/stephaneguindon/phyml/archive/v3.3.20180621.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf v3.3.20180621.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root phyml-3.3.20180621
chkuo@koa[/usr/local]$ cd phyml-3.3.20180621
chkuo@koa[/usr/local/phyml-3.3.20180621]$ sudo ./configure --enable-phyml
chkuo@koa[/usr/local/phyml-3.3.20180621]$ sudo make
chkuo@koa[/usr/local/phyml-3.3.20180621]$ sudo make install
</code>


===== RAxML =====
  * [[http://sco.h-its.org/exelixis/software.html]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget https://github.com/stamatak/standard-RAxML/archive/v8.2.12.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf v8.2.12.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root standard-RAxML-8.2.12
chkuo@koa[/usr/local]$ cd standard-RAxML-8.2.12/
chkuo@koa[/usr/local/standard-RAxML-8.2.12]$ sudo make -f Makefile.AVX.gcc 
chkuo@koa[/usr/local/standard-RAxML-8.2.12]$ sudo rm *.o
</code>




===== FastTree =====
  * FastTree infers approximately-maximum-likelihood phylogenetic trees from alignments of nucleotide or protein sequences.
  * [[http://www.microbesonline.org/fasttree]]
<code bash>
chkuo@koa[/usr/local/bin]$ sudo wget http://www.microbesonline.org/fasttree/FastTree
chkuo@koa[/usr/local/bin]$ sudo chmod 755 FastTree 
</code>


===== TREE-PUZZLE =====
  * Maximum likelihood analysis for nucleotide, amino acid, and two-state data 
<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.tree-puzzle.de/tree-puzzle-5.2.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf tree-puzzle-5.2.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root tree-puzzle-5.2
chkuo@koa[/usr/local]$ sudo chmod -R go-w tree-puzzle-5.2
chkuo@koa[/usr/local/tree-puzzle-5.2]$ sudo ./configure
chkuo@koa[/usr/local/tree-puzzle-5.2]$ sudo make
chkuo@koa[/usr/local/tree-puzzle-5.2]$ sudo make check
chkuo@koa[/usr/local/tree-puzzle-5.2]$ sudo make install
chkuo@koa[/usr/local/tree-puzzle-5.2]$ sudo make clean
chkuo@koa[/usr/local/tree-puzzle-5.2]$ which puzzle
/usr/local/bin/puzzle
</code>

===== MrBayes =====
  * MrBayes: Bayesian Inference of Phylogeny
  * [[http://nbisweden.github.io/MrBayes/]]
<code bash>
# prerequisite
chkuo@koa[/usr/local]$ sudo apt install build-essential autoconf automake libtool git pkg-config
# require BEAGLE
# https://code.google.com/p/beagle-lib
chkuo@koa[/usr/local]$ sudo wget https://github.com/beagle-dev/beagle-lib/archive/v3.1.2.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf beagle-lib-3.1.2
chkuo@koa[/usr/local]$ sudo chown -R root:root beagle-lib-3.1.2
chkuo@koa[/usr/local]$ cd beagle-lib-3.1.2
chkuo@koa[/usr/local/beagle-lib-3.1.2]$ sudo ./autogen.sh
chkuo@koa[/usr/local/beagle-lib-3.1.2]$ sudo ./configure --prefix=/usr/local
chkuo@koa[/usr/local/beagle-lib-3.1.2]$ sudo make
chkuo@koa[/usr/local/beagle-lib-3.1.2]$ sudo make check
chkuo@koa[/usr/local/beagle-lib-3.1.2]$ sudo make install
# install mrbayes
# 2024/04/19
# 3.2.6 -> 3.2.7
chkuo@koa[/usr/local]$ sudo wget https://github.com/NBISweden/MrBayes/releases/download/v3.2.7/mrbayes-3.2.7.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf mrbayes-3.2.7.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root mrbayes-3.2.7
chkuo@koa[/usr/local]$ cd mrbayes-3.2.7
chkuo@koa[/usr/local/mrbayes-3.2.7]$ sudo ./configure --with-mpi
chkuo@koa[/usr/local/mrbayes-3.2.7]$ sudo make
chkuo@koa[/usr/local/mrbayes-3.2.7]$ sudo make install
chkuo@koa[/usr/local/mrbayes-3.2.7]$ /usr/local/bin/mb -v
Version:   3.2.7
</code>




===== sff2fastq =====
  * The program 'sff2fastq' extracts read information from a SFF file, produced by the 454 genome sequencer, and outputs the sequences and quality scores in a FASTQ format.
  * [[https://github.com/indraniel/sff2fastq]]

<code bash>
chkuo@cherry[/usr/local]$ sudo git clone git://github.com/indraniel/sff2fastq.git
chkuo@cherry[/usr/local]$ cd sff2fastq/
chkuo@cherry[/usr/local/sff2fastq]$ sudo make
chkuo@cherry[/usr/local/sff2fastq]$ sudo ln -s /usr/local/sff2fastq/sff2fastq /usr/local/bin/sff2fastq
</code>



===== FASTX =====
  * [[http://hannonlab.cshl.edu/fastx_toolkit/]]
  * The FASTX-Toolkit is a collection of command line tools for Short-Reads FASTA/FASTQ files preprocessing. 

<code bash>
chkuo@koa[/usr/local]$ sudo apt install fastx-toolkit
</code>

===== Phred/Phrap/Consed =====
  * [[http://www.phrap.org/phredphrapconsed.html|Phred, Phrap, and Consed]]

==== phred ====
<code bash>
# prepare files
chkuo@koa[/usr/local/phred_020425]$ sudo uncompress phred-dist-020425.c-acd.tar.Z 
chkuo@koa[/usr/local/phred_020425]$ sudo tar -xvf phred-dist-020425.c-acd.tar 
# change ownership
chkuo@koa[/usr/local/phred_020425]$ sudo chown root:root *
# edit Makefile
# uncomment 'LXFLAGS= -DX86_GCC_LINUX' (line 8)
chkuo@koa[/usr/local/phred_020425]$ sudo emacs Makefile
# compile phred
chkuo@koa[/usr/local/phred_020425]$ sudo make
# compile daev
chkuo@koa[/usr/local/phred_020425]$ sudo make daev
# clean up
chkuo@koa[/usr/local/phred_020425]$ sudo rm *.o
# remove read permission according to the academic user agreement  
chkuo@koa[/usr/local/phred_020425]$ sudo chmod go-r *
# add read permission for .DOC files
chkuo@koa[/usr/local/phred_020425]$ sudo chmod a+r *.DOC
# add read permission for phredpar.dat
chkuo@koa[/usr/local/phred_020425]$ sudo chmod a+r phredpar.dat
# edit the phredpar.dat
# the sequencing core at IPMB uses ABI 3730
# need to append the following lines to 
# /usr/local/phred/phredpar.dat
#
# "KB_3730_POP7_BDTv1.mob"	terminator	big-dye			ABI_3700
# "KB_3730_POP7_BDTv3.mob"	terminator	big-dye			ABI_3700
#
# note: ABI 3730 is not recognized, use 3700 as the substitute
chkuo@koa[/usr/local/phred_020425]$ sudo emacs phredpar.dat
# create symbolic links
chkuo@koa[~]$ sudo ln -s /usr/local/phred_020425 /usr/local/phred
chkuo@koa[~]$ sudo ln -s /usr/local/phred/phred /usr/local/bin/phred
chkuo@koa[~]$ sudo ln -s /usr/local/phred/daev /usr/local/bin/daev
# set the 'PHRED_PARAMETER_FILE' environment variable
chkuo@koa[~]$ sudo emacs /etc/environment
# verify the setting
chkuo@koa[~]$ grep PHRED_PARAMETER_FILE /etc/environment
PHRED_PARAMETER_FILE="/usr/local/phred/phredpar.dat"
</code>

==== phd2fasta ====
<code bash>
# prepare files
chkuo@koa[/usr/local/phd2fasta]$ sudo uncompress phd2fasta-acd-dist.tar.Z 
chkuo@koa[/usr/local/phd2fasta]$ sudo tar -xvf phd2fasta-acd-dist.tar
# change ownership
chkuo@koa[/usr/local/phd2fasta]$ sudo chown root:root *
# compile
chkuo@koa[/usr/local/phd2fasta]$ sudo make
# clean up
chkuo@koa[/usr/local/phd2fasta]$ sudo rm *.o
# remove read permission according to the academic user agreement  
chkuo@koa[/usr/local/phd2fasta]$ sudo chmod go-r *
# add read permission for .DOC files
chkuo@koa[/usr/local/phd2fasta]$ sudo chmod a+r *.DOC
# create symbolic links
chkuo@koa[~]$ sudo ln -s /usr/local/phd2fasta/phd2fasta /usr/local/bin/phd2fasta
</code>

==== phrap ====
<code bash>
# prepare files
chkuo@koa[/usr/local/phrap]$ sudo tar -xzvf distrib.tar.gz 
# change ownership
chkuo@koa[/usr/local/phrap]$ sudo chown -R root:root *
# compile
chkuo@koa[/usr/local/phrap]$ sudo make
# clean up
chkuo@koa[/usr/local/phrap]$ sudo rm *.o
# remove read permission according to the academic user agreement  
chkuo@koa[/usr/local/phrap]$ sudo chmod go-r *
# add read permission for .doc files
chkuo@koa[/usr/local/phrap]$ sudo chmod a+r *.doc
# create symbolic links
chkuo@koa[~]$ sudo ln -s /usr/local/phrap/phrap /usr/local/bin/phrap
chkuo@koa[~]$ sudo ln -s /usr/local/phrap/cross_match /usr/local/bin/cross_match
chkuo@koa[~]$ sudo ln -s /usr/local/phrap/swat /usr/local/bin/swat
chkuo@koa[~]$ sudo ln -s /usr/local/phrap/phrapview /usr/local/bin/phrapview
</code>

==== consed ====
<code bash>
# Installing 
chkuo@koa[/usr/local/consed]$ sudo tar -xzvf consed_linux.tar.gz
chkuo@koa[/usr/local/consed]$ sudo chown -R root:root *
chkuo@koa[/usr/local/consed]$ sudo chmod go-r *
chkuo@koa[/usr/local/consed]$ sudo chmod a+r *txt
</code>

===== LUCY =====
  * Clean sequence data from automated DNA sequencers prior to sequence assembly and other downstream uses.
  * [[http://lucy.sourceforge.net/]]


<code bash>
chkuo@koa[/usr/local]$ sudo wget http://downloads.sourceforge.net/project/lucy/lucy/lucy%201.20/lucy1.20.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf lucy1.20.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root lucy-1.20p/
chkuo@koa[/usr/local/lucy-1.20p]$ sudo make
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/lucy-1.20p/lucy /usr/local/bin/lucy
</code>



===== RDP Classifier =====
  * [[http://rdp.cme.msu.edu/classifier/classifier.jsp]]
  * [[http://sourceforge.net/projects/rdp-classifier/]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://downloads.sourceforge.net/project/rdp-classifier/rdp-classifier/rdp_classifier_2.10.1.zip
chkuo@cherry[/usr/local]$ sudo unzip rdp_classifier_2.10.1.zip 
chkuo@cherry[/usr/local]$ sudo rm /usr/local/rdp_classifier_2.10.1.zip 
</code>

===== QIIME 2 =====
  * [[https://qiime2.org/]]



===== FastQC =====
  * A quality control application for high throughput sequence data
  * [[http://www.bioinformatics.babraham.ac.uk/projects/fastqc/]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.bioinformatics.babraham.ac.uk/projects/fastqc/fastqc_v0.11.8.zip
chkuo@koa[/usr/local]$ sudo unzip fastqc_v0.11.8.zip
chkuo@koa[/usr/local]$ sudo chmod a+x FastQC/fastqc 
</code>

===== Trimmomatic =====
  * A flexible read trimming tool for Illumina NGS data
  * [[http://www.usadellab.org/cms/?page=trimmomatic]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-0.39.zip
chkuo@koa[/usr/local]$ sudo unzip Trimmomatic-0.39.zip 
chkuo@koa[/usr/local]$ sudo chmod 755 /usr/local/Trimmomatic-0.39/trimmomatic-0.39.jar
</code>

===== bbtools =====
  * BBMap short-read aligner and a bunch of tools (shell scripts)
  * [[https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/installation-guide/]]

<code bash>
chuan@koa:/usr/local$ sudo wget https://sourceforge.net/projects/bbmap/files/BBMap_38.73.tar.gz
chuan@koa:/usr/local$ sudo tar xzf BBMap_38.73.tar.gz
chuan@koa:/usr/local$ sudo ln -s /usr/local/bbmap /usr/local/bin/bbmap
chuan@koa:/usr/local$ sudo chmod 755 bbmap/*
chuan@koa:/usr/local$ sudo ln -s /usr/local/bbmap/stats.sh /usr/local/bin/stats.sh
</code>

===== Bionano Tools =====
  * Bionano Genomics tools for analyses of optical mapping data (Saphyr)
  * [[https://bionanogenomics.com/wp-content/uploads/2017/10/30182-Bionano-Tools-Installation-Guide.pdf]]

<code bash>
chuan@koa:/usr/local$ sudo wget -N http://www.bnxinstall.com/access/tools/access.tools.tgz
chuan@koa:/usr/local$ sudo tar -xvf access.tools.tgz
chuan@koa:/usr/local$ sudo apt-get install yum
chuan@koa:/usr/local$ sudo python tools/access/1.0/pbng-install.chuan.py tools/access/1.0/bng-install.chuan.sh koa
</code>
===== FLASH =====
  * FLASH (Fast Length Adjustment of SHort reads) is a very fast and accurate software tool to merge paired-end reads from next-generation sequencing experiments
  * [[http://ccb.jhu.edu/software/FLASH/]]
  * [[http://sourceforge.net/projects/flashpage/]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://sourceforge.net/projects/flashpage/files/FLASH-1.2.11.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf FLASH-1.2.11.tar.gz 
chkuo@koa[/usr/local]$ cd FLASH-1.2.11/
chkuo@koa[/usr/local/FLASH-1.2.11]$ sudo make
chkuo@koa[/usr/local/FLASH-1.2.11]$ sudo ln -s /usr/local/FLASH-1.2.11/flash /usr/local/bin/flash
</code>
===== BWA =====
  * bwa - Burrows-Wheeler Alignment Tool 
  * [[http://bio-bwa.sourceforge.net/bwa.shtml]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://sourceforge.net/projects/bio-bwa/files/bwa-0.7.17.tar.bz2
chkuo@koa[/usr/local]$ sudo tar -jxvf bwa-0.7.17.tar.bz2
chkuo@koa[/usr/local]$ sudo chown -R root:root bwa-0.7.17
chkuo@koa[/usr/local]$ cd bwa-0.7.17
chkuo@koa[/usr/local/bwa-0.7.17]$ sudo make
chkuo@koa[/usr/local/bwa-0.7.17]$ sudo ln -s /usr/local/bwa-0.7.17/bwa /usr/local/bin/bwa
chkuo@koa[/usr/local/bwa-0.7.17]$ which bwa
/usr/local/bin/bwa
</code>



===== Bowtie =====
  * Bowtie - An ultrafast memory-efficient short read aligner
  * [[http://bowtie-bio.sourceforge.net/index.shtml]]
  * note: bowtie2 is better than bowtie1 for reads >50bp

<code bash>
# prerequisite: Threading Building Blocks library (TBB)
chkuo@koa[/usr/local]$ sudo apt-cache search tbb
chkuo@koa[/usr/local]$ sudo apt install libtbb-dev
# install
chkuo@koa[/usr/local]$ sudo wget https://sourceforge.net/projects/bowtie-bio/files/bowtie2/2.3.4.3/bowtie2-2.3.4.3-source.zip
chkuo@koa[/usr/local]$ sudo unzip bowtie2-2.3.4.3-source.zip
chkuo@koa[/usr/local]$ cd bowtie2-2.3.4.3
chkuo@koa[/usr/local/bowtie2-2.3.4.3]$ sudo make
chkuo@koa[/usr/local/bowtie2-2.3.4.3]$ sudo ln -s /usr/local/bowtie2-2.3.4.3/bowtie2 /usr/local/bin/bowtie2
chkuo@koa[/usr/local/bowtie2-2.3.4.3]$ sudo ln -s /usr/local/bowtie2-2.3.4.3/bowtie2-build /usr/local/bin/bowtie2-build
</code>

===== TopHat =====
  * TopHat - A spliced read mapper for RNA-Seq
  * [[http://ccb.jhu.edu/software/tophat/index.shtml]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://ccb.jhu.edu/software/tophat/downloads/tophat-2.0.13.Linux_x86_64.tar.gz
chkuo@cherry[/usr/local]$ sudo tar -xzvf tophat-2.0.13.Linux_x86_64.tar.gz 
chkuo@cherry[/usr/local]$ sudo chown -R root:root tophat-2.0.13.Linux_x86_64
chkuo@cherry[/usr/local]$ sudo ln -s /usr/local/tophat-2.0.13.Linux_x86_64/tophat /usr/local/bin/tophat
chkuo@cherry[/usr/local]$ sudo rm /usr/local/tophat-2.0.13.Linux_x86_64.tar.gz 
</code>

===== Minimap2 =====
  * Minimap2: A versatile pairwise aligner for genomic and spliced nucleotide sequences
  * https://lh3.github.io/minimap2

<code bash>
chkuo@koa[/usr/local]$ sudo curl -L https://github.com/lh3/minimap2/releases/download/v2.15/minimap2-2.15_x64-linux.tar.bz2 | sudo tar -jxvf -
chkuo@koa[/usr/local]$ sudo chown -R root:root minimap2-2.15_x64-linux
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/minimap2-2.15_x64-linux/minimap2 /usr/local/bin/minimap2
</code>


===== Cufflinks =====
  * Cufflinks - Transcript assembly, differential expression, and differential regulation for RNA-Seq
  * [[http://cole-trapnell-lab.github.io/cufflinks/]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://cole-trapnell-lab.github.io/cufflinks/assets/downloads/cufflinks-2.2.1.Linux_x86_64.tar.gz
chkuo@cherry[/usr/local]$ sudo tar -xzvf cufflinks-2.2.1.Linux_x86_64.tar.gz
chkuo@cherry[/usr/local]$ sudo chown -R root:root cufflinks-2.2.1.Linux_x86_64
chkuo@cherry[/usr/local]$ sudo ln -s /usr/local/cufflinks-2.2.1.Linux_x86_64/cufflinks /usr/local/bin/cufflinks
chkuo@cherry[/usr/local]$ sudo ln -s /usr/local/cufflinks-2.2.1.Linux_x86_64/cuffdiff /usr/local/bin/cuffdiff
chkuo@cherry[/usr/local]$ sudo ln -s /usr/local/cufflinks-2.2.1.Linux_x86_64/cuffcompare /usr/local/bin/cuffcompare
chkuo@cherry[/usr/local]$ sudo rm /usr/local/cufflinks-2.2.1.Linux_x86_64.tar.gz
</code>

===== SAMtools/BCFtools =====
  * SAM (Sequence Alignment/Map) format is a generic format for storing large nucleotide sequence alignments.
  * [[http://www.htslib.org/download/]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget https://github.com/samtools/samtools/releases/download/1.9/samtools-1.9.tar.bz2
chkuo@koa[/usr/local]$ sudo tar -jxvf samtools-1.9.tar.bz2
chkuo@koa[/usr/local]$ cd samtools-1.9
chkuo@koa[/usr/local/samtools-1.9]$ sudo make
chkuo@koa[/usr/local/samtools-1.9]$ sudo make install
</code>

<code bash>
chkuo@koa[/usr/local]$ sudo wget https://github.com/samtools/bcftools/releases/download/1.9/bcftools-1.9.tar.bz2
chkuo@koa[/usr/local]$ sudo tar -jxvf bcftools-1.9.tar.bz2
chkuo@koa[/usr/local]$ cd bcftools-1.9
chkuo@koa[/usr/local/bcftools-1.9]$ sudo make
chkuo@koa[/usr/local/bcftools-1.9]$ sudo make install
</code>

===== Picard =====
  * [[http://broadinstitute.github.io/picard/]]
  * Java-based command-line utilities that manipulate SAM files

<code bash>
chkuo@koa[/usr/local]$ sudo wget https://github.com/broadinstitute/picard/archive/2.18.20.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf 2.18.20.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root picard-2.18.20
</code>

===== HTSeq =====
  * [[https://htseq.readthedocs.io/en/master/]]
  * HTSeq: High-throughput sequence analysis in Python
  * Using pip install failed, so using apt install.[[https://ubuntu.pkgs.org/20.04/ubuntu-universe-arm64/python3-htseq_0.11.2-2build1_arm64.deb.html|pkgs.org for python3-htseq]]

<code bash>
hychang@koa:[~]$ sudo apt install python3-htseq
# [sudo] password for hychang: 
# Reading package lists... Done
# Building dependency tree       
# Reading state information... Done
# E: Unable to locate package python3-htseq
hychang@koa:[~]$ htseq-count --version
# 2.0.2
hychang@koa:[~]$ whereis htseq-count
# htseq-count: /usr/local/bin/htseq-count
</code>


===== khmer =====
  *[[https://github.com/ged-lab/khmer]]


<code bash>
# requires python-dev
chkuo@cherry[/usr/local]$ sudo apt-get install python-dev
# setuptools is required for nose
chkuo@cherry[/usr/local]$ sudo wget http://pypi.python.org/packages/2.7/s/setuptools/setuptools-0.6c11-py2.7.egg
chkuo@cherry[/usr/local]$ sudo sh setuptools-0.6c11-py2.7.egg 
# nose is required for screed
# screed is required for khmer
chkuo@cherry[/usr/local]$ sudo /usr/local/bin/easy_install nose
chkuo@cherry[/usr/local]$ sudo /usr/local/bin/easy_install virtualenv
chkuo@cherry[/usr/local]$ sudo python -m virtualenv env
chkuo@cherry[/usr/local]$ sudo chmod a+x ./env/bin/activate*
chkuo@cherry[/usr/local]$ source ./env/bin/activate
chkuo@cherry[/usr/local]$ sudo git clone git://github.com/ctb/screed.git
chkuo@cherry[/usr/local]$ sudo /usr/local/bin/easy_install screed
chkuo@cherry[/usr/local]$ sudo git clone git://github.com/ctb/khmer.git
chkuo@cherry[/usr/local/khmer]$ sudo make clean all
chkuo@cherry[/usr/local/khmer]$ sudo easy_install nose
chkuo@cherry[/usr/local/khmer]$ sudo make test
chkuo@cherry[/usr/local]$ sudo /usr/local/bin/easy_install /usr/local/khmer

</code>

===== KmerGenie =====
  *[[http://kmergenie.bx.psu.edu/]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://kmergenie.bx.psu.edu/kmergenie-1.6950.tar.gz
chkuo@cherry[/usr/local]$ sudo tar -xzvf kmergenie-1.6950.tar.gz 
chkuo@cherry[/usr/local]$ sudo chown -R root:root kmergenie-1.6950
chkuo@cherry[/usr/local]$ cd kmergenie-1.6950
chkuo@cherry[/usr/local/kmergenie-1.6950]$ sudo make clean
chkuo@cherry[/usr/local/kmergenie-1.6950]$ sudo make k=200
chkuo@cherry[/usr/local]$ sudo rm /usr/local/kmergenie-1.6950.tar.gz 
</code>
===== SPAdes =====
  * http://cab.spbu.ru/software/spades/

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://cab.spbu.ru/files/release3.15.0/SPAdes-3.15.0-Linux.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzf SPAdes-3.15.0-Linux.tar.gz
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/SPAdes-3.15.0-Linux/bin/spades.py /usr/local/bin/spades.py
</code>


===== 10X Supernova =====
  * [[https://support.10xgenomics.com/de-novo-assembly/software/overview/latest/welcome]]
  * De novo assembler for 10X Genomics Linked-Read Sequencing

<code bash>
chuan@koa:/usr/local$ sudo wget -O supernova-2.1.1.tar.gz "http://cf.10xgenomics.com/releases/assembly/supernova-2.1.1.tar.gz?Expires=1574703423&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cDovL2NmLjEweGdlbm9taWNzLmNvbS9yZWxlYXNlcy9hc3NlbWJseS9zdXBlcm5vdmEtMi4xLjEudGFyLmd6IiwiQ29uZGl0aW9uIjp7IkRhdGVMZXNzVGhhbiI6eyJBV1M6RXBvY2hUaW1lIjoxNTc0NzAzNDIzfX19XX0_&Signature=kbsBuCSa6ADfZycv8U1Onc7N3Sz1w0-gZViJRfJp7HClpJTLD-SjzcYvjw-6wR9yDX1KswanWLEOhx48b-6rgh44p73-t547E7esV2XIVgHjjWTlSM4KzHmvhu6j4mtDf~rj5tlM1fGfh-53SvZvNofGwElJo97VPbB-LDutDZp0lfrcDwU1vjizKCXLOlRFKmrR9x6-Njss0J7YFmOhgGqm32kzoffP9plLzV30O1~WGc0M5n8~ENTvvqgz3ACcv7Ue1KvR8ycN0vlNAmafKiNtt5tJvcSFD35xVreqC9ii22LoJHwbFxcC9X8PR24lmylpAt6yYcD1M7vn57krRw__&Key-Pair-Id=APKAI7S6A5RYOXBWRPDA"
chuan@koa:/usr/local$ sudo tar -xzf supernova-2.1.1.tar.gz
chuan@koa:/usr/local$ sudo ln -s /usr/local/supernova-2.1.1/supernova /usr/local/bin/supernova
</code>


===== 10X Longranger =====
  * [[https://support.10xgenomics.com/genome-exome/software/pipelines/latest/what-is-long-ranger]]
  * A set of analysis pipelines that processes Chromium sequencing (10X Genomics linked-read sequencing) output to align reads and call and phase SNPs, indels, and structural variants 

<code bash>
chuan@koa:/usr/local$ sudo wget -O longranger-2.2.2.tar.gz "http://cf.10xgenomics.com/releases/genome/longranger-2.2.2.tar.gz?Expires=1584541789&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cDovL2NmLjEweGdlbm9taWNzLmNvbS9yZWxlYXNlcy9nZW5vbWUvbG9uZ3Jhbmdlci0yLjIuMi50YXIuZ3oiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE1ODQ1NDE3ODl9fX1dfQ__&Signature=iUgYd~EJ5iVwEHFyUhBBMkJrfgDV0Ltnx28U7~eM9FpNFun4qG~3DEpl9XXrIeYPYJDlLcmvuusq6TUtCFxQaTP1AgA-rXUeEYt6p~IDUmr0j7V026cxh2sKfuYb4qLOeBaYwmCw9n6rjR1tXKremhPBttJX65Ar6T~xhzj9zBi3F3ELBJupKiHmVKOqW0RtkM2U8KMXMxFUmSH5JRLOoh3hG5~bg9-wzH-4uVH1fIccXnNlqzV4Nqw4yJZbaNZIhgqsmt64LX1MJ1fC1Z-HrwbOyrSjyTl62j3yBMCbW~S5DvQTd3P~1uToCqgyEoRueALpS6aKVD6eLBKpGe0p9A__&Key-Pair-Id=APKAI7S6A5RYOXBWRPDA"
chuan@koa:/usr/local$ sudo tar -xzf longranger-2.2.2.tar.gz
chuan@koa:/usr/local$ sudo ln -s /usr/local/longranger-2.2.2/longranger /usr/local/bin/longranger
# 4792320 barcodes on the whitelist: /usr/local/longranger-2.2.2/longranger-cs/2.2.2/tenkit/lib/python/tenkit/barcodes/4M-with-alts-february-2016.txt
</code>


===== ARCS =====
  * [[https://github.com/bcgsc/arcs]]
  * Scaffolding genome drafts with 10X Genomics linked reads

<code bash>
chuan@koa:/usr/local$ sudo wget https://github.com/bcgsc/arcs/archive/master.zip
chuan@koa:/usr/local$ sudo unzip master.zip
chuan@koa:/usr/local$ sudo mv arcs-master arcs-1.1.1
chuan@koa:/usr/local$ cd arcs-1.1.1/
chuan@koa:/usr/local/arcs-1.1.1$ sudo ./autogen.sh
chuan@koa:/usr/local/arcs-1.1.1$ sudo wget https://sourceforge.net/projects/boost/files/boost/1.58.0/boost_1_58_0.tar.bz2
chuan@koa:/usr/local/arcs-1.1.1$ sudo tar jxf boost_1_58_0.tar.bz2 
chuan@koa:/usr/local/arcs-1.1.1$ sudo ./configure –-with-boost=/usr/local/arcs-1.1.1/boost_1_58_0
chuan@koa:/usr/local/arcs-1.1.1$ sudo apt-get install libsparsehash-dev # dependency: google/sparse_hash_map
chuan@koa:/usr/local/arcs-1.1.1$ sudo make
chuan@koa:/usr/local/arcs-1.1.1$ sudo ln -s /usr/local/arcs-1.1.1/Arcs/arcs /usr/local/bin/arcs
# dependency: LINKS
chuan@koa:/usr/local$ sudo wget https://github.com/bcgsc/LINKS/releases/download/v1.8.7/links_v1-8-7.tar.gz 
chuan@koa:/usr/local$ sudo tar -xvf links_v1-8-7.tar.gz
chuan@koa:/usr/local$ sudo ln -s /usr/local/links_v1.8.7/LINKS /usr/local/bin/LINKS
</code>

===== Velvet =====
  * Sequence assembler for very short reads
  * [[http://www.ebi.ac.uk/~zerbino/velvet/]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.ebi.ac.uk/~zerbino/velvet/velvet_1.2.10.tgz
chkuo@koa[/usr/local]$ sudo tar xzf velvet_1.2.10.tgz 
chkuo@koa[/usr/local]$ sudo chown -R root:root velvet_1.2.10
chkuo@koa[/usr/local]$ sudo chmod 755 velvet_1.2.10
chkuo@koa[/usr/local]$ cd velvet_1.2.10
chkuo@koa[/usr/local/velvet_1.2.10]$ sudo make 'CATEGORIES=10' 'MAXKMERLENGTH=301' 'LONGSEQUENCES=1' 'OPENMP=1'
chkuo@koa[/usr/local/bin]$ sudo ln -s /usr/local/velvet_1.2.10/velvetg /usr/local/bin/velvetg
chkuo@koa[/usr/local/bin]$ sudo ln -s /usr/local/velvet_1.2.10/velveth /usr/local/bin/velveth
</code>

===== Velvet Optimiser =====
  *  VelvetOptimiser is a multi-threaded Perl script for automatically optimising the three primary parameter options (K, -exp_cov, -cov_cutoff) for the Velvet de novo sequence assembler. 
  * [[http://bioinformatics.net.au/software.velvetoptimiser.shtml]]

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.vicbioinformatics.com/VelvetOptimiser-2.2.5.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf VelvetOptimiser-2.2.5.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root VelvetOptimiser-2.2.5
chkuo@koa[/usr/local]$ sudo chmod 755 VelvetOptimiser-2.2.5
</code>


===== Oases =====
  * //De novo// transcriptome assembler for very short reads.
<code bash>
chkuo@koa[/usr/local]$ sudo wget http://www.ebi.ac.uk/~zerbino/oases/oases_0.2.08.tgz
chkuo@koa[/usr/local]$ sudo tar xzf oases_0.2.08.tgz 
chkuo@koa[/usr/local]$ sudo chown -R root:root oases_0.2.8
chkuo@koa[/usr/local]$ sudo chmod 755 oases_0.2.8
chkuo@koa[/usr/local]$ cd oases_0.2.8
chkuo@koa[/usr/local/oases_0.2.8]$ sudo make 'VELVET_DIR=/usr/local/velvet_1.2.10' 'CATEGORIES=10' 'MAXKMERLENGTH=301'
chkuo@koa[/usr/local/bin]$ sudo ln -s /usr/local/oases_0.2.8/oases /usr/local/bin/oases
</code>




===== Unicycler =====
  * https://github.com/rrwick/Unicycler

<code bash>
# 2023/09/07; v0.4.9b -> v0.5.0; chkuo
# 2020/04/29; v0.4.8b -> v0.4.9b; chkuo
chkuo@koa[/usr/local]$ sudo git clone https://github.com/rrwick/Unicycler.git
chkuo@koa[/usr/local]$ sudo mv Unicycler unicycler-0.5.0
chkuo@koa[/usr/local]$ cd unicycler-0.5.0
chkuo@koa[/usr/local/unicycler-0.5.0]$ sudo python3 setup.py install
chkuo@koa[/usr/local/unicycler-0.5.0]$ unicycler --version
Unicycler v0.5.0
</code>

===== ALLPATHS-LG =====
  * short read genome assembler from the Computational Research and Development group at the Broad Institute
  * [[http://www.broadinstitute.org/software/allpaths-lg/blog/]]


<code bash>
# prerequisites (note the order)
# GMP (https://gmplib.org/)
chkuo@koa[/usr/local]$ sudo apt install libgmp-dev
# MPFR (https://www.mpfr.org/)
chkuo@koa[/usr/local]$ sudo apt install libmpfr-dev
# MPC (http://www.multiprecision.org/mpc/)
chkuo@koa[/usr/local]$ sudo apt install libmpc-dev
# Picard (http://picard.sourceforge.net/); installed already
# graphviz (http://www.graphviz.org/)
chkuo@koa[/usr/local]$ sudo apt install graphviz
# g++ (v4.7.0 or higher according to AllPaths-LG manual
# IMPORTANT:
# Ubuntu 18.04 comes with gcc v7.3.0
# use v7.3.0 causes "make" to fail with these error messages
# 
# Makefile:2654: recipe for target 'CleanEfasta.o' failed
# make[1]: *** [CleanEfasta.o] Error 1
# make[1]: Leaving directory '/usr/local/allpathslg-52488/src'
# Makefile:284: recipe for target 'all-recursive' failed
# make: *** [all-recursive] Error 1
#
# install g++ v4.8 and use this version in the "./configure" step (see below; CXX/CXXPP options)
chkuo@koa[/usr/local]$ sudo apt install g++-4.8
# libieee
# IMPORTANT:
# Ubuntu 18.04 uses glibc v2.27
# which does not support libieee and causes "make" to fail with these error messages
#
# /usr/bin/ld: cannot find -lieee
# collect2: error: ld returned 1 exit status
# Makefile:2096: recipe for target 'RemodelGaps' failed
# make[1]: *** [RemodelGaps] Error 1
# make[1]: Leaving directory '/usr/local/allpathslg-52188/src'
# Makefile:284: recipe for target 'all-recursive' failed
# make: *** [all-recursive] Error 1
#
# install libieee1284-3 and create a symbolic link
chkuo@koa[/usr/local]$ sudo apt install libieee1284-3
chkuo@koa[/usr/local]$ sudo ln -s /usr/lib/x86_64-linux-gnu/libieee1284.so.3 /usr/lib/libieee.so
#
# start AllPaths-LG installation
chkuo@koa[/usr/local]$ sudo wget ftp://ftp.broadinstitute.org/pub/crd/ALLPATHS/Release-LG/latest_source_code/allpathslg-52488.tar.gz
chkuo@koa[/usr/local]$ sudo tar xzf allpathslg-52488.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root allpathslg-52488
chkuo@koa[/usr/local]$ sudo chmod 755 allpathslg-52488
chkuo@koa[/usr/local]$ cd allpathslg-52488
chkuo@koa[/usr/local/allpathslg-52488]$ sudo ./configure --prefix=/usr/local CXX=/usr/bin/g++-4.8 CXXPP=/usr/bin/cpp-4.8
chkuo@koa[/usr/local/allpathslg-52488]$ sudo make
chkuo@koa[/usr/local/allpathslg-52488]$ sudo make install
</code>


===== MIRA =====
  * [[http://sourceforge.net/p/mira-assembler/wiki/Home/]]
  * [[http://sourceforge.net/projects/mira-assembler/]]
  * [[http://mira-assembler.sourceforge.net/docs/DefinitiveGuideToMIRA.html]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://sourceforge.net/projects/mira-assembler/files/MIRA/stable/mira_4.0rc5_linux-gnu_x86_64_static.tar.bz2
chkuo@cherry[/usr/local]$ sudo tar -jxvf mira_4.0rc5_linux-gnu_x86_64_static.tar.bz2
chkuo@cherry[/usr/local]$ sudo chown -R root:root mira_4.0rc5_linux-gnu_x86_64_static
chkuo@cherry[/usr/local]$ sudo chmod 755 mira_4.0rc5_linux-gnu_x86_64_static
chkuo@cherry[/usr/local]$ sudo ln -s /usr/local/mira_4.0rc5_linux-gnu_x86_64_static/bin/mira /usr/local/bin/mira
chkuo@cherry[/usr/local]$ sudo rm mira_4.0rc5_linux-gnu_x86_64_static.tar.bz2
</code>

===== Celera Assembler =====
  * [[http://sourceforge.net/apps/mediawiki/wgs-assembler/index.php?title=Main_Page]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://sourceforge.net/projects/wgs-assembler/files/wgs-assembler/wgs-8.1/wgs-8.1-Linux-amd64.tar.bz2
chkuo@cherry[/usr/local]$ sudo tar -jxvf wgs-8.1-Linux-amd64.tar.bz2
chkuo@cherry[/usr/local]$ sudo chown -R root:root wgs-8.1
chkuo@cherry[/usr/local]$ sudo chmod 755 wgs-8.1
chkuo@cherry[/usr/local]$ sudo rm wgs-8.1-Linux-amd64.tar.bz2
</code>


===== PacBio SMRT Analysis =====
  * [[http://www.pacb.com/devnet/]]

<code bash>
# Software Requirement
#   MySQL 5 (apt-get install mysql-server)
#   Perl (v5.10.1) Statistics::Descriptive Perl module: sudo cpan Statistics::Descriptive
# create 'smrtanalysis' user with sudo privileges (add to 'adm' and 'sudo' group)
smrtanalysis@cherry[/opt]$ sudo wget http://files.pacb.com/software/smrtanalysis/2.1.1/smrtanalysis-2.1.1-ubuntu-12.04.run
smrtanalysis@cherry[/opt]$ sudo chown smrtanalysis:smrtanalysis smrtanalysis-2.1.1-ubuntu-12.04.run
smrtanalysis@cherry[/opt]$ SMRT_ROOT=/opt/smrtanalysis
smrtanalysis@cherry[/opt]$ sudo mkdir $SMRT_ROOT
smrtanalysis@cherry[/opt]$ sudo chown smrtanalysis:smrtanalysis $SMRT_ROOT
smrtanalysis@cherry[/opt]$ bash smrtanalysis-2.1.1-ubuntu-12.04.run --rootdir $SMRT_ROOT

# requires remote access by SMRT Portal, abort installation
</code>


===== AMOS =====
  * A Modular, Open-Source whole genome assembler
  * [[http://sourceforge.net/projects/amos/]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://sourceforge.net/projects/amos/files/amos/3.1.0/amos-3.1.0.tar.gz
chkuo@cherry[/usr/local]$ sudo tar xzf amos-3.1.0.tar.gz
chkuo@cherry[/usr/local]$ sudo chown -R root:root amos-3.1.0
chkuo@cherry[/usr/local]$ sudo chmod 755 amos-3.1.0
chkuo@cherry[/usr/local]$ cd amos-3.1.0/
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo aptitude install ash coreutils gawk gcc automake libboost-dev
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo apt-get install libqt4-core
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo apt-get install libqt4-dev
# http://seqanswers.com/forums/showthread.php?t=17802
#   edit 'src/Align/find-tandem.cc'
#   add '#include <getopt.h>'
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo ./configure
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo make
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo make check
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo make install
chkuo@cherry[/usr/local/amos-3.1.0]$ sudo ln -s /usr/local/amos-3.1.0/bin/* /usr/local/bin/
</code>




===== Phusion =====
  * Phusion is a software package for assembling genome sequences from whole genome shotgun(WGS) reads.
  * There are a number of stages in the pipeline. One of the key elements in the assembler system is that it clusters the reads into sensible groups and each group of reads is treated independent of others for reads alignment and consensus generation to form initial contigs. This allows a parallelised approach in this computational intensive stage. The software package phrap is used in the process of initial contig building. Read pair information is applied extensively in the contig and supercontig construction.
  * [[http://www.sanger.ac.uk/resources/software/phusion/]]

<code bash>
chkuo@cherry[/usr/local]$ sudo wget ftp://ftp.sanger.ac.uk/pub4/resources/software/phusion/phusion_pipeline_v2.1c.tar.gz
chkuo@cherry[/usr/local]$ sudo tar -xzvf phusion_pipeline_v2.1c.tar.gz 
# note: need to install tcsh first
chkuo@cherry[/usr/local/phusion_pipeline_v2.1c]$ sudo ./install.csh 
</code>

===== MaSuRCa =====
  * MaSuRCA (Maryland Super Read Cabog Assembler) genome assembly and analysis toolkit 
  * Hybrid assembler of short and long reads
  * https://github.com/alekseyzimin/masurca

<code bash>
chuan@koa[/usr/local]$ sudo wget https://github.com/alekseyzimin/masurca/releases/download/v4.0.3/MaSuRCA-4.0.3.tar.gz
chuan@koa[/usr/local]$ sudo tar xzf MaSuRCA-4.0.3.tar.gz
chuan@koa[/usr/local]$ cd MaSuRCA-4.0.3
chuan@koa[/usr/local/MaSuRCA-4.0.3]$ sudo BOOST_ROOT=install ./install.sh
</code>

===== Racon =====
  * Consensus module for raw de novo DNA assembly of long uncorrected reads
  * https://github.com/isovic/racon

<code bash>
chkuo@koa[/usr/local]$ sudo git clone --recursive https://github.com/isovic/racon.git racon
chkuo@koa[/usr/local]$ cd racon
chkuo@koa[/usr/local/racon]$ sudo mkdir build
chkuo@koa[/usr/local/racon]$ cd build
chkuo@koa[/usr/local/racon/build]$ sudo cmake -DCMAKE_BUILD_TYPE=Release ..
chkuo@koa[/usr/local/racon/build]$ sudo make
chkuo@koa[/usr/local/racon/build]$ sudo ln -s /usr/local/racon/build/bin/racon /usr/local/bin/racon
</code>

===== Raven =====
  * Raven is a de novo genome assembler for long uncorrected reads.
  * https://github.com/lbcb-sci/raven

<code bash>
chuan@koa[/usr/local]$ sudo git clone https://github.com/lbcb-sci/raven
chuan@koa[/usr/local]$ cd raven
chuan@koa[/usr/local/raven]$ sudo mkdir build
chuan@koa[/usr/local/raven]$ cd build
chuan@koa[/usr/local/raven/build]$ sudo cmake -DCMAKE_BUILD_TYPE=Release ..
chuan@koa[/usr/local/raven/build]$ sudo make
chkuo@koa[/usr/local/raven/build]$ sudo ln -s /usr/local/raven/build/bin/raven /usr/local/bin/raven
</code>

===== NextPolish =====
  * NextPolish is used to fix base errors (SNV/Indel) in the genome generated by noisy long reads.
  * https://github.com/Nextomics/NextPolish

<code bash>
chuan@koa[/usr/local]$ sudo wget https://github.com/Nextomics/NextPolish/releases/download/v1.3.1/NextPolish.tgz
chuan@koa[/usr/local]$ sudo tar -xzf NextPolish.tgz && cd NextPolish && make
</code>

===== NextDenovo =====
  * NextDenovo is a string graph-based de novo assembler for long reads (CLR, HiFi and ONT).
  * https://github.com/Nextomics/NextDenovo

<code bash>
chuan@koa[/usr/local]$ sudo wget https://github.com/Nextomics/NextDenovo/releases/download/v2.4.0/NextDenovo.tgz
chuan@koa[/usr/local]$ sudo tar -xzf NextDenovo.tgz && cd NextDenovo
</code>

===== Pilon =====
  * https://github.com/broadinstitute/pilon

<code bash>
chkuo@koa[/usr/local/bin]$ sudo wget https://github.com/broadinstitute/pilon/releases/download/v1.23/pilon-1.23.jar
chkuo@koa[/usr/local/bin]$ sudo chmod 755 pilon-1.23.jar
</code>

===== PAGIT =====
  * PAGIT - Post Assembly Genome Improvement Toolkit
  * [[http://www.sanger.ac.uk/resources/software/pagit/]]


<code bash>
chkuo@koa[/usr/local/PAGIT.V1.01]$ sudo wget ftp://ftp.sanger.ac.uk/pub/resources/software/pagit/PAGIT.V1.01.64bit.tgz
chkuo@koa[/usr/local/PAGIT.V1.01]$ sudo tar xzf PAGIT.V1.64bit.tgz
chkuo@koa[/usr/local/PAGIT.V1.01]$ sudo chown -R root:root *
chkuo@koa[/usr/local/PAGIT.V1.01]$ sudo ./installme.sh 
chkuo@koa[/usr/local/PAGIT.V1.01]$ sudo rm PAGIT.V1.64bit.tgz
</code>
===== SOMA =====
  * Scaffolding using Optical Map Alignment, a tool to automatically place genomic sequences on an optical restriction map.
  * [[http://www.cbcb.umd.edu/soma/]]
  * [[http://bioinformatics.oxfordjournals.org/content/24/10/1229.full]]
<code bash>
chkuo@cherry[/usr/local]$ sudo wget http://www.cbcb.umd.edu/finishing/soma-v2.tar.gz
chkuo@cherry[/usr/local]$ sudo tar xzf soma-v2.tar.gz 
chkuo@cherry[/usr/local]$ sudo chown -R root:root soma-v2
chkuo@cherry[/usr/local]$ sudo chmod 755 soma-v2
chkuo@cherry[/usr/local]$ sudo ln -s soma-v2 soma
chkuo@cherry[/usr/local/soma/src]$ sudo make install
chkuo@cherry[/usr/local/soma/bin]$ sudo chmod a+x *.pl
chkuo@cherry[/usr/local]$ sudo rm /usr/local/soma-v2.tar.gz
</code>



===== CheckM =====
  * Assessing the quality of microbial genomes
  * [[https://github.com/Ecogenomics/CheckM]]

<code bash>
# 2021/09/27; chkuo
chkuo@koa[/usr/local]$ sudo wget https://github.com/matsen/pplacer/releases/download/v1.1.alpha19/pplacer-linux-v1.1.alpha19.zip 
chkuo@koa[/usr/local]$ sudo unzip pplacer-linux-v1.1.alpha19.zip 
chkuo@koa[/usr/local]$ sudo chown -R root:root pplacer-*
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/pplacer-Linux-v1.1.alpha19/guppy /usr/local/bin/guppy
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/pplacer-Linux-v1.1.alpha19/pplacer /usr/local/bin/pplacer
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/pplacer-Linux-v1.1.alpha19/rppr /usr/local/bin/rppr

# CheckM v1.1.3
chkuo@koa[~]$ sudo -H pip3 install numpy
chkuo@koa[~]$ sudo -H pip3 install matplotlib
chkuo@koa[~]$ sudo -H pip3 install pysam
chkuo@koa[~]$ sudo -H pip3 install checkm-genome
chkuo@koa[/usr/local/checkm]$ sudo wget https://data.ace.uq.edu.au/public/CheckM_databases/checkm_data_2015_01_16.tar.gz
chkuo@koa[/usr/local/checkm]$ sudo tar xzvf checkm_data_2015_01_16.tar.gz
chkuo@koa[~]$ sudo checkm data setRoot /usr/local/checkm
chkuo@koa[~]$ checkm
</code>


===== Originx =====
  * Origin of Replication in Circular Prokaryotic Chromosomes
  * [[http://www.cbs.dtu.dk/services/GenomeAtlas/suppl/origin/]]
<code bash>
chkuo@cherry[/usr/local/originx]$ sudo wget http://www.cbs.dtu.dk/services/GenomeAtlas-2.0/suppl/origin/originx.source.tar.gz
chkuo@cherry[/usr/local/originx]$ sudo tar -xzvf originx.source.tar.gz 
chkuo@cherry[/usr/local/originx]$ sudo chown -R root:root *
chkuo@cherry[/usr/local/originx/src]$ sudo make
chkuo@cherry[/usr/local/originx/src]$ sudo ln -s /usr/local/originx/src/originx /usr/local/bin/originx
chkuo@cherry[/usr/local/originx]$ sudo rm /usr/local//originx/originx.source.tar.gz  
</code>

===== MEME =====
  * [[http://meme-suite.org/index.html]]
  * Motif-based sequence analysis tool
  * **WARNING** 
    * As of 2020/04/28, this does not work properly on koa (Ubuntu 18.04 server)
    * Lin Chou tried to install v5.1.1 on his workstation (Ubuntu 18.04 desktop) following the steps below and it works


<code bash>
chkuo@koa[/usr/local]$ sudo wget http://meme-suite.org/meme-software/5.1.1/meme-5.1.1.tar.gz
chkuo@koa[/usr/local]$ sudo tar -zxvf meme-5.1.1.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root meme-5.1.1
# check Perl dependencies
# if something is missing, use ''sudo cpan XXX::YYY'' to install
chkuo@koa[/usr/local/meme-5.1.1/scripts]$ perl dependencies.pl 
# configure and install
chkuo@koa[/usr/local/meme-5.1.1]$ sudo ./configure --prefix=/usr/local/meme-5.1.1 --with-url=http://meme-suite.org/ --enable-build-libxml2 --enable-build-libxslt 
chkuo@koa[/usr/local/meme-5.1.1]$ sudo make 
chkuo@koa[/usr/local/meme-5.1.1]$ sudo make test 
chkuo@koa[/usr/local/meme-5.1.1]$ sudo make install
# note
# see install guide: http://meme-suite.org/doc/install.html
# add this line:
# ''export PATH=/usr/local/meme-5.1.1/bin:/usr/local/meme-5.1.1/libexec/meme-5.1.1:$PATH''
# to ''.profile''
</code>


===== hmmer =====
  * [[http://hmmer.janelia.org/]]
  * NOTE: v3.0 does not work with rnammer-1.2

<code bash>
# require Getopt
chkuo@koa[/usr/local]$ sudo perl -e shell -MCPAN
cpan>install Getopt::Std
cpan>install Getopt::Long
chkuo@koa[/usr/local]$ sudo apt install libperl4-corelibs-perl
#
chkuo@koa[/usr/local]$ sudo wget http://eddylab.org/software/hmmer/hmmer-2.3.2.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf hmmer-2.3.2.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root hmmer-2.3.2
chkuo@koa[/usr/local]$ cd hmmer-2.3.2/
chkuo@koa[/usr/local/hmmer-2.3.2]$ sudo ./configure 
chkuo@koa[/usr/local/hmmer-2.3.2]$ sudo make
chkuo@koa[/usr/local/hmmer-2.3.2]$ sudo make check
chkuo@koa[/usr/local/hmmer-2.3.2]$ sudo make install
</code>

===== hmmer3 =====
  * required by Orthofisher
<code bash>
chuan@koa[/usr/local]$ sudo wget http://eddylab.org/software/hmmer/hmmer.tar.gz
chuan@koa[/usr/local]$ sudo tar zxf hmmer.tar.gz
chuan@koa[/usr/local]$ cd hmmer-3.3.2
chuan@koa[/usr/local/hmmer-3.3.2]$ sudo ./configure --prefix /usr/local/hmmer-3.3.2
chuan@koa[/usr/local/hmmer-3.3.2]$ sudo make
chuan@koa[/usr/local/hmmer-3.3.2]$ sudo make check
chuan@koa[/usr/local/hmmer-3.3.2]$ sudo make install
</code>
===== RNAmmer =====
  * Predicts 5s/8s, 16s/18s, and 23s/28s ribosomal RNA in full genome sequences
  * [[http://www.cbs.dtu.dk/services/RNAmmer/]]
  * requires [[http://hmmer.janelia.org/|hmmer]]
  * request the source code from the [[http://www.cbs.dtu.dk/cgi-bin/nph-sw_request?rnammer|download]] page
<code bash>
chkuo@koa[/usr/local/rnammer-1.2]$ sudo uncompress rnammer-1.2.src.tar.Z 
chkuo@koa[/usr/local/rnammer-1.2]$ sudo tar xvf rnammer-1.2.src.tar 
</code>
  * the executable 'rnammer' is a wrapper script, modify '$INSTALL_PATH' and '$HMMSEARCH_BINARY'
  * delete the two '--cpu 1' in 'core-rnammer' (lines 114 and 187)

===== tRNAscan-SE =====
  * Search for tRNA genes in genomic sequences 
  * [[http://lowelab.ucsc.edu/tRNAscan-SE/]]
<code bash>
chkuo@koa[/usr/local]$ sudo wget http://lowelab.ucsc.edu/software/tRNAscan-SE.tar.gz
chkuo@koa[/usr/local]$ sudo tar -xzvf tRNAscan-SE.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root tRNAscan-SE-1.3.1
chkuo@koa[/usr/local]$ sudo chmod 755 tRNAscan-SE-1.3.1
chkuo@koa[/usr/local]$ cd tRNAscan-SE-1.3.1
# edit Makefile
# BINDIR  = /usr/local/bin
# LIBDIR  = /usr/local/lib/tRNAscan-SE
# MANDIR  = /usr/local/man
chkuo@koa[/usr/local/tRNAscan-SE-1.3.1]$ sudo emacs Makefile
chkuo@koa[/usr/local/tRNAscan-SE-1.3.1]$ sudo make
chkuo@koa[/usr/local/tRNAscan-SE-1.3.1]$ sudo make install
chkuo@koa[/usr/local/tRNAscan-SE-1.3.1]$ sudo make testrun
chkuo@koa[/usr/local/tRNAscan-SE-1.3.1]$ sudo make cleanup
# fix permission
chkuo@koa[/usr/local]$ sudo chmod 755 /usr/local/bin/tRNAscanSE
# fix error: "Can't locate tRNAscanSE/Utils.pm in @INC"
# add 'use lib "/usr/local/bin";' to '/usr/local/bin/tRNAscan-SE' (insert at line 28)
#
# alternative solution for individual users:
# add the following line to .bashrc
# export PERL5LIB="${PERL5LIB}:/usr/local/bin"
</code>


===== Prodigal =====
  * Prokaryotic Dynamic Programming Genefinding Algorithm
  * [[https://github.com/hyattpd/Prodigal]]
<code bash>
chkuo@koa[/usr/local]$ sudo git clone git://github.com/hyattpd/Prodigal.git
chkuo@koa[/usr/local]$ cd Prodigal/
chkuo@koa[/usr/local/Prodigal]$ sudo make
chkuo@koa[/usr/local/Prodigal]$ sudo ln -s /usr/local/Prodigal/prodigal /usr/local/bin/prodigal
chkuo@koa[/usr/local/Prodigal]$ prodigal -v
Prodigal V2.6.3: February, 2016
</code>



===== Augustus =====
  * Gene prediction for eukaryotic genomes (ab initio, reference-assisted or in a comparative way)
  * [[https://github.com/Gaius-Augustus/Augustus.git]]
<code bash>
chuan@koa[~]$ sudo apt install augustus augustus-data augustus-doc
# run augustus
chuan@koa[~]$ augustus

#chuan@koa[/usr/local]$ sudo git clone https://github.com/Gaius-Augustus/Augustus.git
#chuan@koa[/usr/local]$ cd Augustus
#chuan@koa[/usr/local/Augustus]$ sudo docker build -t augustus .
# append USER to docker
#chuan@koa[/usr/local/Augustus]$ sudo usermod -a -G docker USER
# run augustus
#chuan@koa[/usr/local/Augustus]$ sudo docker run augustus /root/augustus/bin/augustus
</code>

===== TMHMM =====
  * Prediction of transmembrane helices in proteins
  * [[http://www.cbs.dtu.dk/cgi-bin/nph-sw_request?tmhmm]]
  * Compiled executable is available for academic users by email
<code bash>
chkuo@koa[/usr/local]$ sudo tar -xzvf tmhmm-2.0c.Linux.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root tmhmm-2.0c
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/tmhmm-2.0c /usr/local/tmhmm
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/tmhmm/bin/decodeanhmm.Linux_x86_64 /usr/local/bin/decodeanhmm
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/tmhmm/bin/tmhmm /usr/local/bin/tmhmm
# edit the wrapper script
chkuo@koa[/usr/local]$ sudo emacs /usr/local/tmhmm/bin/tmhmm
# modify the path to perl (line 1): 
#!/usr/bin/perl
# uncomment and modify the basedir setting (line 13): 
# $opt_basedir = "/usr/local/tmhmm/"; # basis directory for TMHMM package
</code>
  * Usage: 
<code bash>
cat /scratch/chkuo/test/test.fasta  | /usr/local/bin/decodeanhmm -f /usr/local/tmhmm/lib/TMHMM2.0.options -modelfile /usr/local/tmhmm/lib/TMHMM2.0.model
</code>


===== SignalP =====
  * Predicts the presence and location of signal peptide cleavage sites in amino acid sequences.
  * [[https://services.healthtech.dtu.dk/services/SignalP-6.0/]]



<code bash>
# 2024/02/07
# fast
chkuo@koa[/usr/local]$ sudo tar -xzvf signalp-6.0h.fast.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root signalp6_fast
chkuo@koa[/usr/local]$ sudo pip3 install /usr/local/signalp6_fast/signalp-6-package/
# slow
chkuo@koa[/usr/local]$ sudo tar -xzvf signalp-6.0h.slow_sequential.tar.gz
chkuo@koa[/usr/local]$ sudo chown -R root:root signalp6_slow_sequential
chkuo@koa[/usr/local]$ sudo pip3 install /usr/local/signalp6_slow_sequential/signalp-6-package/

chkuo@koa[/usr/local]$ which signalp6
/usr/local/bin/signalp6
chkuo@koa[/usr/local]$ signalp6 --version
SignalP 6.0 Signal peptide prediction tool 6.0h
</code>

<code bash>
chkuo@koa[/usr/local]$ sudo tar -xzvf signalp-5.0.Linux.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root signalp-5.0
chkuo@koa[/usr/local]$ /usr/local/signalp-5.0/bin/signalp -version
SignalP version 5.0 Linux x86_64
</code>


<code bash>
chkuo@koa[/usr/local]$ sudo tar -xzvf signalp-4.1c.Linux.tar.gz 
chkuo@koa[/usr/local]$ sudo chown -R root:root signalp-4.1
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/signalp-4.1/signalp /usr/local/bin/signalp
# edit the wrapper script according to the installation guide (line 13)
# $ENV{SIGNALP} = '/usr/local/signalp-4.1';
chkuo@koa[/usr/local]$ sudo emacs /usr/local/bin/signalp
</code>

<code bash>
# SignalP v3.0 (for testing; version date: 2007/03/05; installation date: 2018/01/31)
chkuo@cherry[/usr/local]$ sudo tar -xzvf signalp-3.0.Linux.tar.Z
chkuo@cherry[/usr/local]$ sudo chown -R root:root signalp-3.0
# edit the wrapper script according to the installation guide (line 13)
# SIGNALP=/usr/local/signalp-3.0
chkuo@cherry[/usr/local]$ sudo emacs /usr/local/bin/signalp
</code>

===== tbl2asn =====
  * a command-line program that automates the creation of sequence records for submission to GenBank
  * [[http://www.ncbi.nlm.nih.gov/genbank/tbl2asn2]]
<code bash>
chkuo@koa[/usr/local/bin]$ sudo wget ftp://ftp.ncbi.nih.gov/toolbox/ncbi_tools/converters/by_program/tbl2asn/linux64.tbl2asn.gz
chkuo@koa[/usr/local/bin]$ sudo gunzip linux64.tbl2asn.gz
chkuo@koa[/usr/local/bin]$ sudo chmod 755 linux64.tbl2asn 
chkuo@koa[/usr/local/bin]$ sudo ln -s /usr/local/bin/linux64.tbl2asn /usr/local/bin/tbl2asn
</code>

===== Circos =====
  * http://circos.ca/software/download/circos/

<code bash>
chkuo@koa[/usr/local]$ sudo wget http://circos.ca/distribution/circos-0.69-9.tgz
chkuo@koa[/usr/local]$ sudo tar -xzvf circos-0.69-9.tgz
chkuo@koa[/usr/local]$ sudo chown -R root:root circos-0.69-9
# make symbolic link
chkuo@koa[/usr/local]$ sudo ln -s /usr/bin/env /bin/env
chkuo@koa[/usr/local]$ sudo ln -s /usr/local/circos-0.69-9/bin/circos /usr/local/bin/circos
# get a list of required perl modules
chkuo@koa[/usr/local]$ circos -modules
# install missing modules
chkuo@koa[/usr/local]$ sudo perl -MCPAN -e shell
cpan[1]> install Config::General
cpan[2]> install Font::TTF::Font
cpan[3]> install Math::Bezier
cpan[4]> install Math::Round
cpan[5]> install Math::VecStat
cpan[6]> install Params::Validate
cpan[7]> install Regexp::Common
cpan[8]> install Set::IntSpan
cpan[9]> install Statistics::Basic
cpan[10]> install Text::Format
# check again to make sure that all tests are ok
chkuo@koa[/usr/local]$ circos -modules
# test man page
chkuo@koa[/usr/local]$ circos -man
# update setting
# change "file_delim = \s" to "file_delim = \t" (line 22)
chkuo@koa[/usr/local]$ sudo emacs /usr/local/circos-0.69-9/etc/housekeeping.conf
# check version
chkuo@koa[/usr/local]$ circos -v
circos | v 0.69-8 | 15 Jun 2019 | Perl 5.026001
# note:
# the version number in v0.69-9 was not updated
# even though it said v0.69-8, this is truly v0.69-9
# see 
# https://groups.google.com/d/msg/circos-data-visualization/Yr9XOkevEq8/FWMc5w3lAQAJ
</code>


===== FastANI =====
  * FastANI is developed for fast alignment-free computation of whole-genome Average Nucleotide Identity (ANI)
  * https://github.com/ParBLiSS/FastANI

<code bash>
# 2024/04/02
# note: v1.34 has some error message; use v1.33 for now
chkuo@koa[/usr/local/bin]$ sudo wget https://github.com/ParBLiSS/FastANI/releases/download/v1.33/fastANI-Linux64-v1.33.zip
chkuo@koa[/usr/local/bin]$ sudo unzip fastANI-Linux64-v1.33.zip
Archive:  fastANI-Linux64-v1.33.zip
  inflating: fastANI   
chkuo@koa[/usr/local/bin]$ sudo mv fastANI fastANI_v1.33
</code>


===== parallel =====
  * GNU parallel is a shell tool for executing jobs in parallel using one or more computers.
  * http://www.gnu.org/software/parallel

<code bash>
# 2024/07/29
hychang@koa[~]$ sudo apt install parallel
hychang@koa[~]$ parallel --version
GNU parallel 20161222
Copyright (C) 2007,2008,2009,2010,2011,2012,2013,2014,2015,2016
Ole Tange and Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
GNU parallel comes with no warranty.

Web site: http://www.gnu.org/software/parallel

When using programs that use GNU Parallel to process data for publication
please cite as described in 'parallel --citation'.

</code>


===== HH-suite =====
  * The HH-suite is an open-source software package for sensitive protein sequence searching based on the pairwise alignment of hidden Markov models (HMMs).
  * https://manpages.ubuntu.com/manpages/lunar/man1/hhsearch.1.html

<code bash>
# 2024/07/29
# note: 
hychang@koa[~]$ sudo apt install hhsuite
hychang@koa[~]$ hhsearch

HHsearch 3.0.0 (15-03-2015)
Search a database of HMMs with a query alignment or query HMM
(C) Johannes Soeding, Michael Remmert, Andreas Biegert, Andreas Hauser
Soding, J. Protein homology detection by HMM-HMM comparison. Bioinformatics 21:951-960 (2005).

Usage: hhsearch -i query -d database [options]
...

</code>