New upstream version 6.0.8+dfsg

  - tar xzf diamond-linux64.tar.gz

  - mkdir ~/bin

  - cp diamond ~/bin

  - perl proteinortho*pl -project=testasd -cpus=1 -ram=100 -verbose=2 -selfblast -silent -force -desc -checkfasta -cleanblast -debug -binpath=~/bin -tmp='~/' -e=0.000001 -sim=0.9 -identity=20 -cov=30 -subparaBlast='--more-sensitive' -synteny -dups=1 -cs=4 -alpha=0.4 -conn=0.01 -purity=0.00001 -minspecies=2 -subparaCluster='-cpus 1 -seed 1' -nograph -singles -xml -exactstep3 test/*faa >/dev/null 2>&1 && rm testasd*info* && export LC_NUMERIC="C" && export LC_ALL="C" && for f in testasd.*; do sort $f >$f.testasd; done; sha256sum -b *testasd | tr -d '\n' | awk '{if($0 == "eb88ba29afd4f2dba16d3dbf97a5b0d2ab7686654a854f8502f0e778628e7f56 *testasd.descriptions.testasd120f22094e2d6a75fb650523c7b5c2763a316aa7f8884dff0cbe3ccd002c9e1e *testasd.ffadj-graph.testasd9ad470e29be4937c6f4996f80221ede51670824bb2e4bb4a50946062a130ffd7 *testasd.poff.html.testasd4f8263bb4b2738e528635f3e121c659407119a1aecafb5340c9d28f5bd66cdaf *testasd.poff.tsv.testasd26d7f5d7b87dd7b71b4920753dc65e7c303e89cdfa56d3aaf00033c7918e6d10 *testasd.poff.tsv.xml.testasdf80df4c1a951bfb55b02300a273f6395694f01e8ae908e296d9c14a847d432ac *testasd.proteinortho.html.testasdfa18e9a0530f5a5754f045cfe97deaf818bdb5eb725619952633f1da0641cf7b *testasd.proteinortho.tsv.testasdc598b8c43e48e06614ec19e2f6b870e2737a7117a50ab2b1613880764d0884b2 *testasd.proteinortho.tsv.xml.testasd"){print $0." -> OK"; exit 0}else{print $0." -> failed"; exit 1}}'

  - perl proteinortho*pl -project=testasd -cpus=1 -ram=100 -verbose=2 -selfblast -silent -force -desc -checkfasta -cleanblast -debug -binpath=~/bin -tmp='~/' -e=0.000001 -sim=0.9 -identity=20 -cov=30 -subparaBlast='--more-sensitive' -synteny -dups=1 -cs=4 -alpha=0.4 -conn=0.01 -purity=0.00001 -minspecies=2 -subparaCluster='-cpus 1 -seed 1' -nograph -singles -xml -exactstep3 test/*faa >/dev/null 2>&1 && rm testasd*poff* && rm testasd*fadj* && rm testasd*info* && export LC_NUMERIC="C" && export LC_ALL="C" && for f in testasd.*; do sort $f >$f.testasd; done; sha256sum -b *testasd | tr -d '\n' | awk '{if($0 == "eb88ba29afd4f2dba16d3dbf97a5b0d2ab7686654a854f8502f0e778628e7f56 *testasd.descriptions.testasdf80df4c1a951bfb55b02300a273f6395694f01e8ae908e296d9c14a847d432ac *testasd.proteinortho.html.testasdfa18e9a0530f5a5754f045cfe97deaf818bdb5eb725619952633f1da0641cf7b *testasd.proteinortho.tsv.testasdc598b8c43e48e06614ec19e2f6b870e2737a7117a50ab2b1613880764d0884b2 *testasd.proteinortho.tsv.xml.testasd"){print $0." -> OK"; exit 0}else{print $0." -> failed"; exit 1}}'

gcc-latest-all-p:

  image: gcc

  stage: recompile-and-test

  script:

  #- apt-get -y install libboost-all-dev

  - export CWD=$(pwd)

  - echo "installing last"

  - wget http://last.cbrc.jp/last-982.zip && unzip last*zip 2>/dev/null && cd last*/ && make && cp src/last* $HOME

  - cd $CWD && echo "installing usearch"

  - curl https://drive5.com/cgi-bin/upload3.py?license=2019070410321731111 --output $HOME/usearch && chmod +x $HOME/usearch

  #- echo "installing rapsearch"

  #- git clone https://github.com/zhaoyanswill/RAPSearch2 && cd RAP*/Src && make && mv *rapsearch* $HOME && cd ../../ 

  - cd $CWD && echo "installing mmseqs2"

  - git clone https://github.com/soedinglab/MMseqs2 && cd MMs* && cmake . && make && cp src/mmseqs $HOME && cd ..

  - cd $CWD && echo "installing blat"

	updated shebang of ffadj such that python2.7 is used directly (ffadj fails if called with higher version of python)

	-p=blastp is now alias of blastp+ and legacy blast is now -p=blastp_legacy (blastn is equivalent)

	Makefile: static now includes -lquadmath

    25. Sept (uid: 3899)

	synteny update to python3 (but the code looks fishy, the -synteny option now gets a deprecated warning)

	proteinortho now only print html for <10 files automatically and otherwise only gives the option

3813

3899

# Run 'make install' for installing the compiled files to /usr/local/bin

# Run 'make install PREFIX=/home/paul/bin/' for local installation

############ FLAGS: ##########################################

############ OPTIONS: ##########################################

## STATIC=TRUE : enable static compiling (default:FALSE) 

## CXX=g++ : the g++ compiler

## CXXFLAGS = compiler flags passed to g++

## CXXLIBRARY = the path to the libs like lapack,... (dont forget the -L)

## CXXINCLUDE = include path (^) (dont forget the -I)

## PREFIX = the installation prefix (only for make install)

##############################################################

################################################################

##########################

## enviroment variables ##

# compile statically

STATIC=FALSE

ifdef static

STATIC=$(static)

endif

ifdef PREFIX

INSTALLDIR=$(PREFIX)

endif

ifdef prefix

INSTALLDIR=$(prefix)

endif

ifdef installdir

INSTALLDIR=$(installdir)

endif

ifdef LAPACK

USELAPACK=$(LAPACK)

endif

ifeq ($(STATIC),true)

STATIC=TRUE

endif

USEPRECOMPILEDLAPACK=TRUE

ifeq ($(USEPRECOMPILEDLAPACK),TRUE)

ifeq ($(STATIC),TRUE)

	@echo "[ 20%] Building **proteinortho_clustering** with LAPACK (static linking)";

	@$(CXX) $(CXXFLAGS) $(CXXFLAGS_PO) -fopenmp  -o $@ $< $(LDFLAGS) $(LDLIBS) -static -Wl,--allow-multiple-definition -llapack -lblas -lgfortran -lquadmath -pthread -Wl,--whole-archive -lpthread -Wl,--no-whole-archive && ([ $$? -eq 0 ] ) || ( \

	@$(CXX) $(CXXFLAGS) $(CXXFLAGS_PO) -fopenmp  -o $@ $< $(LDFLAGS) $(LDLIBS) -static -Wl,--allow-multiple-definition -llapack -lblas -lgfortran -pthread -Wl,--whole-archive -lpthread -Wl,--no-whole-archive -lquadmath && ([ $$? -eq 0 ] ) || ( \

		echo "......$(ORANGE)static linking failed, now I try dynamic linking.$(NC)"; \

		$(CXX) $(CXXFLAGS) $(CXXFLAGS_PO) -fopenmp  -o $@ $< $(LDFLAGS) $(LDLIBS) -llapack -lblas -pthread -Wl,--whole-archive -lpthread -Wl,--no-whole-archive && ([ $$? -eq 0 ] && echo "......OK dynamic linking was successful for proteinortho_clustering!";) || ( \

			echo "......$(ORANGE)dynamic linking failed too, now I try dynamic linking without -WL,-whole-archive (this should now work for OSX).$(NC)"; \

	@echo "If needed you can add $(INSTALLDIR) to \$$PATH with 'export PATH=\$$PATH:$(INSTALLDIR)'."

.PHONY: test

test: proteinortho6.pl test_step2 test_step3 test_clean

test: proteinortho6.pl test_clean test_step2 test_step3 test_clean2

	@echo "[TEST] All tests $(GREEN)passed$(NC)"

.PHONY: test_step2

		echo "$(GREEN)passed$(NC)"; \

	fi

	@echo -n " [2/12] -p=blastp+ synteny (PoFF) test: "

	@if [ "$(shell which blastp)" = "" ]; then\

		echo "$(ORANGE)blastp missing, skipping...$(NC)"; \

	else \

		./proteinortho6.pl -silent -force -project=test_synteny -synteny -singles -p=blastp+ test/*.faa; \

		set -e ; ./src/chk_test.pl test_synteny.proteinortho.tsv; \

		set -e ; ./src/chk_test.pl test_synteny.poff.tsv; \

		echo "$(GREEN)passed$(NC)"; \

	fi

#	@echo -n " [2/12] -p=blastp+ synteny (PoFF) test: "

#	@if [ "$(shell which blastp)" = "" ]; then\

#		echo "$(ORANGE)blastp missing, skipping...$(NC)"; \

#	else \

#		./proteinortho6.pl -silent -force -project=test_synteny -synteny -singles -p=blastp+ test/*.faa; \

#		set -e ; ./src/chk_test.pl test_synteny.proteinortho.tsv; \

#		set -e ; ./src/chk_test.pl test_synteny.poff.tsv; \

#		echo "$(GREEN)passed$(NC)"; \

#	fi

	@echo -n " [3/12] -p=diamond test: "

	@if [ "$(shell which diamond)" = "" ]; then\

	@echo "[TEST] Clean up all test files..."; \

	rm -rf proteinortho_cache_test_* test.* test_* test/C.faa.* test/E.faa.* test/C2.faa.* test/L.faa.* test/M.faa.*> /dev/null 2>&1;

.PHONY: test_clean2

test_clean2:

	@echo "[TEST] Clean up all test files..."; \

	rm -rf proteinortho_cache_test_* test.* test_* test/C.faa.* test/E.faa.* test/C2.faa.* test/L.faa.* test/M.faa.*> /dev/null 2>&1;

.PHONY: clean

clean:

	rm -rf src/BUILD test/C.faa.* test/E.faa.* test/C2.faa.* test/L.faa.* test/M.faa.*

# Proteinortho

 Proteinortho is a tool to detect orthologous genes within different species. For doing so, it compares similarities of given gene sequences and clusters them to find significant groups. The algorithm was designed to handle large-scale data and can be applied to hundreds of species at one. Details can be found in <a href="https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-12-124">Lechner et al., BMC Bioinformatics. 2011 Apr 28;12:124.</a>

To enhance the prediction accuracy, the relative order of genes (synteny) can be used as additional feature for the discrimination of orthologs. The corresponding extension, namely PoFF (manuscript in preparation), is already build in Proteinortho. The general workflow of proteinortho is depicted [![here](https://www.dropbox.com/s/7ubl1ginn3fmf8k/proteinortho_workflow.jpg?dl=0)].

To enhance the prediction accuracy, the relative order of genes (synteny) can be used as additional feature for the discrimination of orthologs. The corresponding extension, namely PoFF (doi:10.1371/journal.pone.0105015), is already build in Proteinortho. The general workflow of proteinortho is depicted [![here](https://www.dropbox.com/s/7ubl1ginn3fmf8k/proteinortho_workflow.jpg?dl=0)].

# New Features of Proteinortho Version 6!

     - blat (http://hgdownload.soe.ucsc.edu/admin/)

     - mmseqs2 (conda install mmseqs2, https://github.com/soedinglab/MMseqs2)

   - Perl v5.08 or higher (to test this, type perl -v in the command line)

   - Python v2.6.0 or higher to include synteny analysis (to test this, type 'python -V' in the command line) 

   - (optional) Python v3.0 or higher to include synteny analysis (to test this, type 'python -V' in the command line)

   - Perl standard modules (these should come with Perl): Thread::Queue, File::Basename, Pod::Usage, threads (if you miss one just install with `cpan install ...` )

</details>

  one. Details can be found in Lechner et al., BMC Bioinformatics. 2011 Apr

  28;12:124. To enhance the prediction accuracy, the relative order of genes

  (synteny) can be used as additional feature for the discrimination of

  orthologs. The corresponding extension, namely PoFF (manuscript in

  preparation), is already build in Proteinortho.

  orthologs. The corresponding extension, namely PoFF (doi:10.1371/journal.pone.0105015), is already build in Proteinortho.

  Proteinortho assumes, that you have all your gene sequences in FASTA

  format either represented as amino acids or as nucleotides. The source

<br>

 **Synteny options (optional, step 2)**

  (This option is deprecated)

  (output: <myproject>.ffadj-graph, <myproject>.poff.tsv (tab separated file)-graph)

<details>

  Lechner, M., Findeisz, S., Steiner, L., Marz, M., Stadler, P. F., &

  Prohaska, S. J. (2011). Proteinortho: detection of (co-) orthologs in

  large-scale analysis. BMC bioinformatics, 12(1), 124.