mitofish (4dcb0b04) · Commits · edna / reference_database

.gitignore

0 → 100644

+2 −0

Original line number	Diff line number	Diff line
		# exclude everything
		mitofish/*

README.md

+4 −6

Original line number	Diff line number	Diff line
		@@ -68,10 +68,8 @@ In addition, it includes `EMBL` folder which contains all the sequences and `TAX

		Now, your reference database can be used for taxonomic assignment in our pipeline to generate species environmental presence from raw eDNA data.

		You can use the absolute path of the folder of your reference database as the `/path/to/reference_database` argument in [only_obitools](http://gitlab.mbb.univ-montp2.fr/edna/only_obitools) and [snakemake_only_obitools](http://gitlab.mbb.univ-montp2.fr/edna/snakemake_only_obitools)





		You can use the absolute path of the folder of your reference database as the `/path/to/reference_database` argument in the following pipelines :
		* [only_obitools](http://gitlab.mbb.univ-montp2.fr/edna/only_obitools)
		* [nextflow_obitools](https://gitlab.mbb.univ-montp2.fr/edna/nextflow_obitoolsand)
		* [snakemake_only_obitools](http://gitlab.mbb.univ-montp2.fr/edna/snakemake_only_obitools)

build_bdr.sh

+10 −0

Original line number	Diff line number	Diff line
		@@ -14,6 +14,16 @@ cd TAXO
		wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz
		tar -zxvf taxdump.tar.gz
		cd ..

		if [ $MITOFISH == 'y' ]
		then
		echo "adding sequences from mitofish..."
		bash scripts/add_sequences_from_mitofish.sh
		obiconvert --skip-on-error --fasta -t ./TAXO --ecopcrdb-output=mitofish/"${rd_prefix}" mitofish/mitogene_12S.fasta
		else
		echo "skip adding sequences from mitofish"
		fi

		# format the data
		obiconvert --skip-on-error --embl -t ./TAXO --ecopcrdb-output="${rd_prefix}" EMBL/rel_std_*.dat
		# ecoPCR to simulate an in silico PCR

config.sh

+4 −0

Original line number	Diff line number	Diff line
		# argument values for building reference database

		## "y" add sequences from mitofish the reference database
		## "n" don't add sequences from mitofish
		MITOFISH="n"

		## reference database prefix
		rd_prefix="embl_std"

scripts/add_sequences_from_mitofish.sh

0 → 100644

+48 −0

Original line number	Diff line number	Diff line
		## add sequences of gene from mitofish database

		mkdir mitofish

		## Downloads mitogenomes
		mkdir mitofish/mitogenomes
		wget http://mitofish.aori.u-tokyo.ac.jp/files/mitogenomes.zip --directory-prefix=mitofish/
		unzip mitofish/mitogenomes.zip -d mitofish/mitogenomes

		## Downloads gene annotations of mitogenomes
		mkdir mitofish/mitoannotations
		wget http://mitofish.aori.u-tokyo.ac.jp/files/mitoannotations.zip --directory-prefix=mitofish/
		unzip mitofish/mitoannotations.zip -d mitofish/mitoannotations

		## list of species with mitogenomes
		for i in `ls mitofish/mitogenomes`;
		do
		echo $i \| cut -d "." -f 1 \| cut -d "_" -f 3-4;
		done \| sort \| uniq \| sed 's/_/ /g' > mitofish/species_mitogenomes.list
		## list of species with mitoannotations
		for i in `ls mitofish/mitoannotations/`;
		do
		echo $i \| cut -d "." -f 1 \| cut -d "_" -f 3-4;
		done \| sort \| uniq \| sed 's/_/ /g' > mitofish/species_mitoannotations.list
		## list of species with mitogenomes AND mitoannotations
		grep -f mitofish/species_mitoannotations.list mitofish/species_mitogenomes.list > mitofish/species_mitogenome_annotations.list
		## extract 12S sequences
		mkdir mitofish/complete
		cat mitofish/species_mitogenome_annotations.list \| while read i;
		do
		GENUS=`echo $i \| awk '{ print $1}'`;
		SPECIES=`echo $i \| awk '{ print $2}'`;
		GENUS_SPECIES=`echo $GENUS"_"$SPECIES`;
		for j in `ls mitofish/mitogenomes/$GENUS_SPECIES`;
		do
		JFILE=`basename $j`
		ln -s $(pwd)/mitofish/mitogenomes/$JFILE mitofish/complete/$JFILE;
		done
		for k in `ls mitofish/mitoannotations/$GENUS_SPECIES`;
		do
		KFILE=`basename $k`
		ln -s $(pwd)/mitofish/mitoannotations/$KFILE mitofish/complete/$KFILE;
		done
		done
		cat mitofish/complete/*fa > mitofish/mitogenomes.fa
		mkdir mitofish/mitogenomes_12S
		python2 scripts/extract_gene_from_mito.py -i mitofish/mitogenomes.fa -a mitofish/complete -o mitofish/mitogenomes_12S -g 12S -t rRNA -5 50 -3 50 -T TAXO/names.dmp
		cat mitofish/mitogenomes_12S/*fa > mitofish/mitogene_12S.fasta