add authorship

README.md

-# reference_database
+# REFERENCE DATABASE
 
-Collection of scripts to build a reference database.
+Collection of scripts to build a reference database for metabarcoding analysis.
 
-# reference database built from EMBL taxonomy and sequences
+# Reference database built from EMBL taxonomy and sequences
 
 This method is based on [OBItools](https://pythonhosted.org/OBITools/welcome.html#installing-the-obitools)'s reference database.
 
@@ -42,7 +42,7 @@ You will also need to have the following programs installed on your computer.
 - clone the project (see [Installation](#installation) section)
 - fill in [config.sh](config.sh) and read [ecoPCR ](https://pythonhosted.org/OBITools/scripts/ecoPCR.html?highlight=ecopcr) documentation
 
-## Build a reference database
+## Build a reference database (MISEQ)
 
 * Overview of the steps
 	1. Download the sequences
@@ -86,4 +86,15 @@ Type the following command to convert your reference database into STAMPA format
 python3 scripts/formatDB_obifasta_to_stampa.py -f /path/to/db_{prefix}.fasta -o /path/to/reference_database_stampa.fasta
 ```
 This command generates a file `/path/to/reference_database_stampa.fasta` which you can use as a reference database for the pipeline :
-* [bash_swarm](https://gitlab.mbb.univ-montp2.fr/edna/bash_swarm)
\ No newline at end of file
+* [bash_swarm](https://gitlab.mbb.univ-montp2.fr/edna/bash_swarm)
+
+
+# Authors
+
+* Pierre-Edouard GUERIN, CNRS, CEFE
+* Virginie Marques, CNRS, MARBEC
+
+
+# License
+
+This project is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details
\ No newline at end of file

build_bdr.sh

-# Build a reference database
-
+##########################################################################
+## Codes for scientific papers related to metabarcoding studies
+##
+## AUTHORS
+## =======
+## * Pierre-Edouard Guerin   | pierre-edouard.guerin@cefe.cnrs.fr
+## * Virginie Marques        | virginie.marques@etu.umontpellier.fr
+## * CNRS/CEFE, CNRS/MARBEC  | Montpellier, France
+## * 2018-2020
+##
+##
+## Inspired by the Eric Coissac et al. obitools
+## Molecular Ecology Resources 2015
+##
+## DESCRIPTION
+## ===========
+##
+## Build a reference database for "miseq" sequences data.
+## We recommand to launch each command line by line into linux terminal
+## to check each step results
+##
+##
+##
+## USAGE
+## =====
+## bash buil_bdr.sh
+##
+##
+##########################################################################
 
 ## load an environment with obitools
 SINGULARITY_SIMG="/media/superdisk/utils/conteneurs/obitools.simg"
@@ -7,21 +34,22 @@ singularity shell --bind /media/superdisk:/media/superdisk $SINGULARITY_SIMG
 
 
 
-# configure arguments value
+## configure arguments value
 source ./config.sh
-# download the sequences
+## download the sequences
 mkdir EMBL
 cd EMBL
 wget ftp://ftp.ebi.ac.uk/pub/databases/ena/sequence/release/std/*
 gzip -d *
 cd ..
-# download taxonomy
+## download taxonomy
 mkdir TAXO
 cd TAXO
 wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz
 tar -zxvf taxdump.tar.gz
 cd ..
 
+## add mitofish sequences (by default we skip this step)
 if [ $MITOFISH == 'y' ]
 then
  echo "adding sequences from mitofish..."
@@ -31,12 +59,12 @@ else
  echo "skip adding sequences from mitofish"
 fi
 
-# format the data
+## format the data
 obiconvert --skip-on-error --embl -t ./TAXO --ecopcrdb-output="${rd_prefix}" EMBL/rel_std_*.dat
-# ecoPCR to simulate an in silico PCR
-# 50 :: change to 20 : lost of lamproie
+## ecoPCR to simulate an in silico PCR
+#### 50 :: change to 20 : lost of lamproie
 ecoPCR -d "${rd_prefix}" -e "${ecoPCR_e}" -l "${ecoPCR_l}" -L "${ecoPCR_L}" "${primer5}" "${primer3}" > v_"${rd_prefix}".ecopcr
-# clean the database
+## clean the database
 ## filter sequences so that they have a good taxonomic description at the species genus and family levels
 obigrep -d "${rd_prefix}" --require-rank=species --require-rank=genus --require-rank=family v_"${rd_prefix}".ecopcr > v_"${rd_prefix}"_clean.fasta
 ## remove redundant sequences
@@ -45,7 +73,7 @@ obiuniq -d "${rd_prefix}" v_"${rd_prefix}"_clean.fasta > v_"${rd_prefix}"_clean_
 obigrep -d "${rd_prefix}" --require-rank=family v_"${rd_prefix}"_clean_uniq.fasta > v_"${rd_prefix}"_clean_uniq_clean.fasta
 ## ensure that sequences each have a unique identification
 obiannotate --uniq-id v_"${rd_prefix}"_clean_uniq_clean.fasta > db_"${rd_prefix}".fasta
-# your reference database is built !
+## your reference database is built !
 
 
 
@@ -54,7 +82,7 @@ obiannotate --uniq-id v_"${rd_prefix}"_clean_uniq_clean.fasta > db_"${rd_prefix}
 #obitaxonomy -d "${rd_prefix}" -a 'Cidella_Hmolitrix':'species':10000088
 
 
-obiconvert --skip-on-error --fasta -t ./TAXO --ecopcrdb-output=mitofish/"${rd_prefix}" mitofish/mitogene_12S.fasta
-obiconvert --skip-on-error --embl -t ./TAXO --ecopcrdb-output="${rd_prefix}" EMBL/rel_std_*.dat
+#obiconvert --skip-on-error --fasta -t ./TAXO --ecopcrdb-output=mitofish/"${rd_prefix}" mitofish/mitogene_12S.fasta
+#obiconvert --skip-on-error --embl -t ./TAXO --ecopcrdb-output="${rd_prefix}" EMBL/rel_std_*.dat
 
 

build_bdr_rapidrun.sh

-###############################################################################
+##########################################################################
+## Codes for scientific papers related to metabarcoding studies
+##
+## AUTHORS
+## =======
+## * Pierre-Edouard Guerin   | pierre-edouard.guerin@cefe.cnrs.fr
+## * Virginie Marques        | virginie.marques@etu.umontpellier.fr
+## * CNRS/CEFE, CNRS/MARBEC  | Montpellier, France
+## * 2018-2020
+##
+##
+## Inspired by the Eric Coissac et al. obitools
+## Molecular Ecology Resources 2015
+##
+## DESCRIPTION
+## ===========
+##
+## Build a reference database for "RAPIDRUN" sequences data.
+## We recommand to launch each command line by line into linux terminal
+## to check each step results
+##
+##
+##
+## USAGE
+## =====
+## bash build_bdr_rapidrun.sh
+##
+##
+##########################################################################
+
+
+##########################################################################
 ## RAPIDRUN
 source ./config.sh
 

config.sh

-# argument values for building reference database
+##########################################################################
+## Codes for scientific papers related to metabarcoding studies
+##
+## AUTHORS
+## =======
+## * Pierre-Edouard Guerin   | pierre-edouard.guerin@cefe.cnrs.fr
+## * Virginie Marques        | virginie.marques@etu.umontpellier.fr
+## * CNRS/CEFE, CNRS/MARBEC  | Montpellier, France
+## * 2018-2020
+##
+## DESCRIPTION
+## ===========
+##
+## Information to fill in order to execute build_bdr.sh and other scripts
+##
+##
+##
+##
+##
+########################################################################### argument values for building reference database
 
 ## "y" add sequences from mitofish the reference database
 ## "n" don't add sequences from mitofish

scripts/add_sequences_from_mitofish.sh

+##########################################################################
+## Codes for scientific papers related to metabarcoding studies
+##
+## AUTHORS
+## =======
+## * Pierre-Edouard Guerin   | pierre-edouard.guerin@cefe.cnrs.fr
+## * Virginie Marques        | virginie.marques@etu.umontpellier.fr
+## * CNRS/CEFE, CNRS/MARBEC  | Montpellier, France
+## * 2018-2020
+##
+##
+## Inspired by the Eric Coissac et al. obitools
+## Molecular Ecology Resources 2015
+##
+## DESCRIPTION
+## ===========
+##
 ## add sequences of gene from mitofish database
+## 
+##
+##########################################################################
+
+## 
 
 mkdir mitofish
 

scripts/extract_gene_from_mito.py

+#===============================================================================
+#HEADER
+#===============================================================================
+__author__ = "Pierre-Edouard Guerin"
+__credits__ = ["Pierre-Edouard Guerin", "Virginie Marques"]
+__license__ = "MIT"
+__version__ = "1.0.1"
+__maintainer__ = "Pierre-Edouard Guerin"
+__email__ = "pierre-edouard.guerin@cefe.cnrs.fr"
+__status__ = "Production"
+"""
+#
+# Codes for scientific papers related to metabarcoding studies
+AUTHORS
+=======
+* Pierre-Edouard Guerin   | pierre-edouard.guerin@cefe.cnrs.fr
+* CNRS/CEFE, CNRS/MARBEC  | Montpellier, France
+* 2018-2020
+
+
+DESCRIPTION
+===========
+extract gene sequences (12S for instance) from mitofish database
+
+"""
+#===============================================================================
+#MODULES
+#===============================================================================
 import Bio
 from Bio import SeqIO
 from Bio.Alphabet import IUPAC

scripts/formatDB_obifasta_to_stampa.py

 #===============================================================================
-#INFORMATIONS
-#===============================================================================
-"""
-CEFE - EPHE - YERSIN 2018
-guerin pierre-edouard
-from reference database obitools fasta files, 
-it creates a stampa-format reference database
-"""
-#===============================================================================
-#USAGES
+#HEADER
 #===============================================================================
+__author__ = "Pierre-Edouard Guerin"
+__credits__ = ["Pierre-Edouard Guerin", "Virginie Marques"]
+__license__ = "MIT"
+__version__ = "1.0.1"
+__maintainer__ = "Pierre-Edouard Guerin"
+__email__ = "pierre-edouard.guerin@cefe.cnrs.fr"
+__status__ = "Production"
 """
+#
+# Codes for scientific papers related to metabarcoding studies
+AUTHORS
+=======
+* Pierre-Edouard Guerin   | pierre-edouard.guerin@cefe.cnrs.fr
+* CNRS/CEFE, CNRS/MARBEC  | Montpellier, France
+* 2018-2020
+
+
+DESCRIPTION
+===========
+
+Format obifasta file into STAMPA database FASTA file
+
+USAGE
+=====
+
 input :
 path to FASTA obitools file with "species=" information field available
 output :
 path to write the STAMPA-format FASTA reference databasae file
 command : 
 python3 ncbi_to_stampa.py -f input -o output
+
 """
 #===============================================================================
 #MODULES