From 81107fa655e9c697e45f2dfbc9573b53de183913 Mon Sep 17 00:00:00 2001 From: Amandine PERRIN <amandine.perrin@pasteur.fr> Date: Wed, 2 Sep 2020 16:03:31 +0200 Subject: [PATCH] add licence header for align module --- PanACoTA/align_module/__init__.py | 32 +++++++++++++++++++++ PanACoTA/align_module/alignment.py | 32 +++++++++++++++++++++ PanACoTA/align_module/get_seqs.py | 34 ++++++++++++++++++++++- PanACoTA/align_module/pan_to_pergenome.py | 32 +++++++++++++++++++++ PanACoTA/align_module/post_align.py | 32 +++++++++++++++++++++ 5 files changed, 161 insertions(+), 1 deletion(-) diff --git a/PanACoTA/align_module/__init__.py b/PanACoTA/align_module/__init__.py index 494d571b..abc8c3e4 100755 --- a/PanACoTA/align_module/__init__.py +++ b/PanACoTA/align_module/__init__.py @@ -1,3 +1,35 @@ +# ############################################################################### +# This file is part of PanACOTA. # +# # +# Authors: Amandine Perrin # +# Copyright © 2018-2020 Institut Pasteur (Paris). # +# See the COPYRIGHT file for details. # +# # +# PanACOTA is a software providing tools for large scale bacterial comparative # +# genomics. From a set of complete and/or draft genomes, you can: # +# - Do a quality control of your strains, to eliminate poor quality # +# genomes, which would not give any information for the comparative study # +# - Uniformly annotate all genomes # +# - Do a Pan-genome # +# - Do a Core or Persistent genome # +# - Align all Core/Persistent families # +# - Infer a phylogenetic tree from the Core/Persistent families # +# # +# PanACOTA is free software: you can redistribute it and/or modify it under the # +# terms of the Affero GNU General Public License as published by the Free # +# Software Foundation, either version 3 of the License, or (at your option) # +# any later version. # +# # +# PanACOTA is distributed in the hope that it will be useful, but WITHOUT ANY # +# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # +# FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License # +# for more details. # +# # +# You should have received a copy of the Affero GNU General Public License # +# along with PanACOTA (COPYING file). # +# If not, see <https://www.gnu.org/licenses/>. # +# ############################################################################### + """ PanACoTA align submodule """ diff --git a/PanACoTA/align_module/alignment.py b/PanACoTA/align_module/alignment.py index 2ea7c08a..a34c0c9b 100755 --- a/PanACoTA/align_module/alignment.py +++ b/PanACoTA/align_module/alignment.py @@ -1,6 +1,38 @@ #!/usr/bin/env python3 # coding: utf-8 +# ############################################################################### +# This file is part of PanACOTA. # +# # +# Authors: Amandine Perrin # +# Copyright © 2018-2020 Institut Pasteur (Paris). # +# See the COPYRIGHT file for details. # +# # +# PanACOTA is a software providing tools for large scale bacterial comparative # +# genomics. From a set of complete and/or draft genomes, you can: # +# - Do a quality control of your strains, to eliminate poor quality # +# genomes, which would not give any information for the comparative study # +# - Uniformly annotate all genomes # +# - Do a Pan-genome # +# - Do a Core or Persistent genome # +# - Align all Core/Persistent families # +# - Infer a phylogenetic tree from the Core/Persistent families # +# # +# PanACOTA is free software: you can redistribute it and/or modify it under the # +# terms of the Affero GNU General Public License as published by the Free # +# Software Foundation, either version 3 of the License, or (at your option) # +# any later version. # +# # +# PanACOTA is distributed in the hope that it will be useful, but WITHOUT ANY # +# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # +# FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License # +# for more details. # +# # +# You should have received a copy of the Affero GNU General Public License # +# along with PanACOTA (COPYING file). # +# If not, see <https://www.gnu.org/licenses/>. # +# ############################################################################### + """ For a given family: diff --git a/PanACoTA/align_module/get_seqs.py b/PanACoTA/align_module/get_seqs.py index 15da584b..dd7d849f 100755 --- a/PanACoTA/align_module/get_seqs.py +++ b/PanACoTA/align_module/get_seqs.py @@ -1,6 +1,38 @@ #!/usr/bin/env python3 # coding: utf-8 +# ############################################################################### +# This file is part of PanACOTA. # +# # +# Authors: Amandine Perrin # +# Copyright © 2018-2020 Institut Pasteur (Paris). # +# See the COPYRIGHT file for details. # +# # +# PanACOTA is a software providing tools for large scale bacterial comparative # +# genomics. From a set of complete and/or draft genomes, you can: # +# - Do a quality control of your strains, to eliminate poor quality # +# genomes, which would not give any information for the comparative study # +# - Uniformly annotate all genomes # +# - Do a Pan-genome # +# - Do a Core or Persistent genome # +# - Align all Core/Persistent families # +# - Infer a phylogenetic tree from the Core/Persistent families # +# # +# PanACOTA is free software: you can redistribute it and/or modify it under the # +# terms of the Affero GNU General Public License as published by the Free # +# Software Foundation, either version 3 of the License, or (at your option) # +# any later version. # +# # +# PanACOTA is distributed in the hope that it will be useful, but WITHOUT ANY # +# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # +# FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License # +# for more details. # +# # +# You should have received a copy of the Affero GNU General Public License # +# along with PanACOTA (COPYING file). # +# If not, see <https://www.gnu.org/licenses/>. # +# ############################################################################### + import sys import os import logging @@ -225,7 +257,7 @@ def extract_sequences(to_extract, fasf, files_todo=None, outf=None): # State machine variables previous_fp = None - + for line in fasf: if line[0] == '>': # Close previous file if needed diff --git a/PanACoTA/align_module/pan_to_pergenome.py b/PanACoTA/align_module/pan_to_pergenome.py index 7d5a48aa..86d20b50 100755 --- a/PanACoTA/align_module/pan_to_pergenome.py +++ b/PanACoTA/align_module/pan_to_pergenome.py @@ -1,6 +1,38 @@ #!/usr/bin/env python3 # coding: utf-8 +# ############################################################################### +# This file is part of PanACOTA. # +# # +# Authors: Amandine Perrin # +# Copyright © 2018-2020 Institut Pasteur (Paris). # +# See the COPYRIGHT file for details. # +# # +# PanACOTA is a software providing tools for large scale bacterial comparative # +# genomics. From a set of complete and/or draft genomes, you can: # +# - Do a quality control of your strains, to eliminate poor quality # +# genomes, which would not give any information for the comparative study # +# - Uniformly annotate all genomes # +# - Do a Pan-genome # +# - Do a Core or Persistent genome # +# - Align all Core/Persistent families # +# - Infer a phylogenetic tree from the Core/Persistent families # +# # +# PanACOTA is free software: you can redistribute it and/or modify it under the # +# terms of the Affero GNU General Public License as published by the Free # +# Software Foundation, either version 3 of the License, or (at your option) # +# any later version. # +# # +# PanACOTA is distributed in the hope that it will be useful, but WITHOUT ANY # +# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # +# FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License # +# for more details. # +# # +# You should have received a copy of the Affero GNU General Public License # +# along with PanACOTA (COPYING file). # +# If not, see <https://www.gnu.org/licenses/>. # +# ############################################################################### + """ From the Persistent Genome file, group all persistent proteins per genome, in order to be able to extract them faster after. diff --git a/PanACoTA/align_module/post_align.py b/PanACoTA/align_module/post_align.py index 6b9a7e4a..c0149a34 100755 --- a/PanACoTA/align_module/post_align.py +++ b/PanACoTA/align_module/post_align.py @@ -1,6 +1,38 @@ #!/usr/bin/env python3 # coding: utf-8 +# ############################################################################### +# This file is part of PanACOTA. # +# # +# Authors: Amandine Perrin # +# Copyright © 2018-2020 Institut Pasteur (Paris). # +# See the COPYRIGHT file for details. # +# # +# PanACOTA is a software providing tools for large scale bacterial comparative # +# genomics. From a set of complete and/or draft genomes, you can: # +# - Do a quality control of your strains, to eliminate poor quality # +# genomes, which would not give any information for the comparative study # +# - Uniformly annotate all genomes # +# - Do a Pan-genome # +# - Do a Core or Persistent genome # +# - Align all Core/Persistent families # +# - Infer a phylogenetic tree from the Core/Persistent families # +# # +# PanACOTA is free software: you can redistribute it and/or modify it under the # +# terms of the Affero GNU General Public License as published by the Free # +# Software Foundation, either version 3 of the License, or (at your option) # +# any later version. # +# # +# PanACOTA is distributed in the hope that it will be useful, but WITHOUT ANY # +# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # +# FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License # +# for more details. # +# # +# You should have received a copy of the Affero GNU General Public License # +# along with PanACOTA (COPYING file). # +# If not, see <https://www.gnu.org/licenses/>. # +# ############################################################################### + """ Concatenate all alignment files of all families. Then, group alignments by genome. -- GitLab