Merge pull request #2 from mutalyzer/py3

Py3

.github/CODE_OF_CONDUCT.md

+# Contributor Covenant Code of Conduct
+## Our Pledge
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone.
+
+## Our Standards
+Examples of behaviour that contributes to creating a positive environment
+include:
+
+- Using welcoming and inclusive language.
+- Being respectful of differing viewpoints and experiences.
+- Gracefully accepting constructive criticism.
+- Focusing on what is best for the community.
+- Showing empathy towards other community members.
+
+Examples of unacceptable behaviour by participants include:
+
+- The use of sexualized language or imagery and unwelcome sexual attention or
+  advances.
+- Trolling, insulting/derogatory comments, and personal or political attacks.
+- Public or private harassment.
+- Publishing others' private information, such as a physical or electronic
+  address, without explicit permission.
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting.
+
+## Our Responsibilities
+Project maintainers are responsible for clarifying the standards of acceptable
+behaviour and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behaviour.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviour that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an
+appointed representative at an online or offline event. Representation of a
+project may be further defined and clarified by project maintainers.
+
+## Enforcement
+Instances of abusive, harassing, or otherwise unacceptable behaviour may be
+reported by contacting the project team at mailto:info@mutalyzer.nl. The
+project team will review and investigate all complaints, and will respond in a
+way that it deems appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an
+incident. Further details of specific enforcement policies may be posted
+separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.4, available at
+[http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

.github/CONTRIBUTING.md

+# Contributing
+Please follow these guidelines if you would like to contribute to the project.
+
+---
+
+## Table of Contents
+Please read through these guidelines before you get started:
+
+1. [Questions & Concerns](#questions--concerns)
+2. [Issues & Bugs](#issues--bugs)
+3. [Feature Requests](#feature-requests)
+4. [Submitting Pull Requests](#submitting-pull-requests)
+5. [Code Style](#code-style)
+
+## Questions & Concerns
+If you have any questions about using or developing for this project, reach out
+to @mutalyzer or send an [email][email].
+
+## Issues & Bugs
+Submit an [issue][issues] or [pull request][compare] with a fix if you find any
+bugs in the project. See [below](#submitting-pull-requests) for instructions on
+sending in pull requests, and be sure to reference the [code style
+guide](#code-style) first!
+
+When submitting an issue or pull request, make sure you are as detailed as
+possible and fill in all answers to questions asked in the templates. For
+example, an issue that simply states "X/Y/Z is not working!" will be closed.
+
+## Feature Requests
+Submit an [issue][issues] to request a new feature. Features fall into one of
+two categories:
+
+1. **Major**: Major changes should be discussed with me via [email][email]. I am
+   always open to suggestions and will get back to you as soon as I can!
+2. **Minor**: A minor feature can simply be added via a [pull request][compare].
+
+## Submitting Pull Requests
+Before you do anything, make sure you check the current list of [pull
+requests][pull] to ensure you are not duplicating anyone's work. Then, do the
+following:
+
+1. Fork the repository and make your changes in a git branch: `git checkout -b
+   my-branch base-branch`
+2. Read and follow the [code style guidelines](#code-style).
+3. Make sure your feature or fix does not break the project! Test thoroughly.
+4. Commit your changes, and be sure to leave a detailed commit message.
+5. Push your branch to your forked repo on GitHub: `git push origin my-branch`
+6. [Submit a pull request][compare] and hold tight!
+7. If any changes are requested by the project maintainers, make them and
+   follow this process again until the changes are merged in.
+
+## Code Style
+Please follow the coding style conventions detailed below:
+
+- For Python: [PEP 8 - Style Guide for Python Code][pep8].
+
+
+[email]: mailto:info@mutalyzer.nl
+[issues]: https://github.com/mutalyzer/backtranslate/issues/new
+[compare]: https://github.com/mutalyzer/backtranslate/compare
+[pull]: https://github.com/mutalyzer/backtranslate/pulls
+[pep8]: https://www.python.org/dev/peps/pep-0008/

.github/ISSUE_TEMPLATE/Bug_report.md

+---
+name: Bug report
+about: Create a report to help us improve
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behaviour:
+
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. Ubuntu Desktop 18.04]
+ - Version [e.g. 0.0.14]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/Feature_request.md

+---
+name: Feature request
+about: Suggest an idea for this project
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always
+frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've
+considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/PULL_REQUEST_TEMPLATE.md

+# Submit a pull request
+Thank you for submitting a pull request. To speed up the review process, please
+ensure that everything below is true:
+
+1. This is not a duplicate of an [existing pull request][1].
+2. No existing features have been broken without good reason.
+3. Your commit messages are detailed
+4. The code style [guidelines][2] have been followed.
+5. Documentation has been updated to reflect your changes.
+6. Tests have been added or updated to reflect your changes.
+7. All tests pass.
+
+Any questions should be directed to @mutalyzer.
+
+---
+
+Replace any ":question:" below with information about your pull request.
+
+## Pull Request Details
+Provide details about your pull request and what it adds, fixes, or changes.
+
+:question:
+
+## Breaking Changes
+Describe what features are broken by this pull request and why, if any.
+
+:question:
+
+## Issues Fixed
+Enter the issue numbers resolved by this pull request below, if any.
+
+1. :question:
+
+## Other Relevant Information
+Provide any other important details below.
+
+:question:
+
+[1]: https://github.com/mutalyzer/backtranslate/pulls
+[2]: https://github.com/mutalyzer/backtranslate/blob/master/docs/CONTRIBUTING.md#code-style

.gitignore

-*.pyc
 *.egg-info
-build
-dist
-.ipynb_checkpoints
+*.pyc
+.cache/
+.tox/
+build/
+dist/
+examples/.ipynb_checkpoints/

.travis.yml

-# Validate this file using http://lint.travis-ci.org/
 language: python
-sudo: false
 python:
-  - "2.7"
-  - "3.3"
-  - "3.4"
-  - "3.5"
-  - "nightly"
-  - "pypy"
-  - "pypy3"
-install: python setup.py install
-script: py.test
+  - 3.5
+  - 3.6
+install: pip install . fake-open tox-travis
+script: tox

LICENSE.md

+Copyright (c) 2015-2019 by LUMC, Jeroen F.J. Laros.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+of the Software, and to permit persons to whom the Software is furnished to do
+so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

-# Back translation
-This library provides functions for back translation from amino acids to
-nucleotides.
-
-```python
->>> from __future__ import unicode_literals
->>>
->>> from backtranslate.backtranslate import BackTranslate
->>>
->>> # Create a class instance, optionally giving the translation table id.
->>> bt = BackTranslate()
->>>
->>> # Find all substitutions that transform the codon 'TGG' into a stop codon.
->>> bt.with_dna('TGG', '*')
-{1: set([('G', 'A')]), 2: set([('G', 'A')])}
-```
-
-Sometimes we do not have access to the DNA sequence so we have to find
-possible substitutions from the amino acids directly.
-
-```python
->>> # Find all substitutions that transform a Tryptophan into a stop codon.
->>> bt.without_dna('W', '*')
-{1: set([('G', 'A')]), 2: set([('G', 'A')])}
-```
-
-To find out which substitution predictions can be improved by adding codon
-information, use the following function.
-
-```python
->>> bt.improvable()
-set([('I', 'L'), ('R', 'W'), ('Q', 'H'), ('C', '*'), ('*', 'W'), ('K', 'N'),
-    ('C', 'W'), ('S', 'R'), ('L', 'I'), ('*', 'S'), ('S', '*'), ('L', '*'),
-    ('L', 'M'), ('L', 'F'), ('*', 'L'), ('D', 'E'), ('R', 'G'), ('S', 'C'),
-    ('E', 'D'), ('R', 'S'), ('N', 'K'), ('H', 'Q'), ('S', 'T'), ('T', 'S'),
-    ('G', 'R'), ('L', 'V'), ('I', 'M'), ('F', 'L'), ('*', 'Y'), ('Y', '*'),
-    ('V', 'L'), ('R', '*')])
-```
-
-To get substitutions in a readable format, we can use the following:
-
-```python
->>> from backtranslate.util import subst_to_cds
->>>
->>> substitutions = bt.without_dna('W', '*')
->>>
->>> # Transform the substitutions to CDS coordinates.
->>> subst_to_cds(substitutions, 12)
-set([(15, 'G', 'A'), (14, 'G', 'A')])
-```
-
-## Command line interface
-Use the command `backtranslate` to find substitutions that explain an amino
-acid change:
-
-```bash
-$ backtranslate with_dna -o 210 data/mhv.fa - 1 Leu
-1       A       C
-1       A       T
-```
-
-If no reference is available, use the `without_dna` subcommand:
-
-```bash
-$ backtranslate without_dna - Asp 92 Tyr
-274     G       T
-```
-
-The command `find_stops` finds a list of positions and substitutions that lead
-to stop codons. This list of destructive substitutions are useful when
-analysing a pool of viral transcripts. Counting the appropriate nucleotides at
-the given positions gives insight into how many transcripts are active.
-
-```bash
-$ backtranslate find_stops -o 210 data/mhv.fa -
-216     A       T
-225     A       T
-230     C       A
-230     C       G
-243     A       T
-...
-```

README.rst

+Back translation
+================
+
+.. image:: https://img.shields.io/github/last-commit/mutalyzer/backtranslate.svg   :target: https://github.com/mutalyzer/backtranslate/graphs/commit-activity
+.. image:: https://travis-ci.org/mutalyzer/backtranslate.svg?branch=master
+   :target: https://travis-ci.org/mutalyzer/backtranslate
+.. image:: https://readthedocs.org/projects/simplerpc/badge/?version=latest
+   :target: https://backtranslate.readthedocs.io/en/latest
+.. image:: https://img.shields.io/github/release-date/mutalyzer/backtranslate.svg
+   :target: https://github.com/mutalyzer/backtranslate/releases
+.. image:: https://img.shields.io/github/release/mutalyzer/backtranslate.svg
+   :target: https://github.com/mutalyzer/backtranslate/releases
+.. image:: https://img.shields.io/pypi/v/backtranslate.svg
+   :target: https://pypi.org/project/backtranslate/
+.. image:: https://img.shields.io/github/languages/code-size/mutalyzer/backtranslate.svg
+   :target: https://github.com/mutalyzer/backtranslate
+.. image:: https://img.shields.io/github/languages/count/mutalyzer/backtranslate.svg
+   :target: https://github.com/mutalyzer/backtranslate
+.. image:: https://img.shields.io/github/languages/top/mutalyzer/backtranslate.svg
+   :target: https://github.com/mutalyzer/backtranslate
+.. image:: https://img.shields.io/github/license/mutalyzer/backtranslate.svg
+   :target: https://raw.githubusercontent.com/mutalyzer/backtranslate/master/LICENSE.md
+
+----
+
+This library provides functions for back translation from amino acids to
+nucleotides.
+
+Please see ReadTheDocs_ for the latest documentation.
+
+
+.. _ReadTheDocs: https://backtranslate.readthedocs.io

backtranslate/__init__.py

-"""
-backtranslate: Functions for reverse translation.
+from os.path import dirname, abspath
 
+from configparser import ConfigParser
 
-Copyright (c) 2015 Leiden University Medical Center <humgen@lumc.nl>
-Copyright (c) 2015 Jeroen F.J. Laros <j.f.j.laros@lumc.nl>
+from .backtranslate import BackTranslate
 
-Licensed under the MIT license, see the LICENSE file.
-"""
 
+config = ConfigParser()
+with open('{}/setup.cfg'.format(dirname(abspath(__file__)))) as handle:
+    config.read_file(handle)
 
-from __future__ import (
-    absolute_import, division, print_function, unicode_literals)
-from future.builtins import str, zip
+_copyright_notice = 'Copyright (c) {} {} <{}>'.format(
+    config.get('metadata', 'copyright'),
+    config.get('metadata', 'author'),
+    config.get('metadata', 'author_email'))
 
-
-__version_info__ = ('0', '0', '5')
-
-
-__version__ = '.'.join(__version_info__)
-__author__ = 'LUMC, Jeroen F.J. Laros'
-__contact__ = 'J.F.J.Laros@lumc.nl'
-__homepage__ = 'https://github.com/mutalyzer/backtranslate'
-
-
-usage = __doc__.split("\n\n\n")
+usage = [config.get('metadata', 'description'), _copyright_notice]
 
 
 def doc_split(func):
-    return func.__doc__.split("\n\n")[0]
+    return func.__doc__.split('\n\n')[0]
 
 
 def version(name):
-    return "%s version %s\n\nAuthor   : %s <%s>\nHomepage : %s" % (name,
-        __version__, __author__, __contact__, __homepage__)
+    return '{} version {}\n\n{}\nHomepage: {}'.format(
+        config.get('metadata', 'name'),
+        config.get('metadata', 'version'),
+        _copyright_notice,
+        config.get('metadata', 'url'))

backtranslate/backtranslate.py

-from __future__ import (
-    absolute_import, division, print_function, unicode_literals)
-from future.builtins import str, zip
-
 from collections import defaultdict
 
 from Bio.Data import CodonTable
@@ -9,8 +5,7 @@ from Levenshtein import hamming
 
 
 def cmp_subst(subst_1, subst_2):
-    """
-    Compare two substitution sets.
+    """Compare two substitution sets.
 
     :arg dict subst_1: Substitution set.
     :arg dict subst_2: Substitution set.
@@ -28,8 +23,7 @@ def cmp_subst(subst_1, subst_2):
 
 
 def reverse_translation_table(table_id=1):
-    """
-    Calculate a reverse translation table.
+    """Calculate a reverse translation table.
 
     :arg int table_id: Translation table id.
 
@@ -47,20 +41,16 @@ def reverse_translation_table(table_id=1):
 
 
 class BackTranslate(object):
-    """
-    Back translation.
-    """
+    """Back translation."""
     def __init__(self, table_id=1):
-        """
-        Initialise the class.
+        """Initialise the class.
 
         :arg int table_id: Translation table id.
         """
         self._back_table = reverse_translation_table(table_id)
 
     def _one_subst(self, substitutions, reference_codon, amino_acid):
-        """
-        Find single nucleotide substitutions that given a reference codon
+        """Find single nucleotide substitutions that given a reference codon
         explains an observed amino acid.
 
         :arg defaultdict(set) substitutions: Set of single nucleotide
@@ -76,8 +66,7 @@ class BackTranslate(object):
                             (reference_codon[position], codon[position]))
 
     def with_dna(self, reference_codon, amino_acid):
-        """
-        Find single nucleotide substitutions that given a reference codon
+        """Find single nucleotide substitutions that given a reference codon
         explains an observed amino acid.
 
         :arg str reference_codon: Original codon.
@@ -93,9 +82,8 @@ class BackTranslate(object):
         return dict(substitutions)
 
     def without_dna(self, reference_amino_acid, amino_acid):
-        """
-        Find single nucleotide substitutions that given a reference amino acid
-        explains an observed amino acid.
+        """Find single nucleotide substitutions that given a reference amino
+        acid explains an observed amino acid.
 
         :arg str reference_amino_acid: Original amino acid.
         :arg str amino_acid: Observed amino acid.
@@ -111,9 +99,8 @@ class BackTranslate(object):
         return dict(substitutions)
 
     def improvable(self):
-        """
-        Calculate all pairs of amino acid substututions that can be improved by
-        looking at the underlying codon.
+        """Calculate all pairs of amino acid substututions that can be improved
+        by looking at the underlying codon.
 
         :returns list: List of improvable substitutions.
         """

backtranslate/cli.py

-#!/usr/bin/env python
-
-
-from __future__ import (
-    absolute_import, division, print_function, unicode_literals)
-from future.builtins import str, zip
-
-import argparse
-import re
+from argparse import ArgumentParser, FileType, RawDescriptionHelpFormatter
+from re import findall
 
 from Bio import SeqIO
 
-from . import usage, version, doc_split
-from .backtranslate import BackTranslate
+from . import BackTranslate, usage, version, doc_split
 from .util import protein_letters_3to1, subst_to_cds
 
 
 def with_dna(input_handle, output_handle, offset, position, amino_acid):
-    """
-    Get all variants that result in the observed amino acid change.
+    """Get all variants that result in the observed amino acid change.
 
     :arg stream input_handle: Open readable handle to a FASTA file.
     :arg stream output_handle: Open writable handle to a file.
@@ -28,18 +19,17 @@ def with_dna(input_handle, output_handle, offset, position, amino_acid):
     :returns set: Variants that lead to the observed amino acid change.
     """
     bt = BackTranslate()
-    reference = str(SeqIO.parse(input_handle, 'fasta').next().seq)
+    reference = str(next(SeqIO.parse(input_handle, 'fasta')).seq)
     codon_pos = offset - 1 + (position - 1) * 3
     codon = reference[codon_pos:codon_pos + 3]
     substitutions = bt.with_dna(codon, protein_letters_3to1[amino_acid])
 
-    for subst in subst_to_cds(substitutions, (position - 1) * 3):
+    for subst in sorted(subst_to_cds(substitutions, (position - 1) * 3)):
         output_handle.write('{}\t{}\t{}\n'.format(*subst))
 
 
 def without_dna(output_handle, position, reference_amino_acid, amino_acid):
-    """
-    Get all variants that result in the observed amino acid change without
+    """Get all variants that result in the observed amino acid change without
     making use of the transcript.
 
     :arg stream output_handle: Open writable handle to a file.
@@ -61,76 +51,87 @@ def without_dna(output_handle, position, reference_amino_acid, amino_acid):
         output_handle.write(
             'This substitution can be improved by using `with_dna`.\n')
 
-    for subst in subst_to_cds(substitutions, (position - 1) * 3):
+    for subst in sorted(subst_to_cds(substitutions, (position - 1) * 3)):
         output_handle.write('{}\t{}\t{}\n'.format(*subst))
 
 
-def find_stops(input_handle, output_handle, offset):
-    """
-    Almost stop codon finder.
+def find_stops(input_handle, output_handle, offset, compact):
+    """Almost stop codon finder.
 
     :arg stream input_handle: Open readable handle to a FASTA file.
     :arg stream output_handle: Open writable handle to a file.
     :arg int offset: Position of the CDS start in the reference sequence.
+    :arg bool compact: Output one line per position.
     """
     bt = BackTranslate()
-    sequence = str(SeqIO.parse(input_handle, 'fasta').next().seq)
+    sequence = str(next(SeqIO.parse(input_handle, 'fasta')).seq)
 
-    for index, codon in enumerate(re.findall('...', sequence[offset - 1:])):
+    for index, codon in enumerate(findall('...', sequence[offset - 1:])):
         stop_positions = bt.with_dna(codon, '*')
 
-        for position in stop_positions:
-            for subst in stop_positions[position]:
+        for position in sorted(stop_positions):
+            if not compact:
+                for subst in sorted(stop_positions[position]):
+                    output_handle.write('{}\t{}\t{}\n'.format(
+                        offset + (index * 3) + position, *subst))
+            else:
                 output_handle.write('{}\t{}\t{}\n'.format(
-                    offset + (index * 3) + position, *subst))
+                    offset + (index * 3) + position,
+                    list(stop_positions[position])[0][0],
+                    ','.join(map(lambda x: x[1],
+                    sorted(stop_positions[position])))))
 
 
 def main():
-    """
-    Main entry point.
-    """
-    input_parser = argparse.ArgumentParser(add_help=False)
-    input_parser.add_argument('input_handle', metavar='INPUT',
-        type=argparse.FileType('r'), help='input file in FASTA format')
-    input_parser.add_argument('-o', dest='offset', type=int, default=1,
+    """Main entry point."""
+    input_parser = ArgumentParser(add_help=False)
+    input_parser.add_argument(
+        'input_handle', metavar='INPUT', type=FileType('r'),