Merge pull request #53 from phac-nml/development

Release v2.1.0

.travis.yml

@@ -10,7 +10,6 @@ notifications: # set notification options
 
 language: python
 python:
-  - '3.5'
   - '3.6'
 os:
   - linux
@@ -20,6 +19,7 @@ os:
 branches:
   only:
     - master
+    - development
 
 # Blacklist of branches to not run CI testing on.
 # branches:

README.rst

@@ -1,17 +1,20 @@
 |logo|
 
+|conda| |nbsp| |pypi| |nbsp| |license| |nbsp| |nbsp| Master:|citest-master| |nbsp| Development:|citest-dev|
 
-|license| |nbsp| |citest| |nbsp| |pypi| |nbsp| |conda| 
 
-.. |logo| image:: https://i.imgur.com/yYOkFlH.png
-    :target: https://github.com/phac-nml/bio_hansel
+
+.. |logo| image:: logo.png
+    :target: https://github.com/phac-nml/biohansel
 .. |pypi| image:: https://badge.fury.io/py/bio-hansel.svg
     :target: https://pypi.python.org/pypi/bio_hansel/
 .. |license| image:: https://img.shields.io/badge/License-Apache%20v2.0-blue.svg
     :target: http://www.apache.org/licenses/LICENSE-2.0
-.. |citest|  image:: https://travis-ci.org/phac-nml/bio_hansel.svg?branch=master
-    :target: https://travis-ci.org/phac-nml/bio_hansel
-.. |conda|   image:: https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat-square
+.. |citest-dev|  image:: https://travis-ci.org/phac-nml/biohansel.svg?branch=development
+    :target: https://travis-ci.org/phac-nml/biohansel
+.. |citest-master| image:: https://travis-ci.org/phac-nml/biohansel.svg?branch=master
+    :target: https://travis-ci.org/phac-nml/biohansel
+.. |conda|   image:: https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg
     :target: https://bioconda.github.io/recipes/bio_hansel/README.html
 .. |nbsp| unicode:: 0xA0
     :trim:
@@ -26,7 +29,7 @@ Works on genome assemblies (FASTA files) or reads (FASTQ files)! Accepts Gzipped
 Citation
 ========
 
-If you find this tool useful, please cite as:
+If you find the ``biohansel`` tool useful, please cite as:
 
 .. epigraph::
 
@@ -38,11 +41,11 @@ If you find this tool useful, please cite as:
 Requirements and Dependencies
 =============================
 
-This tool has only been tested on Linux (specifically Arch Linux). It may or may not work on OSX.
+Each new build of ``biohansel`` is automatically tested on Linux using `Continuous Integration <https://travis-ci.org/phac-nml/bio_hansel/branches>`_. ``biohansel`` has been confirmed to work on Mac OSX (versions 10.13.5 Beta and 10.12.6) when installed with Conda_.
 
-These are the dependencies required for ``bio_hansel``:
+These are the dependencies required for ``biohansel``:
 
-- Python_ (>=v3.5)
+- Python_ (>=v3.6)
     - numpy_ >=1.12.1
     - pandas_ >=0.20.1
     - pyahocorasick_ >=1.1.6
@@ -55,21 +58,21 @@ Installation
 With Conda_
 -----------
 
-Install ``bio_hansel`` from Bioconda_ with Conda_ (`Conda installation instructions <https://bioconda.github.io/#install-conda>`_):
+Install ``biohansel`` from Bioconda_ with Conda_ (`Conda installation instructions <https://bioconda.github.io/#install-conda>`_):
 
 .. code-block:: bash
 
     # setup Conda channels for Bioconda and Conda-Forge (https://bioconda.github.io/#set-up-channels)
     conda config --add channels defaults
     conda config --add channels conda-forge
     conda config --add channels bioconda
-    # install bio_hansel
+    # install biohansel
     conda install bio_hansel
 
 With pip_ from PyPI_
 ---------------------
 
-Install ``bio_hansel`` from PyPI_ with pip_:
+Install ``biohansel`` from PyPI_ with pip_:
 
 .. code-block:: bash
 
@@ -82,12 +85,12 @@ Or install the latest master branch version directly from Github:
 
 .. code-block:: bash
 
-    pip install git+https://github.com/phac-nml/bio_hansel.git@master
+    pip install git+https://github.com/phac-nml/biohansel.git@master
 
 Install into Galaxy_ (version >= 17.01)
 ---------------------------------------
 
-Install ``bio_hansel`` from the main Galaxy_ toolshed:
+Install ``biohansel`` from the main Galaxy_ toolshed:
 
 https://toolshed.g2.bx.psu.edu/repository?repository_id=59b90ef18cc5dbbc&changeset_revision=4654c51dae72
 
@@ -246,6 +249,38 @@ Analysis of all FASTA/FASTQ files in a directory
 ``hansel`` will only attempt to analyze the FASTA/FASTQ files within the specified directory and will not descend into any subdirectories!
 
 
+Development
+===========
+
+
+Get the latest development code using Git from GitHub:
+
+.. code-block:: bash
+
+    git clone https://github.com/phac-nml/biohansel.git
+    cd biohansel/
+    git checkout development
+    # Create a virtual environment (virtualenv) for development
+    virtualenv -p python3 .venv
+    # Activate the newly created virtualenv
+    source .venv/bin/activate
+    # Install biohansel into the virtualenv in "editable" mode
+    pip install -e .
+
+
+Run tests with pytest_:
+
+.. code-block:: bash
+
+    # In the biohansel/ root directory, install pytest for running tests
+    pip install pytest
+    # Run all tests in tests/ directory
+    pytest
+    # Or run a specific test module
+    pytest -s tests/test_qc.py
+
+
+
 Legal
 =====
 
@@ -280,3 +315,4 @@ Contact
 .. _attrs: http://www.attrs.org/en/stable/
 .. _Python: https://www.python.org/
 .. _Galaxy: https://galaxyproject.org/
+.. _pytest: https://docs.pytest.org/en/latest/

bio_hansel/__init__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-__version__ = '2.0.0'
+__version__ = '2.1.0'
 program_name = 'bio_hansel'
 program_summary = 'Subtype microbial genomes using SNV targeting k-mer subtyping schemes.'
 program_desc = program_summary + '''

bio_hansel/const.py

@@ -10,7 +10,7 @@
                                 'version': '0.5.0',
                                 'subtyping_params': SubtypingParams(low_coverage_depth_freq=20)},
                  'enteritidis': {'file': resource_filename(program_name, 'data/enteritidis/tiles.fasta'),
-                                 'version': '0.7.0',
+                                 'version': '0.8.0',
                                  'subtyping_params': SubtypingParams(low_coverage_depth_freq=50)}}
 
 COLUMNS_TO_REMOVE = '''
@@ -65,4 +65,4 @@
 REGEX_FASTQ = re.compile(r'^(.+)\.(fastq|fq|fastqsanger)(\.gz)?$')
 REGEX_FASTA = re.compile(r'^.+\.(fasta|fa|fna|fas)(\.gz)?$')
 
-JSON_EXT_TMPL = '{}.json'
+JSON_EXT_TMPL = '{}.json'

bio_hansel/main.py

@@ -4,18 +4,20 @@
 import argparse
 import logging
 import sys
-import os
 import re
+import os
 from typing import Optional, List, Any, Tuple
+
+import attr
 import pandas as pd
 
 from . import program_desc, __version__
 from .const import SUBTYPE_SUMMARY_COLS, REGEX_FASTQ, REGEX_FASTA, JSON_EXT_TMPL
 from .subtype import Subtype
 from .subtype_stats import subtype_counts
 from .subtyper import \
-    query_contigs_ac, \
-    query_reads_ac
+    subtype_contigs_samples, \
+    subtype_reads_samples
 from .metadata import read_metadata_table, merge_metadata_with_summary_results
 from .utils import \
     genome_name_from_fasta_path, \
@@ -192,36 +194,36 @@ def main():
     scheme_subtype_counts = subtype_counts(scheme_fasta)
     logging.debug(args)
     subtyping_params = init_subtyping_params(args, scheme)
-    input_genomes, reads = collect_inputs(args)
-    if len(input_genomes) == 0 and len(reads) == 0:
+    input_contigs, input_reads = collect_inputs(args)
+    if len(input_contigs) == 0 and len(input_reads) == 0:
         raise Exception('No input files specified!')
     df_md = None
     if args.scheme_metadata:
         df_md = read_metadata_table(args.scheme_metadata)
     n_threads = args.threads
 
-    subtype_results = []  # type: List[Subtype]
-    dfs = []  # type: List[pd.DataFrame]
-    if len(input_genomes) > 0:
-        query_contigs_ac(subtype_results=subtype_results,
-                         dfs=dfs,
-                         input_genomes=input_genomes,
-                         scheme=scheme,
-                         scheme_name=scheme_name,
-                         subtyping_params=subtyping_params,
-                         scheme_subtype_counts=scheme_subtype_counts,
-                         n_threads=n_threads)
-    if len(reads) > 0:
-        query_reads_ac(subtype_results=subtype_results,
-                       dfs=dfs,
-                       reads=reads,
-                       scheme=scheme,
-                       scheme_name=scheme_name,
-                       subtyping_params=subtyping_params,
-                       scheme_subtype_counts=scheme_subtype_counts,
-                       n_threads=n_threads)
+    subtype_results = []  # type: List[Tuple[Subtype, pd.DataFrame]]
+    if len(input_contigs) > 0:
+        contigs_results = subtype_contigs_samples(input_genomes=input_contigs,
+                                                  scheme=scheme,
+                                                  scheme_name=scheme_name,
+                                                  subtyping_params=subtyping_params,
+                                                  scheme_subtype_counts=scheme_subtype_counts,
+                                                  n_threads=n_threads)
+        logging.info('Generated %s subtyping results from %s contigs samples', len(contigs_results), len(input_contigs))
+        subtype_results += contigs_results
+    if len(input_reads) > 0:
+        reads_results = subtype_reads_samples(reads=input_reads,
+                                              scheme=scheme,
+                                              scheme_name=scheme_name,
+                                              subtyping_params=subtyping_params,
+                                              scheme_subtype_counts=scheme_subtype_counts,
+                                              n_threads=n_threads)
+        logging.info('Generated %s subtyping results from %s contigs samples', len(reads_results), len(input_reads))
+        subtype_results += reads_results
 
-    dfsummary = pd.DataFrame(subtype_results)
+    dfs = [df for st, df in subtype_results]  # type: List[pd.DataFrame]
+    dfsummary = pd.DataFrame([attr.asdict(st) for st, df in subtype_results])
     dfsummary = dfsummary[SUBTYPE_SUMMARY_COLS]
 
     if dfsummary['avg_tile_coverage'].isnull().all():