Merge pull request #18 from CGATOxford/TS-RefactorTools

Ts refactor tools

.travis.yml

@@ -0,0 +1,29 @@
+language: python
+
+python:
+  - "2.7"
+#  - "3.4"
+
+script:
+  - cd $TRAVIS_BUILD_DIR ; pip install cython; python setup.py install
+
+after_script:
+  - umi_tools --help
+  - umi_tools extract --help
+  - umi_tools dedup --help
+
+# to do
+#deploy:
+#  provider: pypi
+#  user: toms
+#  password:
+#    secure: my_secure_password
+#  on:
+#    tags: true
+#    branch: master
+
+
+notifications:
+  email:
+    - [email protected]
+    - [email protected]

MANIFEST.in

@@ -0,0 +1,2 @@
+# extensions
+include umi_tools/*.pyx

README.rst

@@ -1,35 +1,72 @@
 Tools for dealing with Unique Molecular Identifiers
 ====================================================
 
-This repository contains a number of tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs). Currently there are two tools::
+This repository contains tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs). Currently there are two tools:
 
-extract_umi.py:   Flexible removal of UMI sequences from fastq reads.
-                  UMIs are removed and appended to the read name. Any other barcode, for example a 
-                  library barcode, is left on the read.
+* extract: Flexible removal of UMI sequences from fastq reads.
+    UMIs are removed and appended to the read name. Any other barcode, for example a library barcode, is left on the read.
 
-dedup_umi.py:     Implements a number of different UMI deduplication schemes. 
-                  The recommended methods are `directional_adjecency` and `adjecency`. In general 
-                  `directional_adjecency` seems to be less sensitive to starting conditions, but there 
-                  are situations where `adjecency` might out perform.
+* dedup: Implements a number of different UMI deduplication schemes.
+    The recommended method is `directional_adjecency`.
 
 See simulation results at the `CGAT blog <https://cgatoxford.wordpress.com/2015/08/14/unique-molecular-identifiers-the-problem-the-solution-and-the-proof/>`_.
 
 `Genome Science 2015 poster <http://f1000research.com/posters/4-728>`_.
 
+Preprint on the way shortly...
+
+
 Installation
 ------------
 
-Both tools are just python scripts. Type
+If you're using Conda, you can use:
+
+.. code:: bash
+
+   conda install -c https://conda.anaconda.org/toms umi_tools
+
+Or pip:
+
+.. code:: bash
+
+   pip install umi_tools
+
+
+Or if you'd like to work directly from the git repository:
+
+.. code:: bash
+
+   git clone [email protected]:CGATOxford/UMI-tools.git
+
+Enter repository and run:
 
-```
-python dedup_umi.py --help
-```
+.. code:: bash
 
-or
+   python setup.py install
 
 
-```
-python extract_umi.py --help
-```
+Help
+----- 
 
-for help. `dedup_umi.py` is dependent on `numpy`, `pandas` and both are dependent, at the moment, on `CGAT <https://www.cgat.org/downloads/public/cgat/documentation/cgat.html#cgat>`_.
+To get help on umi_tools run
+
+.. code:: bash
+
+   `umi_tools --help`
+
+To get help on umi_tools extract run
+
+.. code:: bash
+
+   `umi_tools extract --help`
+
+To get help on umi_tools dedup run
+
+.. code:: bash
+
+   `umi_tools dedup --help`
+
+
+Dependencies
+------------
+umi_tools is dependent on `numpy`, `pandas`, `cython`, `pysam` and `future`

requirements.txt

@@ -0,0 +1,6 @@
+setuptools>=1.1
+cython>=0.19
+numpy>=1.7
+pandas>=0.12.0
+pysam>=0.8.4
+future

setup.cfg

@@ -0,0 +1,2 @@
+[metadata]
+description-file = README.rst

setup.py

@@ -0,0 +1,111 @@
+import sys
+import os
+import glob
+
+try:
+    import Cython
+except ImportError:
+    raise ImportError(
+        "UMI-tools requires cython to "
+        "be installed before running setup.py (pip install cython)")
+
+try:
+    import pysam
+except ImportError:
+    raise ImportError(
+        "UMI-tools requires pysam to "
+        "be installed before running setup.py (pip install pysam)")
+
+########################################################################
+########################################################################
+# Import setuptools
+# Use existing setuptools, otherwise try ez_setup.
+
+try:
+    import setuptools
+except ImportError:
+    raise ImportError(
+        "UMI-tools requires setuptools"
+        "be installed before running setup.py (pip install setuptools)")
+
+from setuptools import setup, find_packages, Extension
+
+from distutils.version import LooseVersion
+if LooseVersion(setuptools.__version__) < LooseVersion('1.1'):
+    print ("Version detected:", LooseVersion(setuptools.__version__))
+    raise ImportError(
+        "UMI-tools requires setuptools 1.1 higher")
+
+from Cython.Build import cythonize
+########################################################################
+########################################################################
+# collect umi_tools version
+sys.path.insert(0, "umi_tools")
+import version
+
+version = version.__version__
+
+###############################################################
+###############################################################
+# Define dependencies 
+# Perform a umi_tools Installation
+
+major, minor1, minor2, s, tmp = sys.version_info
+
+if (major == 2 and minor1 < 7) or major < 2:
+    raise SystemExit("""UMI-tools requires Python 2.7 or later.""")
+
+umi_tools_packages = ["umi_tools"]
+umi_tools_package_dirs = {'umi_tools': 'umi_tools'}
+
+install_requires = []
+
+for requirement in (
+        l.strip() for l in open('requirements.txt') if not l.startswith("#")):
+    install_requires.append(requirement)
+
+
+##########################################################
+##########################################################
+# Classifiers
+classifiers = """
+Development Status :: 3 - Alpha
+Intended Audience :: Science/Research
+Intended Audience :: Developers
+License :: OSI Approved
+Programming Language :: Python
+Topic :: Software Development
+Topic :: Scientific/Engineering
+Operating System :: POSIX
+Operating System :: Unix
+Operating System :: MacOS
+"""
+
+setup(
+    # package information
+    name='umi_tools',
+    version=version,
+    description='umi-tools: Tools for UMI analyses',
+    author='Ian Sudbery',
+    author_email='[email protected]',
+    license="MIT",
+    platforms=["any"],
+    keywords="computational genomics",
+    long_description='umi-tools: Tools for UMI analyses',
+    classifiers=list(filter(None, classifiers.split("\n"))),
+    url="https://github.com/CGATOxford/UMI-tools",
+    download_url="https://github.com/CGATOxford/UMI-tools/tarball/%s" % version,
+    # package contents
+    packages=umi_tools_packages,
+    package_dir=umi_tools_package_dirs,
+    include_package_data=True,
+    # dependencies
+    install_requires=install_requires,
+    # extension modules
+    ext_modules=cythonize("umi_tools/_dedup_umi.pyx"),
+    entry_points={
+        'console_scripts': ['umi_tools = umi_tools.umi_tools:main']
+    },
+    # other options
+    zip_safe=False,
+)