Merge pull request #7 from czbiohub/olgabot/compare-peptide

Move peptide kmer comparison code out of jupyter notebooks

.travis.yml

@@ -12,7 +12,7 @@ before_install:
 install:
 - conda create -n testenv --yes python=$TRAVIS_PYTHON_VERSION pip
 - source activate testenv
-- conda install --yes --file conda_requirements.txt
+- conda install -c bioconda -c conda-forge --yes --file conda_requirements.txt
 - pip install -r requirements.txt
 - pip install .
 script:

Makefile

@@ -12,7 +12,10 @@ coverage:
 	coverage report --show-missing
 
 lint:
-	flake8 --exclude docs khtools
+	# ignore:
+	# E126 continuation line over-indented for hanging indent
+	# E127 continuation line over-indented for visual indent
+	flake8 --exclude docs,tests --ignore=E127,E126 khtools
 
 conda_install:
 	conda install --file conda_requirements.txt

conda_requirements.txt

@@ -4,3 +4,17 @@ flake8
 click
 tqdm
 colorama
+numpy
+networkx
+seaborn
+pandas
+ipykernel
+notebook
+joblib
+s3fs
+scipy
+matplotlib
+scikit-learn
+sourmash
+fastcluster
+biopython

environment.yml

@@ -0,0 +1,149 @@
+name: kh-tools
+channels:
+  - bioconda
+  - conda-forge
+  - r
+  - defaults
+dependencies:
+  - appnope=0.1.0=py37_1000
+  - asn1crypto=1.0.1=py37_0
+  - atomicwrites=1.3.0=py_0
+  - attrs=19.1.0=py_0
+  - backcall=0.1.0=py_0
+  - biopython=1.74=py37h01d97ff_0
+  - blas=2.12=openblas
+  - bleach=3.1.0=py_0
+  - bokeh=1.3.4=py37_0
+  - boto3=1.9.246=py_0
+  - botocore=1.12.246=py_0
+  - bzip2=1.0.6=h1de35cc_1002
+  - ca-certificates=2019.9.11=hecc5488_0
+  - certifi=2019.9.11=py37_0
+  - cffi=1.12.3=py37hccf1714_0
+  - chardet=3.0.4=py37_1003
+  - click=6.7=py_1
+  - colorama=0.4.1=py_0
+  - coverage=4.5.3=py37h1de35cc_0
+  - cryptography=2.7=py37h212c5bf_0
+  - cycler=0.10.0=py_1
+  - decorator=4.4.0=py_0
+  - defusedxml=0.6.0=py_0
+  - docutils=0.15.2=py37_0
+  - entrypoints=0.3=py37_1000
+  - fastcluster=1.1.25=py37h1702cab_1000
+  - flake8=3.7.7=py37_0
+  - freetype=2.10.0=h24853df_1
+  - holoviews=1.12.6=py_0
+  - httmock=1.2.6=py_0
+  - idna=2.8=py37_1000
+  - ijson=2.4=py_0
+  - ipykernel=5.1.1=py37h5ca1d4c_0
+  - ipython=7.8.0=py37h5ca1d4c_0
+  - ipython_genutils=0.2.0=py_1
+  - jedi=0.15.1=py37_0
+  - jinja2=2.10.3=py_0
+  - jmespath=0.9.4=py_0
+  - joblib=0.13.2=py_0
+  - jpeg=9c=h1de35cc_1001
+  - json5=0.8.5=py_0
+  - jsonschema=3.0.2=py37_0
+  - jupyter_client=5.3.3=py37_1
+  - jupyter_core=4.5.0=py_0
+  - jupyterlab=1.1.4=py_0
+  - jupyterlab_server=1.0.6=py_0
+  - kiwisolver=1.1.0=py37h770b8ee_0
+  - libblas=3.8.0=12_openblas
+  - libcblas=3.8.0=12_openblas
+  - libcxx=8.0.0=1
+  - libcxxabi=8.0.0=1
+  - libffi=3.2.1=h6de7cb9_1006
+  - libgfortran=3.0.1=0
+  - liblapack=3.8.0=12_openblas
+  - liblapacke=3.8.0=12_openblas
+  - libopenblas=0.3.7=hd44dcd8_1
+  - libpng=1.6.37=h2573ce8_0
+  - libsodium=1.0.17=h01d97ff_0
+  - libtiff=4.0.10=hd08fb8f_1003
+  - llvm-openmp=8.0.1=h770b8ee_0
+  - lz4-c=1.8.3=h6de7cb9_1001
+  - markupsafe=1.1.1=py37h1de35cc_0
+  - matplotlib=2.2.2=py37hbf02d85_2
+  - matplotlib-base=3.1.1=py37h3a684a6_1
+  - mccabe=0.6.1=py_1
+  - mistune=0.8.4=py37h1de35cc_1000
+  - more-itertools=4.3.0=py37_1000
+  - nbconvert=5.6.0=py37_1
+  - nbformat=4.4.0=py_1
+  - ncurses=6.1=h0a44026_1002
+  - networkx=2.3=py_0
+  - notebook=5.5.0=py37_0
+  - numpy=1.17.1=py37h6b0580a_0
+  - olefile=0.46=py_0
+  - openssl=1.1.1c=h01d97ff_0
+  - packaging=19.2=py_0
+  - pandas=0.25.1=py37h86efe34_0
+  - pandoc=2.7.3=0
+  - pandocfilters=1.4.2=py_1
+  - param=1.9.2=py_0
+  - parso=0.5.1=py_0
+  - patsy=0.5.1=py_0
+  - pexpect=4.7.0=py37_0
+  - pickleshare=0.7.5=py37_1000
+  - pillow=6.2.0=py37hb6f49c9_0
+  - pip=19.0.3=py37_0
+  - pluggy=0.9.0=py_0
+  - prometheus_client=0.7.1=py_0
+  - prompt_toolkit=2.0.10=py_0
+  - ptyprocess=0.6.0=py_1001
+  - py=1.8.0=py_0
+  - pycodestyle=2.5.0=py_0
+  - pycparser=2.19=py37_1
+  - pyflakes=2.1.1=py_0
+  - pygments=2.4.2=py_0
+  - pyopenssl=19.0.0=py37_0
+  - pyparsing=2.4.2=py_0
+  - pyrsistent=0.15.4=py37h01d97ff_0
+  - pysocks=1.7.1=py37_0
+  - pytest=3.9.1=py37_1000
+  - python=3.7.3=h0d93f26_0
+  - python-dateutil=2.8.0=py_0
+  - pytz=2019.2=py_0
+  - pyviz_comms=0.7.2=py_0
+  - pyyaml=5.1.2=py37h01d97ff_0
+  - pyzmq=18.1.0=py37hee98d25_0
+  - readline=7.0=hcfe32e1_1001
+  - requests=2.22.0=py37_1
+  - s3fs=0.1.6=py_0
+  - s3transfer=0.2.1=py37_0
+  - scikit-learn=0.21.3=py37hd4ffd6c_0
+  - scipy=1.3.1=py37hab3da7d_2
+  - seaborn=0.8.1=py_1
+  - send2trash=1.5.0=py_0
+  - setuptools=39.1.0=py37_0
+  - six=1.12.0=py37_1000
+  - sqlite=3.26.0=h1765d9f_1001
+  - statsmodels=0.10.1=py37heacc8b8_0
+  - terminado=0.8.2=py37_0
+  - testpath=0.4.2=py_1001
+  - tk=8.6.9=ha441bb4_1001
+  - tornado=5.1.1=py37h1de35cc_1000
+  - tqdm=4.31.1=py_0
+  - traitlets=4.3.3=py37_0
+  - urllib3=1.25.6=py37_0
+  - wcwidth=0.1.7=py_1
+  - webencodings=0.5.1=py_1
+  - wheel=0.33.1=py37_0
+  - xz=5.2.4=h1de35cc_1001
+  - yajl=2.1.0=0
+  - yaml=0.1.7=h1de35cc_1001
+  - zeromq=4.3.2=h6de7cb9_2
+  - zlib=1.2.11=h1de35cc_1004
+  - zstd=1.4.0=ha9f0a20_0
+  - pip:
+    - bz2file==0.98
+    - docopt==0.6.2
+    - khmer==2.1.1
+    - pipreqs==0.4.9
+    - screed==1.0
+    - yarg==0.1.9
+

khtools/__init__.py

@@ -16,3 +16,7 @@
 from . import s3_utils
 from . import sourmash_compare_utils
 from . import sourmash_utils
+
+__all__ = ['common', 'downsample_hashes', 'extract_metadata', 'idf',
+           'jaccard_utils', 'jupyter_utils', 'knn', 'os_utils', 's3_utils',
+           'sourmash_compare_utils', 'sourmash_utils']

khtools/commandline.py

@@ -21,7 +21,8 @@
              context_settings=settings)
 def cli():
     """
-    Kmer hashing tools contains data cleaning and visualization code for analyzing kmer-hashing similarity matrices
+    Kmer hashing tools contains data cleaning and visualization code for
+    analyzing kmer-hashing similarity matrices
     """
     pass
 

khtools/common.py

@@ -5,9 +5,9 @@
 from . import jupyter_utils
 
 
-
 FIGURE_FOLDER = os.path.join('..', 'figures')
 
+
 def get_notebook_basename():
     notebook_path = jupyter_utils.get_notebook_name()
     notebook_basename = os.path.basename(notebook_path).split('.ipynb')[0]
@@ -23,7 +23,8 @@ def get_figure_folder():
 def load_tabula_muris_annotations():
     """Fetch latest FACS annotations of Tabula Muris data from GitHub"""
     annotations = pd.read_csv(
-        'https://github.com/czbiohub/tabula-muris/raw/master/00_data_ingest/18_global_annotation_csv/annotations_facs.csv',
+        'https://github.com/czbiohub/tabula-muris/raw/master/00_data_ingest/'
+        '18_global_annotation_csv/annotations_facs.csv',
         index_col='cell')
 
     # Sanitize the input - no dots