PyPI release updates

Speed up nearest neighbor computation

README.md

@@ -6,26 +6,20 @@ Harmony is a unified framework for data visualization, analysis and interpretati
 
 #### Installation and dependencies
 1. Harmony has been implemented in Python3 and can be installed using:
-```
-        $> git clone git://github.com/dpeerlab/Harmony.git
-        $> cd Harmony
-        $> sudo -H pip3 install .
-
-	$> cd ../
-        $> git clone git://github.com/dpeerlab/Palantir.git
-        $> cd Palantir
-        $> sudo -H pip3 install .
-```
+
+        $> pip install harmonyTS
+        $> pip install palantir
+
 2. Harmony depends on a number of `python3` packages available on pypi and these dependencies are listed in `setup.py`
 All the dependencies will be automatically installed using the above commands
 
 3. To uninstall:
 
-		$> sudo -H pip3 uninstall harmony
+		$> pip uninstall harmonyTS
 
 4. If you would like to determine gene expression trends, please install <a href="https://cran.r-project.org"> R <a> programming language and the R package <a href="https://cran.r-project.org/web/packages/gam/">GAM </a>. You will also need to install the rpy2 module using 
 
-		$> sudo -H pip3 install rpy2
+		$> pip install rpy2
 		
 
 #### Usage

setup.py

@@ -5,35 +5,52 @@
 from warnings import warn
 
 if sys.version_info.major != 3:
-    raise RuntimeError('Palantir requires Python 3')
+    raise RuntimeError("Palantir requires Python 3")
 if sys.version_info.minor < 6:
-    warn('Analysis methods were developed using Python 3.6')
+    warn("Analysis methods were developed using Python 3.6")
 
 # get version
-with open('src/harmony/version.py') as f:
+with open("src/harmony/version.py") as f:
     exec(f.read())
-
+with open("README.md", "r") as fh:
+    long_description = fh.read()
 
 # install GraphDiffusion
-if shutil.which('pip3'):
-    call(['pip3', 'install', 'git+https://github.com/dpeerlab/Palantir.git'])
+if shutil.which("pip3"):
+    call(["pip3", "install", "git+https://github.com/dpeerlab/Palantir.git"])
 
 
-setup(name='harmony',
-      version=__version__,  # read in from the exec of version.py; ignore error   
-      description='Harmony is a unified framework for data visualization, analysis and interpretation of scRNA-seq data measured across discrete time points',
-      url='https://github.com/dpeerlab/harmony',
-      author='Manu Setty',
-      author_email='[email protected]',
-      package_dir={'': 'src'},
-      packages=['harmony'],
-      install_requires=[
-          'numpy>=1.14.2',
-          'pandas>=0.22.0',
-          'scipy>=1.0.1',
-          'sklearn',
-          'fa2',
-          'matplotlib>=2.2.2',
-          'seaborn>=0.8.1'
-      ],
-      )
+setup(
+    name="harmony_time_series",
+    version=__version__,  # read in from the exec of version.py; ignore error
+    description=(
+        "Harmony is a unified framework for data visualization, analysis "
+        "and interpretation of scRNA-seq data measured across discrete time points"
+    ),
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/dpeerlab/harmony",
+    author="Manu Setty",
+    author_email="[email protected]",
+    package_dir={"": "src"},
+    packages=["harmony"],
+    install_requires=[
+        "numpy>=1.14.2",
+        "pandas>=0.22.0",
+        "scipy>=1.0.1",
+        "sklearn",
+        "fa2",
+        "matplotlib>=2.2.2",
+        "seaborn>=0.8.1",
+    ],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+        "Operating System :: POSIX :: Linux",
+        "Development Status :: 5 - Production/Stable",
+        "Topic :: Scientific/Engineering :: Bio-Informatics",
+        "Topic :: Scientific/Engineering :: Visualization",
+    ],
+    python_requires='>=3.6',
+)

src/harmony/core.py

@@ -1,5 +1,6 @@
 import pandas as pd
 import numpy as np
+import scanpy as sc
 
 from scipy.sparse import find, csr_matrix
 from sklearn.neighbors import NearestNeighbors
@@ -41,16 +42,35 @@ def augmented_affinity_matrix(data_df, timepoints, timepoint_connections,
 
     # Nearest neighbor graph construction and affinity matrix
     print('Nearest neighbor computation...')
-    nbrs = NearestNeighbors(n_neighbors=n_neighbors,
-                            metric='euclidean', n_jobs=-2)
-    nbrs.fit(pca_projections.values)
-    dists, _ = nbrs.kneighbors(pca_projections.values)
-    adj = nbrs.kneighbors_graph(pca_projections.values, mode='distance')
-    # Scaling factors for affinity matrix construction
-    ka = np.int(n_neighbors / 3)
-    scaling_factors = pd.Series(dists[:, ka], index=cell_order)
+
+    # --------------------------------------------------------------------------
+    # nbrs = NearestNeighbors(n_neighbors=n_neighbors,
+    #                         metric='euclidean', n_jobs=-2)
+    # nbrs.fit(pca_projections.values)
+    # dists, _ = nbrs.kneighbors(pca_projections.values)
+    # adj = nbrs.kneighbors_graph(pca_projections.values, mode='distance')
+    # # Scaling factors for affinity matrix construction
+    # ka = np.int(n_neighbors / 3)
+    # scaling_factors = pd.Series(dists[:, ka], index=cell_order)
+    # # Affinity matrix
+    # nn_aff = _convert_to_affinity(adj, scaling_factors, True)
+    # --------------------------------------------------------------------------
+
+    temp = sc.AnnData(data_df.values)
+    sc.pp.neighbors(temp, n_pcs=0, n_neighbors=n_neighbors)
+    kNN = temp.uns['neighbors']['distances']
+
+    # Adaptive k
+    adaptive_k = int(np.floor(n_neighbors / 3))
+    scaling_factors = np.zeros(data_df.shape[0])
+
+    for i in np.arange(len(scaling_factors)):
+        scaling_factors[i] = np.sort(kNN.data[kNN.indptr[i]:kNN.indptr[i + 1]])[adaptive_k - 1]
+
+    scaling_factors = pd.Series(scaling_factors, index=cell_order)
+
     # Affinity matrix
-    nn_aff = _convert_to_affinity(adj, scaling_factors, True)
+    nn_aff = _convert_to_affinity(kNN, scaling_factors, True)
 
     # Mututally nearest neighbor affinity matrix
     # Initilze mnn affinity matrix
@@ -96,7 +116,7 @@ def _convert_to_affinity(adj, scaling_factors, with_self_loops=False):
     """
     N = adj.shape[0]
     rows, cols, dists = find(adj)
-    dists = dists ** 2/ (scaling_factors.values[rows] ** 2)
+    dists = dists ** 2/(scaling_factors.values[rows] ** 2)
 
     # Self loops
     if with_self_loops:

src/harmony/version.py

@@ -1 +1 @@
-__version__ = "0.1.1"
+__version__ = "0.1.2"