Merge pull request #69 from churchmanlab/update2023

Update2023

.github/workflows/tests.yml

@@ -17,7 +17,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: 3.6
+        python-version: 3.8
     - name: Install without INDRA
       run: |
         pip install nose coverage

README.md

@@ -4,7 +4,7 @@
 [![Documentation](https://readthedocs.org/projects/genewalk/badge/?version=latest)](https://genewalk.readthedocs.io/en/latest/?badge=latest)
 [![PyPI version](https://badge.fury.io/py/genewalk.svg)](https://badge.fury.io/py/genewalk)
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat)](http://bioconda.github.io/recipes/genewalk/README.html)
-[![Python 3.6+](https://img.shields.io/pypi/pyversions/genewalk.svg)](https://www.python.org/downloads/release)
+[![Python 3.8+](https://img.shields.io/pypi/pyversions/genewalk.svg)](https://www.python.org/downloads)
 
 GeneWalk determines for individual genes the functions that are relevant in a
 particular biological context and experimental condition. GeneWalk quantifies

doc/conf.py

@@ -25,9 +25,9 @@
 author = 'GeneWalk Developers'
 
 # The short X.Y version
-version = '1.5'
+version = '1.6'
 # The full version, including alpha/beta/rc tags
-release = '1.5.3'
+release = '1.6.0'
 
 
 # -- General configuration ---------------------------------------------------

genewalk/__init__.py

@@ -12,4 +12,4 @@
 logging.getLogger('gensim.summarization.textcleaner').setLevel(logging.WARNING)
 
 
-__version__ = '1.5.3'
+__version__ = '1.6.0'

genewalk/cli.py

@@ -199,7 +199,8 @@ def run_main(args):
         save_pickle(MG.graph, project_folder, 'multi_graph')
         for i in range(args.nreps_graph):
             logger.info('%s/%s' % (i + 1, args.nreps_graph))
-            DW = run_walks(MG.graph, workers=args.nproc, size=args.dim_rep)
+            DW = run_walks(MG.graph, workers=args.nproc, 
+                           vector_size=args.dim_rep)
 
             # Pickle the node vectors (embeddings) and DW object
             if args.save_dw:
@@ -218,7 +219,7 @@ def run_main(args):
         for i in range(args.nreps_null):
             logger.info('%s/%s' % (i + 1, args.nreps_null))
             RG = get_rand_graph(MG)
-            DW = run_walks(RG, workers=args.nproc, size=args.dim_rep)
+            DW = run_walks(RG, workers=args.nproc, vector_size=args.dim_rep)
 
             # Pickle the node vectors (embeddings) and DW object
             if args.save_dw:

genewalk/deepwalk.py

@@ -95,7 +95,7 @@ def get_walks(self, workers=1):
         end = time.time()
         logger.info('Running random walks done in %.2fs' % (end - start))
 
-    def word2vec(self, sg=1, size=8, window=1, min_count=1, negative=5,
+    def word2vec(self, sg=1, vector_size=8, window=1, min_count=1, negative=5,
                  workers=1, sample=0):
         """Set the model based on Word2Vec
         Source: https://radimrehurek.com/gensim/models/word2vec.html
@@ -108,7 +108,7 @@ def word2vec(self, sg=1, size=8, window=1, min_count=1, negative=5,
         sg : Optional[int] {1, 0}
             Defines the training algorithm. If 1, skip-gram is employed;
             otherwise, CBOW is used. For GeneWalk this is set to 1.
-        size : Optional[int]
+        vector_size : Optional[int]
             Dimensionality of the node vectors. Default for GeneWalk is 8.
         window : Optional[int]
             a.k.a. context size. Maximum distance between the current and
@@ -132,7 +132,8 @@ def word2vec(self, sg=1, size=8, window=1, min_count=1, negative=5,
         """
         logger.info('Generating node vectors...')
         start = time.time()
-        self.model = Word2Vec(sentences=self.walks, sg=sg, size=size,
+        self.model = Word2Vec(sentences=self.walks, sg=sg, 
+                              vector_size=vector_size,
                               window=window, min_count=min_count,
                               negative=negative, workers=workers,
                               sample=sample)
@@ -223,4 +224,4 @@ def run_walks(graph, **kwargs):
     DW = DeepWalk(graph, **dw_args)
     DW.get_walks(kwargs.get('workers', 1))
     DW.word2vec(**kwargs)
-    return DW
+    return DW

genewalk/perform_statistics.py

@@ -234,8 +234,8 @@ def generate_output(self, alpha_fdr=1):
         df.drop(['pval_rep'+str(i) for i in range(len(self.nvs))],
                 axis=1, inplace=True) 
         df[self.gene_id_type] = df[self.gene_id_type].astype('category')
-        df[self.gene_id_type].cat.set_categories(df[self.gene_id_type].unique(),
-                                            inplace=True)
+        df[self.gene_id_type] = \
+        df[self.gene_id_type].cat.set_categories(df[self.gene_id_type].unique())
         df[['ncon_gene', 'ncon_go']] = \
             df[['ncon_gene', 'ncon_go']].astype('str')
         df = df.sort_values(by=[self.gene_id_type, 'global_padj', 'gene_padj',

setup.py

@@ -8,11 +8,11 @@
 
 
 def main():
-    install_list = ['numpy', 'pandas', 'networkx>=2.1', 'gensim<4', 'goatools',
+    install_list = ['numpy', 'pandas', 'networkx>=2.1', 'gensim>=4.0.0', 'goatools',
                     'scipy>=1.3.0', 'matplotlib', 'seaborn', 'plotly>=4.0.0']
 
     setup(name='genewalk',
-          version='1.5.3',
+          version='1.6.0',
           description='Determine gene function based on network embeddings.',
           long_description=long_description,
           long_description_content_type='text/markdown',
@@ -25,9 +25,10 @@ def main():
             'Intended Audience :: Science/Research',
             'License :: OSI Approved :: BSD License',
             'Operating System :: OS Independent',
-            'Programming Language :: Python :: 3.6',
-            'Programming Language :: Python :: 3.7',
             'Programming Language :: Python :: 3.8',
+            'Programming Language :: Python :: 3.9',
+            'Programming Language :: Python :: 3.10',
+            'Programming Language :: Python :: 3.11',
             'Topic :: Scientific/Engineering :: Bio-Informatics',
             ],
           keywords=['gene function', 'network', 'embedding'],