exprmat 0.1.35__tar.gz → 0.1.37__tar.gz

{exprmat-0.1.35 → exprmat-0.1.37}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exprmat
-Version: 0.1.35
+Version: 0.1.37
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
@@ -16,8 +16,8 @@ Requires-Dist: igraph>=0.10.3
 Requires-Dist: pyarrow
 Requires-Dist: pyfaidx>=0.7.0,<0.8.0
 Requires-Dist: rustworkx
-Requires-Dist: scipy>=1.4,<2.0.0
-Requires-Dist: scikit-learn>=1.0,<2.0.0
+Requires-Dist: scipy>=1.11,<2.0.0
+Requires-Dist: scikit-learn>=1.1,<2.0.0
 Requires-Dist: tqdm>=4.62
 Requires-Dist: typeguard>=4.0
 Requires-Dist: umap-learn>=0.5.0
@@ -55,6 +55,7 @@ Requires-Dist: hdbscan
 Requires-Dist: graphtools
 Requires-Dist: bincsync>=0.3.0
 Requires-Dist: pybigwig
+Requires-Dist: pybedgraph
 Requires-Dist: loompy
 Requires-Dist: squidpy
 Requires-Dist: zarr
@@ -68,6 +69,12 @@ Requires-Dist: pyogrio>=0.7.2
 Requires-Dist: pyproj>=3.3.0
 Requires-Dist: geopandas
 Requires-Dist: packaging
+Requires-Dist: lightmotif
+Requires-Dist: pymemesuite
+Requires-Dist: formulaic>=1.0.2
+Requires-Dist: formulaic-contrasts>=0.2.0
+Requires-Dist: cython
+Requires-Dist: pyfastx
 Requires-Dist: sphinx ; extra == 'dev'
 Requires-Dist: twine ; extra == 'dev'
 Requires-Dist: ipykernel ; extra == 'dev'
@@ -75,9 +82,7 @@ Requires-Dist: ipytree ; extra == 'dev'
 Provides-Extra: dev
 License-File: license
 Summary: exprmat: Routines for expression matrices
-Author: Kai Zhang <kai@kzhang.org>
 Author-email: Zheng Yang <xornent@outlook.com>
-License: MIT
 Requires-Python: >=3.9, <3.13
 Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
 Project-URL: Repository, https://github.com/yang-z-03/exprmat

{exprmat-0.1.35 → exprmat-0.1.37}/exprmat/__init__.py

@@ -12,6 +12,50 @@ import pandas as pd
 import pathlib
 from PIL import Image
 
+# build cython package
+
+try: import exprmat.peaks.idr.invcdf
+except ImportError:
+    
+    from exprmat.ansi import info
+    info('seems to be your first use of exprmat. the C modules are not compiled yet.')
+    info('compiling cython extension modules ...')
+
+    from distutils.core import setup
+    from distutils.extension import Extension
+    from Cython.Distutils import build_ext
+    from Cython.Build import cythonize
+    import numpy
+    import sys
+
+    # change to the project source directory
+    # thus we can build the extension in the source directory.
+    sys.argv = ['', 'build_ext', '--inplace']
+    cwd = os.getcwd()
+    os.chdir(os.path.dirname(__file__))
+    info(f'entering working directory: {os.getcwd()}')
+
+    extensions = [
+        Extension(
+            'peaks.idr.invcdf',
+            [__file__.replace('__init__.py', os.path.join('peaks', 'idr', 'invcdf.pyx'))],
+            include_dirs = [numpy.get_include()],
+            define_macros = [('NPY_NO_DEPRECATED_API', 'NPY_1_7_API_VERSION')]
+        )
+    ]
+    
+    setup(
+        name = 'peaks.idr.invcdf',
+        cmdclass = { 'build_ext': build_ext },
+        ext_modules = cythonize(extensions, language_level = 3, quiet = True)
+    )
+
+    os.chdir(cwd)
+    # remove the autogenerated build directory. since we compile inplace.
+    os.system(f'rm -r {os.path.join(os.path.dirname(__file__), "build")}')
+    info('compilation finished.')
+
+
 from exprmat.configuration import default as config
 from exprmat.ansi import warning, info
 
@@ -19,7 +63,7 @@ mu.set_options(pull_on_update = False)
 Image.MAX_IMAGE_PIXELS = config['max.image']
 
 DATABASE_SETUP_MESSAGE = """
-The exprmat package do not come with a included database after version 0.1.25, 
+The exprmat package do not come with an included database after version 0.1.25, 
 due to the extensive size of the reference data. You need to setup the database
 and configure it properly with configuration file `.exprmatrc` under your
 user root or current working directory
@@ -39,9 +83,11 @@ default_finders = [
     os.path.join(str(pathlib.Path.home()), '.exprmatrc')
 ]
 
+DEFAULT_CONFIG = '[internals]'
 for finder in default_finders:
     if os.path.exists(finder):
-        info(f'load configuration from {finder}')
+        DEFAULT_CONFIG = finder
+        if False: info(f'load configuration from {finder}')
         with open(finder, 'r') as f:
             import json
             workspace_config = json.load(f)
@@ -94,6 +140,7 @@ def version():
     MAJOR, MINOR, REVISION = [int(x) for x in ver_string.split('.')]
     info(f'exprmat {MAJOR}.{MINOR}.{REVISION} / exprmat-db {db_ver if db_ver is not None else "(Not installed)"}')
     info(f'os: {os.name} ({sys.platform})  platform version: {platform.release()}')
+    info(f'loaded configuration from {finder}')
     info(f'current working directory: {os.getcwd()}')
     info(f'current database directory: {config["data"]} ({db_ver if db_ver is not None else "(Not found)"})')
     memory()

{exprmat-0.1.35 → exprmat-0.1.37}/exprmat/data/finders.py

@@ -75,6 +75,43 @@ def get_genome_model(assembly):
     return pandas.read_feather(path)
 
 
+def get_genome_ranges(assembly, fname, as_grange = False):
+    
+    taxa = cfg['taxa.reference'][assembly.lower()]
+    path = os.path.join(basepath, taxa, 'assemblies', assembly.lower(), f'{fname}.feather')
+    feather = pandas.read_feather(path)
+    
+    if as_grange: 
+        import genomicranges
+        return genomicranges.GenomicRanges.from_pandas(
+            feather[['ucsc', 'start', 'end', 'strand', 'gene']].rename(
+            columns = {'ucsc': 'seqnames', 'start': 'starts', 'end': 'ends'}
+        ))
+    else: return feather
+
+
+def get_genome_first_exonic(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'first-exonic', as_grange = as_grange)
+
+def get_genome_other_exonic(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'other-exonic', as_grange = as_grange)
+
+def get_genome_first_intronic(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'first-intronic', as_grange = as_grange)
+
+def get_genome_transcript(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'genebody', as_grange = as_grange)
+
+def get_genome_promoters(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'promoters', as_grange = as_grange)
+
+def get_genome_utr3(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'utr3', as_grange = as_grange)
+
+def get_genome_utr5(assembly, as_grange = False):
+    return get_genome_ranges(assembly, 'utr5', as_grange = as_grange)
+
+
 def get_mapper_name(taxa):
     '''
     Return a name mapper mapping from gene names to universal gene id across species.