brie 2.2.2__tar.gz → 2.3.0__tar.gz

{brie-2.2.2 → brie-2.3.0}/PKG-INFO

@@ -1,16 +1,30 @@
 Metadata-Version: 2.1
 Name: brie
-Version: 2.2.2
+Version: 2.3.0
 Summary: BRIE: Bayesian regression for isoform estimate
 Home-page: https://brie.readthedocs.io
 Author: Yuanhua Huang
 Author-email: yuanhua@hku.hk
 License: Apache-2.0
 Keywords: RNA splicing,Bayesian regression,single cell RNA-seq,variantional inference
-Platform: UNKNOWN
 Requires-Python: >=3.5
-Provides-Extra: docs
 License-File: LICENSE
+Requires-Dist: anndata>=0.6
+Requires-Dist: scanpy>=1.5
+Requires-Dist: pysam>=0.15.2
+Requires-Dist: numpy>=1.18.0
+Requires-Dist: scipy>=1.4.1
+Requires-Dist: statsmodels>=0.11
+Requires-Dist: pandas>=0.23.0
+Requires-Dist: h5py>=2.9.0
+Requires-Dist: matplotlib>=3.1.2
+Requires-Dist: seaborn>=0.10.0
+Requires-Dist: tensorflow>=2.0.0
+Requires-Dist: tensorflow-probability>=0.8.0
+Requires-Dist: scikit-learn>=0.23
+Requires-Dist: click>=7.0.0
+Provides-Extra: docs
+Requires-Dist: sphinx_bootstrap_theme; extra == "docs"
 
 |PyPI| |Docs| |Build Status|
 
@@ -125,5 +139,3 @@ References
   quantification in single cells 
   <https://genomebiology.biomedcentral.com/articles/10.1186/s13059-017-1248-5>`_. 
   \ **Genome Biology**\, 2017; 18(1):123.
-
-

{brie-2.2.2 → brie-2.3.0}/brie/bin/count.py

@@ -17,7 +17,7 @@ from ..utils.io_utils import read_brieMM, read_gff, convert_to_annData
 #TODO: something wrong as there is no reads for isoform 2. Please check!!
 
 def smartseq_count(gff_file, samList_file, out_dir=None, nproc=1, 
-        event_type='SE', verbose=False):
+        event_type='SE', verbose=False, edge_hang=10, junc_hang=2):
     """CLI for counting reads supporting isoforms
     """
     # Parameter check
@@ -102,7 +102,7 @@ def smartseq_count(gff_file, samList_file, out_dir=None, nproc=1,
           %(len(genes), sam_table.shape[0], nproc))
 
     get_smartseq_matrix(genes, sam_table, out_dir, event_type=event_type, 
-        edge_hang=10, junc_hang=2, nproc=nproc, verbose=verbose)
+        edge_hang=edge_hang, junc_hang=junc_hang, nproc=nproc, verbose=verbose)
     
 
     ## Don't save into h5ad if not all genes only with two isoforms
@@ -134,7 +134,8 @@ def smartseq_count(gff_file, samList_file, out_dir=None, nproc=1,
 
 
 def droplet_count(gff_file, sam_file, barcode_file, out_dir=None, nproc=1, 
-                  event_type='SE', CB_tag='CB', UMI_tag='UR', verbose=False):
+                  event_type='SE', CB_tag='CB', UMI_tag='UR', verbose=False,
+                  edge_hang=10, junc_hang=2):
     """CLI for counting reads supporting isoforms
     """
     ## TODO: Parameter check
@@ -217,7 +218,8 @@ def droplet_count(gff_file, sam_file, barcode_file, out_dir=None, nproc=1,
           %(len(genes), cell_list.shape[0], nproc))
 
     res = get_droplet_matrix(genes, sam_file, cell_list, out_dir, event_type, 
-                             10, 2, CB_tag, UMI_tag, nproc, verbose)
+                             edge_hang, junc_hang, CB_tag, UMI_tag, nproc, 
+                             verbose)
     
     ## Don't save into h5ad if not all genes only with two isoforms
     n_trans = [len(g.trans) for g in genes]
@@ -278,6 +280,13 @@ def main():
     group2.add_option("--eventType", "-t", dest="event_type", default="SE",
         help="Type of splicing event for check. SE: skipping-exon; "
              "Any: no-checking [default: %default]")
+
+    group3 = OptionGroup(parser, "Reads compatibility")
+    group3.add_option("--minMatch", type="int", dest="min_match", default="10", 
+        help="Min matched bases to the isoform; consider the read length and "
+             "transcript completeness [default: %default]")
+    group3.add_option("--maxMiss", type="int", dest="max_miss", default="2", 
+        help="Max missed bases in the isoform range [default: %default]")
     
     # group.add_option("--add_premRNA", action="store_true", dest="add_premRNA", 
     #     default=False, help="Add the pre-mRNA as a transcript")
@@ -285,6 +294,7 @@ def main():
     parser.add_option_group(group0)
     parser.add_option_group(group1)
     parser.add_option_group(group2)
+    parser.add_option_group(group3)
     
     (options, args) = parser.parse_args()
     if len(sys.argv[1:]) == 0:
@@ -301,11 +311,13 @@ def main():
     
     if options.samList_file is not None:
         smartseq_count(options.gff_file, options.samList_file, options.out_dir, 
-            options.nproc, options.event_type, options.verbose)
+            options.nproc, options.event_type, options.verbose, 
+            options.min_match, options.max_miss)
     else:
         droplet_count(options.gff_file, options.sam_file, options.barcodes_file, 
-            options.out_dir, options.nproc, options.event_type, options.cell_tag,
-            options.UMI_tag, options.verbose)
+            options.out_dir, options.nproc, options.event_type, 
+            options.cell_tag, options.UMI_tag, options.verbose, 
+            options.min_match, options.max_miss)
 
 
 if __name__ == "__main__":

{brie-2.2.2 → brie-2.3.0}/brie/plot/LRtest_plot.py

@@ -75,7 +75,7 @@ def volcano(adata, x="cell_coeff", y="ELBO_gain", index=0, score_red=4,
     plt.scatter(xval[~idx], yval[~idx], color="gray")
     plt.scatter(xval[idx], yval[idx], color="firebrick")
     
-    lable = adata.var.index if anno_id is 'index' else adata.var[anno_id]
+    lable = adata.var.index if anno_id == 'index' else adata.var[anno_id]
     
     texts = []
     for i in idx_anno:

{brie-2.2.2 → brie-2.3.0}/brie/plot/base_plot.py

@@ -35,7 +35,7 @@ def counts(adata, genes, size='Psi', color=None, gene_key='index',
     if ncol is None:
         ncol = min(4, len(genes))
     if nrow is None:
-        nrow = np.ceil(len(genes) / ncol)
+        nrow = int(np.ceil(len(genes) / ncol))
     
     if color is None:
         color_use = None

{brie-2.2.2 → brie-2.3.0}/brie/utils/count.py

@@ -118,26 +118,34 @@ def _get_segment(exons, read):
 def check_reads_compatible(transcript, reads, edge_hang=10, junc_hang=2):
     """Check if reads are compatible with a transcript
     """
+    # TODO: the configuration can be further optimized
+    max_all_miss   = junc_hang
+    max_exon_miss  = junc_hang
+    min_all_match  = edge_hang
+    min_side_match = junc_hang
+
     is_compatible = [True] * len(reads)
     for i in range(len(reads)):
         _segs = _get_segment(transcript.exons, reads[i])
         
         # check mismatch to regions not in this transcript
-        if len(reads[i].positions) - sum(_segs) >= junc_hang:
+        if len(reads[i].positions) - sum(_segs) >= max_all_miss:
             is_compatible[i] = False
             continue
 
         # check if edge hang is too short
-        if (_segs[0] > 0 or _segs[-1] > 0) and sum(_segs[1:-1]) < edge_hang:
+        # it may be determined by reads length and transcript completeness
+        if (_segs[0] > 0 or _segs[-1] > 0) and sum(_segs[1:-1]) < min_all_match:
             is_compatible[i] = False
             continue
             
         # check if exon has been skipped
-        if len(_segs) > 4:
+        if len(_segs) > 2:
             for j in range(2, len(_segs) - 2):
-                if (_segs[j-1] >= junc_hang and _segs[j+1] >= junc_hang and
-                    transcript.exons[j-1, 1] - transcript.exons[j-1, 0] - 
-                    _segs[j] >= junc_hang):
+                exon_len = transcript.exons[j-1, 1] - transcript.exons[j-1, 0]
+                if (_segs[j-1] >= min_side_match and 
+                    _segs[j+1] >= min_side_match and
+                    (exon_len - _segs[j]) >= max_exon_miss):
                     is_compatible[i] = False
                     break
 
@@ -180,12 +188,16 @@ def fetch_reads_count(gene, sam_file, event_type="SE", RNA_type="spliced",
         idx_U1 = np.arange(n_readsPE, n_readsPE + n_readsU1)
         idx_U2 = np.arange(n_readsPE + n_readsU1, n_reads)
         
-        Rmat[idx_PE, i] = check_reads_compatible(_tran, reads["reads1"])
+        Rmat[idx_PE, i] = check_reads_compatible(
+            _tran, reads["reads1"], edge_hang=edge_hang, junc_hang=junc_hang)
         if len(reads["reads2"]) > 0:
-            Rmat[idx_PE, i] *= check_reads_compatible(_tran, reads["reads2"])
+            Rmat[idx_PE, i] *= check_reads_compatible(
+                _tran, reads["reads2"], edge_hang=edge_hang, junc_hang=junc_hang)
             
-        Rmat[idx_U1, i] = check_reads_compatible(_tran, reads["reads1u"])
-        Rmat[idx_U2, i] = check_reads_compatible(_tran, reads["reads2u"])
+        Rmat[idx_U1, i] = check_reads_compatible(
+            _tran, reads["reads1u"], edge_hang=edge_hang, junc_hang=junc_hang)
+        Rmat[idx_U2, i] = check_reads_compatible(
+            _tran, reads["reads2u"], edge_hang=edge_hang, junc_hang=junc_hang)
     
     return Rmat
 

{brie-2.2.2 → brie-2.3.0}/brie/utils/io_utils.py

@@ -48,8 +48,7 @@ def convert_to_annData(Rmat_dict, effLen_tensor, cell_note, gene_note,
                                effLen_tensor[:, 1, :], axis=1)
     varm['p_ambiguous'] = Prob_tensor[:, :, 2]
     
-    adata = anndata.AnnData(X=X, obs=obs, var=var, varm=varm,
-                            layers=layers, dtype='float32')
+    adata = anndata.AnnData(X=X, obs=obs, var=var, varm=varm, layers=layers)
     return adata
 
 

brie-2.3.0/brie/version.py

@@ -0,0 +1,2 @@
+__version__ = "2.3.0"
+

{brie-2.2.2 → brie-2.3.0}/brie.egg-info/PKG-INFO

@@ -1,16 +1,30 @@
 Metadata-Version: 2.1
 Name: brie
-Version: 2.2.2
+Version: 2.3.0
 Summary: BRIE: Bayesian regression for isoform estimate
 Home-page: https://brie.readthedocs.io
 Author: Yuanhua Huang
 Author-email: yuanhua@hku.hk
 License: Apache-2.0
 Keywords: RNA splicing,Bayesian regression,single cell RNA-seq,variantional inference
-Platform: UNKNOWN
 Requires-Python: >=3.5
-Provides-Extra: docs
 License-File: LICENSE
+Requires-Dist: anndata>=0.6
+Requires-Dist: scanpy>=1.5
+Requires-Dist: pysam>=0.15.2
+Requires-Dist: numpy>=1.18.0
+Requires-Dist: scipy>=1.4.1
+Requires-Dist: statsmodels>=0.11
+Requires-Dist: pandas>=0.23.0
+Requires-Dist: h5py>=2.9.0
+Requires-Dist: matplotlib>=3.1.2
+Requires-Dist: seaborn>=0.10.0
+Requires-Dist: tensorflow>=2.0.0
+Requires-Dist: tensorflow-probability>=0.8.0
+Requires-Dist: scikit-learn>=0.23
+Requires-Dist: click>=7.0.0
+Provides-Extra: docs
+Requires-Dist: sphinx_bootstrap_theme; extra == "docs"
 
 |PyPI| |Docs| |Build Status|
 
@@ -125,5 +139,3 @@ References
   quantification in single cells 
   <https://genomebiology.biomedcentral.com/articles/10.1186/s13059-017-1248-5>`_. 
   \ **Genome Biology**\, 2017; 18(1):123.
-
-

{brie-2.2.2 → brie-2.3.0}/brie.egg-info/SOURCES.txt

@@ -1,9 +1,5 @@
-.gitignore
-.readthedocs.yml
-.travis.yml
 LICENSE
 README.rst
-requirements.txt
 setup.py
 brie/__init__.py
 brie/settings.py
@@ -47,34 +43,4 @@ brie/utils/io_utils.py
 brie/utils/preprocessing.py
 brie/utils/run_utils.py
 brie/utils/sam_utils.py
-brie/utils/tran_utils.py
-brie/version1/brie.py
-brie/version1/brie_diff.py
-brie/version1/model_brie.py
-doc/Makefile
-doc/brie1.rst
-doc/brie_count.rst
-doc/brie_quant.rst
-doc/conf.py
-doc/index.rst
-doc/install.rst
-doc/quick_start.rst
-doc/release.rst
-doc/requirements.txt
-doc/tutorial.rst
-doc/image/BRIE2_roadmap.png
-examples/brie2_demo.sh
-examples/make_list.sh
-examples/demo_v1/anno_maker.sh
-examples/demo_v1/brie_demo.sh
-examples/gastrulation/E-MTAB-4079.130cells.txt
-examples/gastrulation/brie_sashimi.sh
-examples/gastrulation/gastrulation_130cells.sh
-examples/gastrulation/prepare_anno.sh
-examples/gastrulation/sashimi_setting.txt
-simulator/README.rst
-simulator/simuDropout.py
-simulator/simuPSI.py
-simulator/spanki_demo.sh
-simulator/utils.py
-tests/README.rst
+brie/utils/tran_utils.py

{brie-2.2.2 → brie-2.3.0}/brie.egg-info/entry_points.txt

@@ -4,4 +4,3 @@ brie-count = brie.bin.count:main
 brie-quant = brie.bin.quant:main
 brie1 = brie.version1.brie:main
 brie1-diff = brie.version1.brie_diff:main
-

brie-2.2.2/.gitignore

@@ -1,106 +0,0 @@
-.DS_Store*
-.vscode/
-temp/
-
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-env/
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-doc/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# pyenv
-.python-version
-
-# celery beat schedule file
-celerybeat-schedule
-
-# SageMath parsed files
-*.sage.py
-
-# dotenv
-.env
-
-# virtualenv
-.venv
-venv/
-ENV/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-

brie-2.2.2/.readthedocs.yml

@@ -1,16 +0,0 @@
-sphinx:
-  configuration: doc/conf.py
-build:
-  image: latest
-python:
-  version: 3.7
-  install:
-    - requirements: doc/requirements.txt
-    - requirements: requirements.txt
-    - method: pip
-      path: .
-      extra_requirements:
-          - docs
-    - method: setuptools
-      path: package
-  system_packages: true

brie-2.2.2/.travis.yml

@@ -1,10 +0,0 @@
-
-language: python
-python:
-  - "3.6"
-  - "3.7"
-cache: pip
-install:
-  - pip install pysam
-script:
-  - python setup.py check

brie-2.2.2/brie/version.py

@@ -1,2 +0,0 @@
-__version__ = "2.2.2"
-