Merge pull request #114 from faridrashidi/develop

release v0.1.0

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.0.21
+current_version = 0.1.0
 commit = True
 message = [skip ci] {current_version} → {new_version}
 tag = False

.github/workflows/ci.yml

@@ -56,7 +56,7 @@ jobs:
             fail-fast: false
             max-parallel: 20
             matrix:
-                python: [3.6, 3.7, 3.8, 3.9]
+                python: [3.7, 3.8, 3.9]
                 os: [ubuntu-latest, macos-latest]
         env:
             OS: ${{ matrix.os }}

.pre-commit-config.yaml

@@ -25,7 +25,7 @@ repos:
     -   id: check-merge-conflict
     -   id: check-ast
     -   id: check-symlinks
-    -   id: check-added-large-files
+    # -   id: check-added-large-files
     -   id: check-executables-have-shebangs
     -   id: fix-encoding-pragma
         args: [--remove]

Makefile

@@ -1,3 +1,11 @@
+clean:
+	rm -rf docs/build
+	rm -rf htmlcov
+	rm -rf .coverage*
+	rm -rf docs/source/trisicell*
+	rm -rf docs/source/auto_examples
+	rm -rf docs/source/gen_modules
+
 test:
 	pytest --cov=trisicell ./tests
 	rm -rf .coverage*

docs/source/api.rst

@@ -110,3 +110,5 @@ This module offers a bunch of functions for simulating data.
     :toctree: .
 
     datasets.example
+    datasets.sublines_bwes
+    datasets.sublines_scrnaseq

docs/source/conf.py

@@ -122,6 +122,7 @@
     "sklearn": ("https://scikit-learn.org/stable/", None),
     "seaborn": ("https://seaborn.pydata.org/", None),
     "anndata": ("https://anndata.readthedocs.io/en/latest/", None),
+    "mudata": ("https://mudata.readthedocs.io/en/latest/", None),
 }
 
 

docs/source/release_notes.rst

@@ -7,8 +7,17 @@ Release Notes
 =============
 
 
+Version 0.1.0 :small:`June 24, 2022`
+------------------------------------
+
+This version includes:
+
+    - Add sublines bWES dataset.
+    - Add sublines scRNAseq dataset.
+
+
 Version 0.0.21 :small:`April 22, 2022`
------------------------------------------
+--------------------------------------
 
 This version includes:
 
@@ -93,7 +102,7 @@ This version includes:
 
 
 Version 0.0.12 :small:`July 7, 2021`
--------------------------------------
+------------------------------------
 
 This version includes:
 
@@ -102,7 +111,7 @@ This version includes:
 
 
 Version 0.0.11 :small:`July 4, 2021`
--------------------------------------
+------------------------------------
 
 This version includes:
 
@@ -112,7 +121,7 @@ This version includes:
 
 
 Version 0.0.10 :small:`July 3, 2021`
--------------------------------------
+------------------------------------
 
 This version includes:
 
@@ -121,7 +130,7 @@ This version includes:
 
 
 Version 0.0.9 :small:`June 17, 2021`
--------------------------------------
+------------------------------------
 
 This version includes:
 
@@ -130,7 +139,7 @@ This version includes:
 
 
 Version 0.0.8 :small:`June 12, 2021`
--------------------------------------
+------------------------------------
 
 This version includes:
 
@@ -139,7 +148,7 @@ This version includes:
 
 
 Version 0.0.7 :small:`May 29, 2021`
--------------------------------------
+-----------------------------------
 
 This version includes:
 
@@ -152,7 +161,7 @@ This version includes:
 
 
 Version 0.0.6 :small:`May 25, 2021`
--------------------------------------
+-----------------------------------
 
 This version includes:
 
@@ -168,7 +177,7 @@ This version includes:
 
 
 Version 0.0.5 :small:`May 4, 2021`
--------------------------------------
+----------------------------------
 
 This version includes:
 
@@ -186,7 +195,7 @@ This version includes:
 
 
 Version 0.0.3 :small:`April 8, 2021`
--------------------------------------
+------------------------------------
 
 This version includes:
 

requirements.txt

@@ -8,8 +8,9 @@ ete3
 ipython
 joblib
 matplotlib
+mudata
 natsort
-networkx
+networkx<=2.8.3
 numba
 numpy
 pandas

setup.py

@@ -12,7 +12,7 @@
     __author__ = ", ".join(["Farid Rashidi"])
     __maintainer__ = ", ".join(["Farid Rashidi"])
     __email__ = ", ".join(["[email protected]"])
-    __version__ = "0.0.21"
+    __version__ = "0.1.0"
 
 if platform == "linux" or platform == "linux2":
     os.environ["CC"] = "g++"

trisicell/__init__.py

@@ -7,5 +7,5 @@
 __author__ = ", ".join(["Farid Rashidi"])
 __maintainer__ = ", ".join(["Farid Rashidi"])
 __email__ = ", ".join(["[email protected]"])
-__version__ = "0.0.21"
+__version__ = "0.1.0"
 __all__ = (datasets, io, logg, pl, pp, settings, tl, ul)

trisicell/datasets/__init__.py

@@ -23,6 +23,8 @@
     myeloproliferative_neoplasms712,
     oligodendroglioma_idh_mutated_tumor,
     renal_cell_carcinoma,
+    sublines_bwes,
+    sublines_scrnaseq,
     test,
     tnbc,
 )
@@ -56,4 +58,6 @@
     simulate,
     add_noise,
     add_doublets,
+    sublines_bwes,
+    sublines_scrnaseq,
 )

trisicell/datasets/_datasets.py

@@ -1,6 +1,81 @@
+import mudata as md
+
 import trisicell as tsc
 
 
+def sublines_scrnaseq():
+    """Trisicell sublines scRNAseq data.
+
+    The size is n_cells × n_muts = 175 × 450
+
+    Returns
+    -------
+    :class:`mudata.MuData`
+
+        A mudata with two modalities (`.mod`)
+
+    Examples
+    --------
+    >>> mdata = tsc.datasets.sublines_scrnaseq()
+    >>> mdata
+    MuData object with n_obs × n_vars = 175 × 55851
+    2 modalities
+      expression: 175 x 55401
+        obs:	'cells', 'uniquely_mapped_percent', 'num_splices', ...
+        layers:	'fpkm', 'tpm'
+      mutation: 175 x 450
+        obs:	'cells', 'clone', 'group', 'group_color', 'is_red', 'is_sub', ...
+        var:	'kind', 'amino_acid_change', 'ensemble', 'gene', 'chrom', ...
+        layers:	'genotype', 'mutant', 'total', 'trisicell_input', 'trisicell_output'
+
+    See Also
+    --------
+    :func:`trisicell.datasets.sublines_bwes`.
+    """
+
+    mdata = md.read_h5mu(
+        tsc.ul.get_file("trisicell.datasets/data/sublines_scrnaseq.h5md.gz")
+    )
+    return mdata
+
+
+def sublines_bwes():
+    """Trisicell sublines bWES data.
+
+    The size is n_sublines × n_muts = 24 × 6653
+
+    Returns
+    -------
+    :class:`anndata.AnnData`
+        An anndata in which `.var` contains information about the mutations.
+
+            - `.layers['trisicell_input']` the binary input genotype matrix used as
+                input to the Trisicell.
+            - `.layers['trisicell_output']` the binary input genotype matrix inferred by
+                Trisicell-boost(SCITE).
+            - `.layers['genotype']` noisy genotype matrix, 0: reference, 1: heterozygous
+                2: unknown and 3: homozygous_alt.
+            - `.layers['mutant']` number of mutant reads.
+            - `.layers['total']` number of total reads.
+
+    Examples
+    --------
+    >>> adata = tsc.datasets.sublines_bwes()
+    >>> adata
+    AnnData object with n_obs × n_vars = 24 × 6653
+        var: 'kind', 'amino_acid_change', 'ensemble', 'gene', 'chrom', 'position', ...
+        layers: 'genotype', 'mutant', 'total', 'trisicell_input', 'trisicell_output'
+
+    See Also
+    --------
+    :func:`trisicell.datasets.sublines_scrnaseq`.
+    """
+    adata = tsc.io.read(
+        tsc.ul.get_file("trisicell.datasets/data/sublines_bwes.h5ad.gz")
+    )
+    return adata
+
+
 def example(is_expression=False):
     """Return an example for sanity checking and playing with Trisicell.