Merge branch 'crichgriffin-pip-_install' into main

.gitignore

@@ -1,2 +1,5 @@
+dist/panpipes-0.2.0-py3-none-any.whl
+dist/panpipes-0.2.0.tar.gz
+panpipes.egg-info/PKG-INFO
+panpipes.egg-info/requires.txt
 panpipes/__pycache__
-panpipes.egg-info

panpipes/entry.py

@@ -18,83 +18,32 @@
 import os
 import sys
 import re
-import glob
 import imp
 import panpipes
 
 
-def printListInColumns(l, ncolumns):
-    '''output list *l* in *ncolumns*.'''
-    ll = len(l)
-
-    if ll == 0:
-        return
-
-    max_width = max([len(x) for x in l]) + 3
-    n = ll // ncolumns
-    if ll % ncolumns != 0:
-        n += 1
-
-    # build columns
-    columns = [l[x * n:x * n + n] for x in range(ncolumns)]
-
-    # add empty fields for missing columns in last row
-    for x in range(ncolumns - (len(l) % ncolumns)):
-        columns[-(x + 1)].append('')
-
-    # convert to rows
-    rows = list(zip(*columns))
-
-    # build pattern for a row
-    p = '%-' + str(max_width) + 's'
-    pattern = ' '.join([p for x in range(ncolumns)])
-
-    # put it all together
-    return '\n'.join([pattern % row for row in rows])
-
-# l = ['a', 'b', 'c', 'd']
-# ncolumns = 2
-# printListInColumns(l, ncolumns)
-
 def main(argv=None):
-
     argv = sys.argv
-
     # paths to look for pipelines:
-    #print(pipelines.__file__)
-    path = os.path.abspath(os.path.dirname(panpipes.__file__))
-    relpath = os.path.abspath("../")
-
+    path = os.path.abspath(os.path.join(os.path.dirname(panpipes.__file__), "panpipes"))
+    relpath = os.path.abspath("./")
     paths = [path, relpath]
-
     if len(argv) == 1 or argv[1] == "--help" or argv[1] == "-h":
-        pipelines = []
-        for path in paths:
-            pipelines.extend(glob.glob(os.path.join(path, "pipeline_*.py")))
-        print((globals()["__doc__"]))
         print("The list of available workflows are:\n")
-        # pipelines_list = sorted([os.path.basename(x)[len("pipeline_"):-len(".py")] for x in pipelines])
         pipelines_list = ['1. "qc_mm" : for the ingestion of data and computation of QC metrics' , 
                           '2. "preprocess" : for filtering and normalising of each modality',
                           '3. "integration" : integrate and batch correction using  single and multimodal methods', 
                           '4. "clustering" : cell clustering on single modalities', 
                           '5. "refmap" : transfer scvi-tools models from published data to your data', 
                           '6. "vis" : visualise metrics from other pipelines in context of experiment metadata']
-        print("{}\n".format(
-            printListInColumns(pipelines_list,1)))
+        print(*pipelines_list, sep="\n")
         return
-
     command = argv[1]
     command = re.sub("-", "_", command)
     pipeline = "pipeline_{}".format(command)
-
-    # remove 'cellhub' from sys.argv
     del sys.argv[0]
-
     (file, pathname, description) = imp.find_module(pipeline, paths)
-
     module = imp.load_module(pipeline, file, pathname, description)
-
     module.main(sys.argv)
 
 

panpipes/pipeline_clustering.py → panpipes/panpipes/pipeline_clustering.py

@@ -25,9 +25,10 @@
      "../pipeline.yml",
      "pipeline.yml"])
 
-PARAMS['py_path'] =  os.path.join(os.path.dirname(os.path.dirname(__file__)), 'python')
-PARAMS['r_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'R')
+PARAMS['py_path'] =  os.path.join(os.path.dirname(__file__), 'python_scripts')
+PARAMS['r_path'] = os.path.join(os.path.dirname(__file__), 'R_scripts')
 PARAMS['mudata_with_knn'] = 'mudata_w_neighbors.h5mu'
+
 job_kwargs={}
 if PARAMS['condaenv'] is not None:
     job_kwargs["job_condaenv"] =PARAMS['condaenv']

panpipes/pipeline_integration.py → panpipes/panpipes/pipeline_integration.py

@@ -16,9 +16,9 @@
      "pipeline.yml"])
 
 
-PARAMS['py_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "python")
-PARAMS['R_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "R")
-PARAMS['resources_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "resources")
+PARAMS['py_path'] =  os.path.join(os.path.dirname(__file__), 'python_scripts')
+PARAMS['r_path'] = os.path.join(os.path.dirname(__file__), 'R_scripts')
+PARAMS['resources_path'] = os.path.join(os.path.dirname(__file__), "resources")
 
 sprefix = PARAMS['sample_prefix']
 

panpipes/pipeline_preprocess.py → panpipes/panpipes/pipeline_preprocess.py

@@ -21,9 +21,9 @@
      "pipeline.yml"])
 
 
-PARAMS['py_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "python")
-PARAMS['R_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "R")
-PARAMS['resources_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "resources")
+PARAMS['py_path'] =  os.path.join(os.path.dirname(__file__), 'python_scripts')
+PARAMS['r_path'] = os.path.join(os.path.dirname(__file__), 'R_scripts')
+PARAMS['resources_path'] = os.path.join(os.path.dirname(__file__), "resources")
 
 if  PARAMS['sample_prefix'] is not None:
     PARAMS['filt_file'] = PARAMS['sample_prefix'] + "_filt.h5mu"

panpipes/pipeline_qc_mm.py → panpipes/panpipes/pipeline_qc_mm.py

@@ -17,10 +17,9 @@
      "../pipeline.yml",
      "pipeline.yml"])
 
-PARAMS['py_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "python")
-PARAMS['R_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "R")
-PARAMS['resources_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "resources")
-
+PARAMS['py_path'] =  os.path.join(os.path.dirname(__file__), 'python_scripts')
+PARAMS['r_path'] = os.path.join(os.path.dirname(__file__), 'R_scripts')
+PARAMS['resources_path'] = os.path.join(os.path.dirname(__file__), "resources")
 job_kwargs = {}
 
 if PARAMS['condaenv'] is not None:

panpipes/pipeline_refmap.py → panpipes/panpipes/pipeline_refmap.py

@@ -21,10 +21,9 @@
     job_kwargs["job_condaenv"] =PARAMS['condaenv']
 
 
-
-PARAMS['py_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "python")
-PARAMS['R_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "R")
-PARAMS['resources_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), "resources")
+PARAMS['py_path'] =  os.path.join(os.path.dirname(__file__), 'python_scripts')
+PARAMS['r_path'] = os.path.join(os.path.dirname(__file__), 'R_scripts')
+PARAMS['resources_path'] = os.path.join(os.path.dirname(__file__), "resources")
 
 
 

panpipes/pipeline_vis.py → panpipes/panpipes/pipeline_vis.py

@@ -15,8 +15,8 @@
      "../pipeline.yml",
      "pipeline.yml"])
 
-PARAMS['py_path'] =  os.path.join(os.path.dirname(os.path.dirname(__file__)), 'python')
-PARAMS['r_path'] = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'R')
+PARAMS['py_path'] =  os.path.join(os.path.dirname(__file__), 'python_scripts')
+PARAMS['r_path'] = os.path.join(os.path.dirname(__file__), 'R_scripts')
 
 job_kwargs = {}
 

pyproject.toml

@@ -1,3 +1,90 @@
+
+[project]
+name = "panpipes"
+version = "0.2.0"
+authors = [
+    {name = "Charlotte Rich-Griffin"},
+    {name = "Fabiola Curion"}
+]
+description = "Panpipes - multimodal single cell pipelines"
+readme = "README.md"
+
+classifiers = [
+    # Pick your license as you wish
+    "License :: OSI Approved :: BSD License",
+
+    # Optional
+    # How mature is this project? Common values are
+    #   3 - Alpha
+    #   4 - Beta
+    #   5 - Production/Stable
+    "Development Status :: 3 - Alpha",
+
+    # Indicate who your project is intended for
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: R"
+    ]
+
+requires-python = ">= 3.8"
+
+dependencies = [
+    "anndata>=0.8.0",
+    "apsw", 
+    "bbknn", 
+    "cgatcore", 
+    "drmaa", 
+    "gevent",
+    "harmonypy", 
+    "leidenalg", 
+    "louvain",
+    "matplotlib",
+    "mofapy2",
+    "mudata @ git+https://github.com/scverse/mudata",
+    "muon @ git+https://github.com/scverse/muon",
+    "numpy>=1.22.4", 
+    "packaging", 
+    "pandas>=1.0", 
+    "paramiko", 
+    "pep8",
+    "pysam",
+    "pytest",
+    "pyyaml",
+    "ruffus", 
+    "scanorama", 
+    "scanpy>=1.9.1", 
+    "seaborn",
+    "scikit-misc", 
+    "scirpy @ git+https://github.com/scverse/scirpy",
+    "scrublet", 
+    "scvi-tools>=0.16.3",
+    "sqlalchemy"
+]
+
+[project.optional-dependencies]
+notebook = [
+    "jupyter",
+    "jupyterlab"
+]
+
+# The following would provide a command line executable called `sample`
+# which executes the function `entry` from this package when invoked.
+[project.scripts]  # Optional
+panpipes = "panpipes:entry.main"
+
+# This is configuration specific to the `setuptools` build backend.
+# If you are using a different build backend, you will need to change this.
+[tool.setuptools]
+# If there are data files included in your packages that need to be
+# installed, specify them here.
+package-data = {"panpipes" = ["panpipes/*/*.yml", "R_scripts/*.R"]}
+
+
 [build-system]
-requires = ["setuptools ~= 58.0", "wheel"]
+# These are the assumed default build requirements from pip:
+# https://pip.pypa.io/en/stable/reference/pip/#pep-517-and-518-support
+requires = ["setuptools>=43.0.0", "wheel"]
 build-backend = "setuptools.build_meta"
+
+
+#template for this file from https://github.com/pypa/sampleproject/blob/main/pyproject.toml