Make SPRAS installable

This commit adds the ability to install spras as a python module using pip,
which is something we'll need for running in remote environments such as on
the OSPool. The installation "instructions" used by pip during building are
laid out in `pyproject.toml`. While I chose to use setup-tools as a builder
backend in this first pass, other builder backends with more robust build
features are available and may eventually be switched to (eg flit, poetry).

Several additional files had to be modified to adhere to python packaging
guidelines, the most notable of which was changing `src` to spras, and referencing
the new spras directory instead of src. Several lines of omicsintegrator2.py were
also modified becasue they were dealing with an absolute path, which made the
workflow un-runnable outside of the repo. I verified that all tests and the entirety of
the snakefile still run both in the conda environment from the repo root (which is
how the tool is currently used) and in a separate directory with spras installed where
the input data, snakefile, and config file have been brought along.

For testing, install spras using `pip install .` in the repo root. If the extra
development packages are needed, spras can be installed with the command
`pip install .[dev]`. Spras can also be installed via `pip install -e .` to
make the installation editable. That is, when installed via this command, you
can continue to edit spras in the repo and have those changes reflected anywhere
you run spras on the machine.

Note that several package versions had to be modified (they're noted in
pyproject.toml) to get past a few versioning issues between conda and pypi. To the
extent of my knowledge and testing, these changes didn't affect the way spras runs.
Famous last words?

Snakefile

@@ -1,10 +1,10 @@
 import os
-from src import runner
+from spras import runner
 import shutil
 import yaml
-from src.dataset import Dataset
-from src.util import process_config
-from src.analysis import ml, summary, graphspace
+from spras.dataset import Dataset
+from spras.util import process_config
+from spras.analysis import ml, summary, graphspace
 
 # Snakemake updated the behavior in the 6.5.0 release https://github.com/snakemake/snakemake/pull/1037
 # and using the wrong separator prevents Snakemake from matching filenames to the rules that can produce them

pyproject.toml

@@ -1,3 +1,56 @@
+[project]
+name = "SPRAS"
+version = "v0.0.1"
+description = "Signaling Pathway Reconstruction Analysis Streamliner (SPRAS)"
+authors = [
+  { name = "Anthony Gitter", email = "[email protected]" },
+]
+license = { file = "LICENSE" }
+readme = "README.md"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+requires-python = ">=3.8"
+dependencies = [
+    "adjusttext==0.7.3",
+    "snakemake==7.19.1",
+    "docker==5.0.3", # Switched from docker-py to docker because docker-py is not maintained in pypi. This appears to have no effect
+    "matplotlib==3.5",
+    "networkx==2.8",
+    "pandas==1.4",
+    "pip==22.1",
+    "requests==2.28",
+    "scikit-learn==1.2", #Version bumped from 1.1-->1.2 to get past compilation errors. No other errors encountered
+    "seaborn==0.12",
+    "spython==0.2",
+    # Only required for GraphSpace
+    "commonmark==0.9",
+    "docutils", #==0.18
+    "jinja2==3.1",
+    "mock==4.0",
+    "recommonmark==0.7",
+    "sphinx==5.0",
+    "graphspace_python==1.3.1",
+    "sphinx-rtd-theme==1.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+   # Only required for development
+    "pre-commit==2.20",
+    "pytest==7.1",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/Reed-CompBio/spras"
+"Bug Tracker" = "https://github.com/Reed-CompBio/spras/issues"
+
+[build-system]
+requires = ["setuptools>=64.0"]
+build-backend = "setuptools.build_meta"
+
 [tool.ruff]
 target-version = "py38"
 # Autofix errors when possible
@@ -16,3 +69,9 @@ select = [
     "I", # isort
     "W292", # missing-newline-at-end-of-file
 ]
+
+[tool.setuptools]
+# py-modules tells setuptools which directory is our actual module
+py-modules = ["spras"]
+# packages tells setuptools what the exported package is called (ie allows import spras)
+packages = ["spras", "spras.analysis"]

src/allpairs.py → spras/allpairs.py

@@ -3,8 +3,8 @@
 
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_volume, run_container
+from spras.prm import PRM
+from spras.util import prepare_volume, run_container
 
 __all__ = ['AllPairs']
 

src/analysis/ml.py → spras/analysis/ml.py

@@ -12,7 +12,7 @@
 from sklearn.decomposition import PCA
 from sklearn.preprocessing import StandardScaler
 
-from src.util import make_required_dirs
+from spras.util import make_required_dirs
 
 plt.switch_backend('Agg')
 

src/domino.py → spras/domino.py

@@ -3,8 +3,8 @@
 
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_volume, run_container
+from spras.prm import PRM
+from spras.util import prepare_volume, run_container
 
 __all__ = ['DOMINO', 'pre_domino_id_transform', 'post_domino_id_transform']
 

src/meo.py → spras/meo.py

@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_volume, run_container
+from spras.prm import PRM
+from spras.util import prepare_volume, run_container
 
 __all__ = ['MEO', 'write_properties']
 

src/mincostflow.py → spras/mincostflow.py

@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_volume, run_container
+from spras.prm import PRM
+from spras.util import prepare_volume, run_container
 
 __all__ = ['MinCostFlow']
 

src/omicsintegrator1.py → spras/omicsintegrator1.py

@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_volume, run_container
+from spras.prm import PRM
+from spras.util import prepare_volume, run_container
 
 __all__ = ['OmicsIntegrator1', 'write_conf']
 

src/omicsintegrator2.py → spras/omicsintegrator2.py

@@ -4,8 +4,8 @@
 import docker
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_path_docker
+from spras.prm import PRM
+from spras.util import prepare_path_docker
 
 __all__ = ['OmicsIntegrator2']
 
@@ -68,7 +68,10 @@ def run(edges=None, prizes=None, output_file=None, w=None, b=None, g=None, noise
 
         # Initialize a Docker client using environment variables
         client = docker.from_env()
-        work_dir = Path(__file__).parent.parent.absolute()
+        # work_dir = Path(__file__).parent.parent.absolute()
+        # Instead of getting path from __file__, we need to consider cwd to account for the fact
+        # that we might be running outside of the repo
+        work_dir = Path(os.getcwd()).absolute()
 
         edge_file = Path(edges)
         prize_file = Path(prizes)

src/pathlinker.py → spras/pathlinker.py

@@ -3,8 +3,8 @@
 
 import pandas as pd
 
-from src.prm import PRM
-from src.util import prepare_volume, run_container
+from spras.prm import PRM
+from spras.util import prepare_volume, run_container
 
 __all__ = ['PathLinker']
 

src/runner.py → spras/runner.py

@@ -1,12 +1,12 @@
 # supported algorithm imports
-from src.allpairs import AllPairs as allpairs
-from src.dataset import Dataset
-from src.domino import DOMINO as domino
-from src.meo import MEO as meo
-from src.mincostflow import MinCostFlow as mincostflow
-from src.omicsintegrator1 import OmicsIntegrator1 as omicsintegrator1
-from src.omicsintegrator2 import OmicsIntegrator2 as omicsintegrator2
-from src.pathlinker import PathLinker as pathlinker
+from spras.allpairs import AllPairs as allpairs
+from spras.dataset import Dataset
+from spras.domino import DOMINO as domino
+from spras.meo import MEO as meo
+from spras.mincostflow import MinCostFlow as mincostflow
+from spras.omicsintegrator1 import OmicsIntegrator1 as omicsintegrator1
+from spras.omicsintegrator2 import OmicsIntegrator2 as omicsintegrator2
+from spras.pathlinker import PathLinker as pathlinker
 
 
 def run(algorithm, params):

test/AllPairs/test_ap.py

@@ -4,7 +4,7 @@
 
 import pytest
 
-from src.allpairs import AllPairs
+from spras.allpairs import AllPairs
 
 TEST_DIR = 'test/AllPairs/'
 OUT_DIR = TEST_DIR+'output/'

test/DOMINO/test_domino.py

@@ -4,7 +4,7 @@
 
 import pytest
 
-from src.domino import DOMINO, post_domino_id_transform, pre_domino_id_transform
+from spras.domino import DOMINO, post_domino_id_transform, pre_domino_id_transform
 
 TEST_DIR = 'test/DOMINO/'
 OUT_FILE_DEFAULT = TEST_DIR+'output/domino-output.txt'

test/MEO/test_meo.py

@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.meo import MEO, write_properties
+from spras.meo import MEO, write_properties
 
 TEST_DIR = 'test/MEO/'
 OUT_FILE = TEST_DIR + 'output/edges.txt'

test/MinCostFlow/test_mcf.py

@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.mincostflow import MinCostFlow
+from spras.mincostflow import MinCostFlow
 
 TEST_DIR = 'test/MinCostFlow/'
 OUT_FILE = TEST_DIR + 'output/mincostflow-output.txt'

test/OmicsIntegrator1/test_oi1.py

@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.omicsintegrator1 import OmicsIntegrator1, write_conf
+from spras.omicsintegrator1 import OmicsIntegrator1, write_conf
 
 TEST_DIR = 'test/OmicsIntegrator1/'
 OUT_FILE = TEST_DIR+'output/test_optimalForest.sif'

test/OmicsIntegrator2/test_oi2.py

@@ -1,6 +1,6 @@
 import pytest
 
-from src.omicsintegrator2 import OmicsIntegrator2
+from spras.omicsintegrator2 import OmicsIntegrator2
 
 TEST_DIR = 'test/OmicsIntegrator2/'
 

test/PathLinker/test_pathlinker.py

@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.pathlinker import PathLinker
+from spras.pathlinker import PathLinker
 
 TEST_DIR = 'test/PathLinker/'
 OUT_FILE_DEFAULT = TEST_DIR+'output/pathlinker-ranked-edges.txt'

test/analysis/test_analysis.py

@@ -1,5 +1,5 @@
-import src.analysis.graphspace as graphspace
-import src.analysis.summary as summary
+import spras.analysis.graphspace as graphspace
+import spras.analysis.summary as summary
 
 TEST_DIR = 'test/analysis/'
 

test/analysis/test_summary.py

@@ -2,7 +2,7 @@
 
 import pandas as pd
 
-from src.analysis.summary import summarize_networks
+from spras.analysis.summary import summarize_networks
 
 # Notes:
 # - Column labels are required in the node table

test/ml/test_ml.py

@@ -3,7 +3,7 @@
 
 import pandas as pd
 
-import src.analysis.ml as ml
+import spras.analysis.ml as ml
 
 INPUT_DIR = 'test/ml/input/'
 OUT_DIR = 'test/ml/output/'

test/test_prepare_inputs.py

@@ -3,7 +3,7 @@
 
 import yaml
 
-from src import runner
+from spras import runner
 
 config_loc = os.path.join("config", "config.yaml")
 

test/test_util.py

@@ -2,7 +2,7 @@
 
 import pytest
 
-from src.util import (
+from spras.util import (
     convert_docker_path,
     hash_params_sha1_base32,
     prepare_path_docker,