Merge pull request #126 from jhiemstrawisc/make-installable

Make SPRAS installable
Reed-CompBio · Oct 13, 2023 · 1cc6acb · 1cc6acb
2 parents e67167f + 44ae505
commit 1cc6acb
Show file tree

Hide file tree

Showing 35 changed files with 118 additions and 48 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -169,7 +169,7 @@ After completing this step, try running the Local Neighborhood algorithm through
 ```bash
 snakemake --cores 1 --configfile config/config.yaml
 ```
-Make sure to run the command inside the `spras` conda environment.
+Make sure to run the command inside the `spras` conda environment. If installing via `pip` instead of using conda, install with the `-e .[dev]` options (the full command to run from the repo root is `python -m pip install -e .[dev]`) so that Python picks up any changes you make and installs all optional development packages. Omitting the `-e` flag will prevent your changes from being reflected unless you force re-install, and omitting `.[dev]` will prevent pip from installing `pre-commit` and `pytest`.
 
 As a workflow manager, Snakemake will consider the work described in the configuration file to be completed once the necessary output files have been written to the relevant output directory (`output` in the `config/config.yaml` configuration).
 That means that if you change your code and rerun the Snakemake command above, nothing may happen if the output files already exist.
@@ -223,7 +223,7 @@ Example errors include a yaml file that cannot be parsed or a local variable tha
 These tests are run automatically on every commit through the GitHub Actions.
 However, developers will benefit from setting up their environment to run the same tests locally while they modify the SPRAS source.
 
-The `pre-commit` package is installed as part of the conda environment in `environment.yml`.
+The `pre-commit` package is installed as part of the conda environment in `environment.yml`, or when installing SPRAS with `python -m pip install -e .[dev]`.
 From there, the pre-commit [quick start](https://pre-commit.com/#quick-start) guide explains two primary ways to use it locally:
 - run against all source files with `pre-commit run --all-files` to identify errors and automatically fix them when possible
 - configure `git` to run the hooks before every `git commit` so that a commit will only succeed if the tests pass, ensuring new errors are not introduced

diff --git a/README.md b/README.md
@@ -35,6 +35,13 @@ conda activate spras
 to create a conda environment with the required packages and activate that environment.
 If you have a different version of Python already, you can install the specified versions of the required packages in your preferred manner instead of using Anaconda.
 
+SPRAS can also be installed with Python's package manager `pip` by running `python -m pip install .` from the repo's root directory. This makes SPRAS more portable by allowing you to run
+snakemake anywhere the Snakefile, data, and configuration file can be accessed. However, use caution when pip installing directly to your computer without using some form of virtual
+environment as this can alter your system's underlying python modules, which could lead to unexpected behavior.
+
+For developers, SPRAS can be installed via `pip` with the `-e` flag, as in `python -m pip install -e .`. This points Python back to the SPRAS repo so that any changes made to the source
+code are reflected in the installed module.
+
 You also need to install [Docker](https://docs.docker.com/get-docker/).
 After installing Docker, start Docker before running SPRAS.
 
@@ -60,7 +67,7 @@ The files to create these Docker images are in the `docker-wrappers` subdirector
 The Docker images are available on [DockerHub](https://hub.docker.com/orgs/reedcompbio).
 
 **Python wrapper for calling algorithms**: Wrapper functions provide an interface between the common file formats for input and output data and the algorithm-specific file formats and reconstruction commands.
-These wrappers are in the `src/` subdirectory.
+These wrappers are in the `spras/` subdirectory.
 
 **Test code**: Tests for the Docker wrappers and SPRAS code.
 The tests require the conda environment in `environment.yml` and Docker.

diff --git a/Snakefile b/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, cytoscape
+from spras.dataset import Dataset
+from spras.util import process_config
+from spras.analysis import ml, summary, graphspace, cytoscape
 
 # 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

diff --git a/environment.yml b/environment.yml
@@ -13,7 +13,7 @@ dependencies:
   - python=3.8
   - pip=22.1
   - requests=2.28
-  - scikit-learn=1.1
+  - scikit-learn=1.2
   - seaborn=0.12
   - spython=0.2
   # Only required for GraphSpace
@@ -25,4 +25,4 @@ dependencies:
   - sphinx=5.0
   - pip:
      - graphspace_python==1.3.1
-     - sphinx-rtd-theme==1.0.0
+     - sphinx-rtd-theme==1.2.0
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,3 +1,60 @@
+[project]
+name = "spras"
+version = "0.0.1"
+description = "Signaling Pathway Reconstruction Analysis Streamliner"
+authors = [
+  { name = "Anthony Gitter", email = "[email protected]" },
+  { name = "Anna Ritz", email = "[email protected]"},
+]
+license = { file = "LICENSE" }
+readme = "README.md"
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+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",
+    "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==1.2.0",
+]
+
+[project.optional-dependencies]
+dev = [
+   # Only required for development
+    "pre-commit==2.20",
+    "pytest==7.1",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/Reed-CompBio/spras"
+"Issues" = "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 +73,9 @@ 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"]
diff --git a/src/__init__.py → spras/__init__.py b/src/__init__.py → spras/__init__.py
diff --git a/src/allpairs.py → spras/allpairs.py b/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']
 

diff --git a/src/analysis/__init__.py → spras/analysis/__init__.py b/src/analysis/__init__.py → spras/analysis/__init__.py
diff --git a/src/analysis/cytoscape.py → spras/analysis/cytoscape.py b/src/analysis/cytoscape.py → spras/analysis/cytoscape.py
@@ -2,7 +2,7 @@
 from shutil import rmtree
 from typing import List, Union
 
-from src.util import prepare_volume, run_container
+from spras.util import prepare_volume, run_container
 
 
 def run_cytoscape(pathways: List[Union[str, PurePath]], output_file: str, singularity: bool = False) -> None:

diff --git a/src/analysis/graphspace.py → spras/analysis/graphspace.py b/src/analysis/graphspace.py → spras/analysis/graphspace.py
diff --git a/src/analysis/ml.py → spras/analysis/ml.py b/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')
 

diff --git a/src/analysis/summary.py → spras/analysis/summary.py b/src/analysis/summary.py → spras/analysis/summary.py
diff --git a/src/dataset.py → spras/dataset.py b/src/dataset.py → spras/dataset.py
diff --git a/src/domino.py → spras/domino.py b/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']
 

diff --git a/src/meo.py → spras/meo.py b/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']
 

diff --git a/src/mincostflow.py → spras/mincostflow.py b/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']
 

diff --git a/src/omicsintegrator1.py → spras/omicsintegrator1.py b/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']
 

diff --git a/src/omicsintegrator2.py → spras/omicsintegrator2.py b/src/omicsintegrator2.py → spras/omicsintegrator2.py
@@ -2,9 +2,9 @@
 
 import pandas as pd
 
-from src.dataset import Dataset
-from src.prm import PRM
-from src.util import add_rank_column, prepare_volume, run_container
+from spras.dataset import Dataset
+from spras.prm import PRM
+from spras.util import add_rank_column, prepare_volume, run_container
 
 __all__ = ['OmicsIntegrator2']
 

diff --git a/src/pathlinker.py → spras/pathlinker.py b/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']
 

diff --git a/src/prm.py → spras/prm.py b/src/prm.py → spras/prm.py
diff --git a/src/runner.py → spras/runner.py b/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):

diff --git a/src/util.py → spras/util.py b/src/util.py → spras/util.py
diff --git a/test/AllPairs/test_ap.py b/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/'

diff --git a/test/DOMINO/test_domino.py b/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'

diff --git a/test/MEO/test_meo.py b/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'

diff --git a/test/MinCostFlow/test_mcf.py b/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'

diff --git a/test/OmicsIntegrator1/test_oi1.py b/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'

diff --git a/test/OmicsIntegrator2/test_oi2.py b/test/OmicsIntegrator2/test_oi2.py
@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.omicsintegrator2 import OmicsIntegrator2
+from spras.omicsintegrator2 import OmicsIntegrator2
 
 TEST_DIR = 'test/OmicsIntegrator2/'
 EDGE_FILE = TEST_DIR+'input/oi2-edges.txt'

diff --git a/test/PathLinker/test_pathlinker.py b/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'

diff --git a/test/analysis/test_analysis.py b/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/'
 

diff --git a/test/analysis/test_cytoscape.py b/test/analysis/test_cytoscape.py
@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.analysis.cytoscape import run_cytoscape
+from spras.analysis.cytoscape import run_cytoscape
 
 INPUT_DIR = 'test/analysis/input/example/'
 INPUT_PATHWAYS = [INPUT_DIR + 'data0-meo-params-GKEDDFZ_pathway.txt',

diff --git a/test/analysis/test_summary.py b/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

diff --git a/test/ml/test_ml.py b/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/'

diff --git a/test/test_prepare_inputs.py b/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")
 

diff --git a/test/test_util.py b/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,