Package / pyproject.toml

.github/workflows/ci.yml

@@ -15,10 +15,9 @@ jobs:
         with:
             python-version: '3.13'
 
-      - name: Install dependencies
+      - name: Install package
         run: |
-            pip install pandas scipy matplotlib lmfit joblib scikit-learn \
-              imbalanced-learn umap-learn hdbscan seaborn pytest
+            pip install .[test]
 
       - name: Run tests
         run: |

MANIFEST.in

@@ -0,0 +1 @@
+recursive-include src/complexfinder/reference-data *

README.md

@@ -64,41 +64,54 @@ If you analyzed your data using ComplexFinder, we highly recommend to upload the
 
 ## Installation
 
-Download the zip file containing the source code from github.
-Navigate to the folder in terminal/command line tool.
+Navigate to the folder in which you would like create a new virtual Python
+environment via the terminal/command line tool, then:
+
 On Mac / Linux:
 ```
 #create virt env
 python3 -m venv env
 #activate
 source env/bin/activate
-#install packages from req file
-pip install -r requirements.txt
+#install package from GitHub
+pip install git+https://github.com/hnolCol/ComplexFinder.git
 ```
-For windows user:
+For Windows user:
 ```
 #create virt env
 py -m venv env
-#actve
+#activate
 .\env\Scripts\activate
-#install packages from req file
-pip3 install -r requirements.txt
-````
+#install package from GitHub
+pip install git+https://github.com/hnolCol/ComplexFinder.git
+```
+
+Alternatively, you can also clone the repository and install the package
+locally. This will allow you to make changes to the code and test them
+immediately.
+
+```
+git clone https://github.com/hnolCol/ComplexFinder.git
+cd ComplexFinder
+python3 -m venv env
+source env/bin/activate
+pip install -e .
+```
 
 ## Usage Example
 
 Upon downlaod and extraction of the package. You can find example data in the example-data folder.
 To run the anaylsis, you can enter:
 ```python
-from .src.main import ComplexFinder
+from complexfinder import ComplexFinder
 X = pd.read_table("./example-data/SILAC_01.txt", sep = "\t") #loading tab delimited txt file.
 ComplexFinder(analysisName = "ExampleRun_01").run(X)
 ```
 You can also pass a folder path to run. This will yield in the anaylsis of each txt file in the folder.
 
 ```python
 import os
-from .src.main import ComplexFinder
+from complexfinder import ComplexFinder
 folderPath = os.path(".","<my folder>")
 ComplexFinder().run(folderPath)
 ```

pyproject.toml

@@ -0,0 +1,53 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "complexfinder"
+version = "0.4.48"
+description = "ComplexFinder: A software package for the analysis of native protein complex fractionation experiments."
+readme = "README.md"
+requires-python = ">=3.11"
+license = "MIT"
+authors = [
+    { name = "hnolCol" },
+]
+classifiers = [
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering",
+]
+dependencies = [
+    "hdbscan",
+    "imbalanced-learn",
+    "joblib",
+    "lmfit",
+    "matplotlib",
+    "numpy>=2",
+    "pandas>=2",
+    "scikit-learn",
+    "scipy",
+    "seaborn",
+    "umap-learn",
+]
+
+[project.optional-dependencies]
+test = ["pytest>=9"]
+
+[project.urls]
+"Source" = "https://github.com/hnolcol/ComplexFinder"
+
+[tool.pytest]
+minversion = "9.0"
+testpaths = [
+    "tests",
+]
+norecursedirs = [
+    "dist",
+    "build",
+    "complexfinder.egg-info",
+    "results*",
+    "env*",
+    "venv*",
+    "*data*",
+]

src/modules/Database.py → src/complexfinder/Database.py

@@ -10,6 +10,8 @@
 import time
 import pickle
 from collections import OrderedDict
+from pathlib import Path
+
 
 def chunks(l, n):
     """Yield successive n-sized chunks from l."""
@@ -49,7 +51,7 @@ def createSingleChunk(self,idx, entriesInChunks,pathToTmp,metricColumns,df):
 class Database(object):
 
 
-    def __init__(self, nJobs = 4, splitString = ";"):
+    def __init__(self, nJobs = 4, splitString = ";", databaseDir=None):
         """Database Module.
 
         The pipeline requires a database containing positve feature interactions.
@@ -62,19 +64,26 @@ def __init__(self, nJobs = 4, splitString = ";"):
 
         Parameters
         ----------
-
-
+        databaseDir:
+            Directory to use for looking up reference files.
+            If `None`, the `reference-data` directory inside the
+            package root will be used. This is assumed to be writable.
         """
         self.dbs = dict()
         self.nJobs = nJobs
         self.splitString = splitString
         self.params = {"n_jobs":nJobs}
+
+        if databaseDir is None:
+           self.databaseDir = str(Path(__file__).parent / 'reference-data')
+        else:
+           self.databaseDir = databaseDir
+
         self._load()
 
     def _load(self):
         ""
-        folderPath = self._getPathToReferenceFiles()
-        self._loadFiles(folderPath)
+        self._loadFiles(self.databaseDir)
 
     def _loadFiles(self, folderPath):
         """
@@ -323,8 +332,7 @@ def _loadFile(self, *args, **kwargs):
     def _checkIfFilteredFileExists(self,dbID,filterDb):
         ""
         fileName = self._generateFileName(dbID,filterDb)
-        sourcePath = self._getPathToReferenceFiles()
-        self.pathToFile = os.path.join(sourcePath,fileName)
+        self.pathToFile = os.path.join(self.databaseDir, fileName)
         return os.path.exists(self.pathToFile)
 
     def _generateFileName(self,dbName,filterDb):
@@ -389,9 +397,8 @@ def _getFiles(self, folderPath, extn = 'txt'):
     def _getPathToReferenceFiles(self):
         ""
         filePath = os.path.dirname(os.path.realpath(__file__))
-        mainPath = os.path.abspath(os.path.join(filePath ,"../.."))
         pathToReferenceFolder = os.path.join(
-                mainPath,
+                filePath,
                 'reference-data'
             )
         return pathToReferenceFolder

src/complexfinder/__init__.py

@@ -0,0 +1 @@
+from complexfinder.main import ComplexFinder

src/main.py → src/complexfinder/main.py

@@ -8,12 +8,13 @@
 import pickle
 import shutil
 from datetime import datetime
+from pathlib import Path
 
 #internal imports
-from modules.Signal import Signal
-from modules.Database import Database
-from modules.Predictor import Classifier, ComplexBuilder
-from modules.utils import calculateDistanceP, chunks, cleanPath, minMaxNorm, extractMeanByBounds, extractMetricByShiftBounds
+from complexfinder.Signal import Signal
+from complexfinder.Database import Database
+from complexfinder.Predictor import Classifier, ComplexBuilder
+from complexfinder.utils import calculateDistanceP, chunks, cleanPath, minMaxNorm, extractMeanByBounds, extractMetricByShiftBounds
 
 import joblib
 from joblib import Parallel, delayed, dump, load
@@ -131,6 +132,7 @@ def __init__(self,
                 compTabFormat = False,
                 considerOnlyInteractionsPresentInAllRuns = 2,
                 correlationWindowSize = 5,
+                databaseDir = None,
                 databaseFilter = {'Organism': ["Human"]},#{'Organism': ["Human"]},#{"Confidence" : [1,2,3,4]} - for hu.map2.0,# {} for HUMAN_COMPLEX_PORTAL
                 databaseIDColumn = "subunits(UniProt IDs)",
                 databaseFileName = "20190823_CORUM.txt",#"humap2.txt
@@ -235,6 +237,13 @@ def __init__(self,
         * correlationWindowSize = 5,
                     Number of fractions used for rolling pearson correlation
 
+        * databaseDir
+                    Directory to use for looking up reference files and caching
+                    any filtered reference files.
+                    If `None`, the `reference-data` directory inside the
+                    package root will be used. This is assumed to be writable.
+                    If the installation location is not writable, pass a
+                    different path.
         * databaseFilter = {'Organism': ["Human"]},
                     Filter dict used to find relevant complexes from database. By default,
                     the corum database is filtered based on the column 'Organism' using 'Mouse' as a search string.
@@ -412,6 +421,7 @@ def __init__(self,
             "grouping" : grouping,
             "analysisMode" : analysisMode,
             "normValueDict" : normValueDict,
+            "databaseDir" : databaseDir,
             "databaseFilter" : databaseFilter,
             "databaseIDColumn" : databaseIDColumn,
             "databaseFileName" : databaseFileName,
@@ -872,7 +882,7 @@ def _loadReferenceDB(self):
 
         print("Info :: Load positive set from data base")
         if not hasattr(self,"DB"):
-            self.DB = Database(nJobs = self.params["n_jobs"], splitString=self.params["databaseEntrySplitString"])
+            self.DB = Database(nJobs = self.params["n_jobs"], splitString=self.params["databaseEntrySplitString"], databaseDir=self.params["databaseDir"])
 
         pathToDatabase = os.path.join(self.params["pathToComb"], "InteractionDatabase.txt")
         if os.path.exists(pathToDatabase):
@@ -2634,4 +2644,6 @@ def _combinePeakResults(self):
         removeSingleDataPointPeaks=True,
         keepOnlySignalsValidInAllConditions = False,
         quantFiles = {},
-        useRawDataForDimensionalReduction = False).run("../example-data/D1") #adjust the folder where the files are sstored
+        useRawDataForDimensionalReduction = False).run(
+        str(Path(__file__).parents[2] / "example-data" / "D1")
+    ) # adjust the folder where the files are sstored

tests/test_misc.py

@@ -1,16 +1,15 @@
 import os
-import sys
+import shutil
 from pathlib import Path
-from tempfile import TemporaryDirectory
+from tempfile import TemporaryDirectory, tempdir
 
 import pandas as pd
 
-# update sys.path until there is a proper package installation
-sys.path.append(str(Path(__file__).parent.parent / "src"))
+from complexfinder import ComplexFinder
+from complexfinder.Database import Database
 
-from main import ComplexFinder
-
-SAMPLE_DATA_DIR = Path(__file__).parents[1] / "example-data"
+REPO_ROOT = Path(__file__).parents[1]
+SAMPLE_DATA_DIR = REPO_ROOT / "example-data"
 
 
 def test_workflow_completes():
@@ -71,3 +70,16 @@ def test_workflow_completes():
             useRawDataForDimensionalReduction=False).run(
             tmpdir
         )
+
+
+def test_custom_database_dir():
+    """Test that a custom database directory can be used."""
+    db_file = REPO_ROOT / "src" / "complexfinder" / "reference-data" / "CORUM.txt"
+    with TemporaryDirectory() as tmpdir:
+        shutil.copyfile(db_file, Path(tmpdir) / db_file.name)
+        Database(databaseDir=tmpdir).pariwiseProteinInteractions(
+            dbID=db_file.name,
+            complexIDsColumn="subunits(UniProt IDs)",
+            filterDb={'Organism': ["Human"]}
+        )
+        assert Path(tmpdir, f"{db_file.stem}_Organism__Human.txt").is_file()