add function to read and format diann pg files

.github/workflows/black.yml

@@ -6,11 +6,16 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - name: Setup Python 3.8
-        uses: actions/setup-python@v2
+      - uses: actions/checkout@v3
+      - name: Setup Python 3.9
+        uses: actions/setup-python@v4
         with:
-          python-version: "3.8"
+          python-version: "3.9"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install black[colorama]==24.10.0
 
       - name: Run black
         uses: psf/black@stable

gopher/__init__.py

@@ -1,4 +1,5 @@
 """See the README for detailed documentation and examples."""
+
 try:
     from importlib.metadata import PackageNotFoundError, version
 

gopher/annotations.py

@@ -1,4 +1,5 @@
 """Get GO annotations."""
+
 import uuid
 from pathlib import Path
 

gopher/config.py

@@ -1,4 +1,5 @@
 """This module contains the configuration details for ppx"""
+
 import logging
 import os
 from pathlib import Path

gopher/enrichment.py

@@ -1,4 +1,5 @@
 """Calculate the enrichments for a collection of experiments."""
+
 import logging
 
 import numpy as np

gopher/gopher.py

@@ -1,4 +1,5 @@
 """The command line entry point for gopher-enrich"""
+
 import logging
 from argparse import ArgumentParser
 

gopher/ontologies.py

@@ -1,4 +1,5 @@
 """Download the GO ontologies"""
+
 from collections import defaultdict
 
 from . import config, utils

gopher/parsers/__init__.py

@@ -1,2 +1,3 @@
 """The parsers"""
+
 from .tabular import read_encyclopedia, read_metamorpheus

gopher/parsers/tabular.py

@@ -1,4 +1,5 @@
 """Parse tabular result files from common tools"""
+
 import pandas as pd
 
 
@@ -52,3 +53,37 @@ def read_metamorpheus(proteins_txt: str) -> pd.DataFrame:
         .fillna(0)
     )
     return proteins
+
+
+def read_diann(proteins_tsv: str) -> pd.DataFrame:
+    """
+    Reads a DIANN-generated TSV file containing protein information, processes it,
+    and returns a cleaned Pandas DataFrame with relevant data.
+
+    The function:
+    - Extracts the first protein accession from the "Protein.Ids" column to use as the DataFrame index.
+    - Renames the index axis to "Protein".
+    - Drops unnecessary metadata columns.
+
+    Args:
+        proteins_tsv (str): Path to the DIANN-generated TSV file.
+
+    Returns:
+        pd.DataFrame: A DataFrame with the processed protein data, indexed by the first protein accession.
+                      The returned DataFrame excludes the following columns:
+                      ["Protein.Group", "Protein.Ids", "Protein.Names", "Genes", "First.Protein.Description"].
+    """
+    proteins = pd.read_table(proteins_tsv)
+    accessions = proteins["Protein.Ids"].str.split(";").str[0]
+
+    proteins = proteins.set_index(accessions)
+    proteins = proteins.rename_axis("Protein", axis="index")
+    return proteins.drop(
+        columns=[
+            "Protein.Group",
+            "Protein.Ids",
+            "Protein.Names",
+            "Genes",
+            "First.Protein.Description",
+        ]
+    )

gopher/stats.py

@@ -1,4 +1,5 @@
 """Numba Mann-Whitney U test"""
+
 import numba as nb
 import numpy as np
 from scipy import stats

gopher/utils.py

@@ -1,4 +1,5 @@
 """Utility functions"""
+
 import socket
 from pathlib import Path
 

setup.py

@@ -1,4 +1,5 @@
 """Setup ppx"""
+
 import setuptools
 
 setuptools.setup()

tests/unit_tests/annotations_test.py

@@ -1,4 +1,5 @@
 """Test that the annotations functions are working correctly"""
+
 import re
 
 import pandas as pd

tests/unit_tests/enrichment_test.py

@@ -1,4 +1,5 @@
 """Test that the enrichment functions are working correctly"""
+
 import random
 
 import numpy as np

tests/unit_tests/test_version.py

@@ -1,4 +1,5 @@
 """Test that setuptools-scm is working correctly"""
+
 import gopher