New features

.gitignore

@@ -189,3 +189,7 @@ examples/new_test_examples/*
 
 # Ignore new tools examples
 examples/new_tools/
+
+#apple system files
+.DS_Store
+

ProtPeptigram/DataProcessor.py

@@ -176,7 +176,7 @@ def remove_ptm(self, peptide: str) -> str:
 
         return clean_peptide
 
-    def extract_protein_ids(self, accession_value: str) -> List[str]:
+    def extract_protein_ids(self, accession_value: str, protein_pattern=None ) -> List[str]:
         """
         Extract protein IDs from an accession value, which may contain multiple IDs.
 
@@ -191,15 +191,49 @@ def extract_protein_ids(self, accession_value: str) -> List[str]:
         """
         if pd.isna(accession_value) or accession_value == "":
             return []
-
+        if protein_pattern is None:
+            # Default pattern to split by common delimiters
+            protein_pattern = r'[,:;|/\s]+'
+        else:
+            # Use the provided regex pattern if specified
+            protein_pattern = re.compile(protein_pattern)
         # Split by common delimiters
-        protein_ids = re.split(r'[,:;|/\s]+', accession_value)
+        protein_ids = re.split(protein_pattern, accession_value)
 
         # Remove empty entries and trim whitespace
         protein_ids = [pid.strip() for pid in protein_ids if pid.strip()]
-
         return protein_ids
 
+    def extract_protein_isoforms(self, accession_value: str, protein_pattern: str = r'[,:;|/\\s]+') -> List[str]:
+        """
+        Extract protein isoforms from an accession value, splitting by delimiters and extracting isoform info.
+
+        Parameters:
+        -----------
+        accession_value : str
+            Accession value from the PEAKS output
+        protein_pattern : str, optional
+            Regex pattern to split multiple protein IDs (default: r'[,:;|/\s]+')
+
+        Returns:
+        --------
+        List[str]: List of protein isoforms (e.g., 'P12345-2' or 'P12345.2' if present, else just 'P12345')
+        """
+        if pd.isna(accession_value) or accession_value == "":
+            return []
+        # Split by common delimiters
+        protein_ids = re.split(protein_pattern, accession_value)
+        isoforms = []
+        for pid in protein_ids:
+            pid = pid.strip()
+            if not pid:
+                continue
+            # Match patterns like "P12345-1" or "P12345.1"
+            isoform_match = re.match(r'^([A-Z0-9]+(?:[-\.]\d+)?)', pid)
+            if isoform_match:
+                isoforms.append(isoform_match.group(1))
+        return isoforms
+
     def find_peptide_position(self, peptide: str, protein_sequence: str) -> Tuple[int, int]:
         """
         Find the start and end positions of a peptide in a protein sequence.

ProtPeptigram/__init__.py

@@ -23,6 +23,6 @@
 #controll for __all__ to limit what is imported when using 'from module import *'
 # __all__ = ['PeptideDataProcessor', 'ImmunoViz']
 
-__version__ = "1.1.0-dev"
+__version__ = "1.1.1-dev"
 __author__ = "Sanjay Krishna,Prithvi Munday,Chen Li"
 __email__ = "sanjay.sondekoppagopalakrishna@monash.edu"

ProtPeptigram/runner.py

@@ -131,9 +131,26 @@ def run_pipeline(
 
     # Read specific protein list if provided
     specific_proteins = None
-    if protein_list and os.path.exists(protein_list):
-        specific_proteins = read_protein_list(protein_list)
-        console.log(f"Using {len(specific_proteins)} proteins from provided list.", style="bold")
+    # console.log(f"Checking for specific protein list...{protein_list}", style="bold")
+    if protein_list:
+        console.log(f"Protein list provided: {protein_list}", style="bold yellow")
+        try:
+            if isinstance(protein_list, str):
+                console.log(f"Checking if protein_list is a file or string: {protein_list}", style="bold yellow")
+                specific_proteins = [protein_list]  # If it's a single string, treat it as a list with one protein
+            # If protein_list is a string, assume it's a comma-separated list
+            elif isinstance(protein_list, str) and ',' in protein_list:
+                console.log("Parsing comma-separated protein list...", style="bold green")
+                specific_proteins = str(protein_list).split(",")
+
+            elif protein_list and os.path.exists(protein_list):
+                console.log(f"Reading specific protein list from {protein_list}", style="bold green")
+                specific_proteins = read_protein_list(protein_list)
+            else:
+                specific_proteins = read_protein_list(protein_list)
+        except FileNotFoundError:
+            console.log(f"Error reading protein list file: {protein_list}", style="bold red")
+            # raise
 
     # 1. Initialize the data processor
     processor = PeptideDataProcessor()
@@ -184,7 +201,7 @@ def run_pipeline(
                 group_by='Sample',
                 color_by='protein',
                 figsize=(14, 12),
-                title=f"Peptide-Protein alignment visualisation - {prot}",
+                title=f"Prot-Petigram :Peptide-Protein alignment visualisation for {prot}",
                 color_by_protein_and_intensity=False,
                 intensity_cmaps=["Blues", "Reds", "Greens", "Purples"],
                 protein_cmap="Set1",