Release 3.0.0

.gitignore

@@ -48,4 +48,6 @@ target/
 # Other
 *~
 .nfs*
-tests/
+tests/
+# JetBrains IDE settings
+.idea/

CHANGES.txt

@@ -1,5 +1,15 @@
 Changelog
 ---------
+# 3.0.0
+* added new `--regions` flag to enable detection of interactions between protein regions (by @snbolz)
+* reworked XML and TXT report file naming; changes default behavior
+* introduced pyproject.toml to ensure compliance with Python packaging standards
+* updated Dockerfile
+* fixed switched coordinates of halogen bond acceptor and donor atoms
+* fixed handling of PDB input passed as string
+* fixed handling of modified residues in protein and peptide ligands
+* several minor bug fixes
+
 # 2.4.0
 * new "--chains" flag to enable detection of interactions between protein chains by @PhiCMS and @snbolz
 * update setup.py, attempt to fix and install broken python openbabel bindings 3.1.1.1

plip/basic/config.py

@@ -1,7 +1,7 @@
-__version__ = '2.4.0'
+__version__ = '3.0.0'
 __maintainer__ = 'PharmAI GmbH (2020-2021) - www.pharm.ai - hello@pharm.ai'
-__citation_information__ = "Adasme,M. et al. PLIP 2021: expanding the scope of the protein-ligand interaction profiler to DNA and RNA. " \
-                           "Nucl. Acids Res. (05 May 2021), gkab294. doi: 10.1093/nar/gkab294"
+__citation_information__ = "Schake,P. Bolz,SN. et al. PLIP 2025: introducing protein–protein interactions to the protein–ligand interaction profiler. " \
+                           "Nucl. Acids Res. (10 May 2025), gkaf361. doi: 10.1093/nar/gkaf361"
 
 import logging
 
@@ -28,11 +28,13 @@
 RESIDUES = {}
 KEEPMOD = False
 DNARECEPTOR = False
-OUTPUTFILENAME = "report"  # Naming for the TXT and XML report files
+OUTPUTFILENAME = None  # Naming for the TXT and XML report files
 NOPDBCANMAP = False  # Skip calculation of mapping canonical atom order: PDB atom order
 NOHYDRO = False  # Do not add hydrogen bonds (in case already present in the structure)
 MODEL = 1  # The model to be selected for multi-model structures (default = 1).
-CHAINS = None # Define chains for protein-protein interaction detection
+CHAINS = None  # Define chains for protein-protein interaction detection
+REGIONS = None
+COMPRESS = False  # Compress XML and TXT report files
 
 
 # Configuration file for Protein-Ligand Interaction Profiler (PLIP)

plip/basic/remote.py

@@ -21,11 +21,12 @@ def __init__(self, mol, site):
 
         # General Information
         self.lig_members = sorted(pli.ligand.members)
-        self.sourcefile = pcomp.sourcefiles['pdbcomplex']
+        self.source_pdb_file_content = pcomp.sourcefiles['pdbstring'] # store pdb file content as string
         self.corrected_pdb = pcomp.corrected_pdb
         self.pdbid = mol.pymol_name
         self.hetid = ligand.hetid
         self.ligandtype = ligand.type
+        self.regions = ligand.regions
         self.chain = ligand.chain if not ligand.chain == "0" else ""  # #@todo Fix this
         self.position = str(ligand.position)
         self.uid = ":".join([self.hetid, self.chain, self.position])

plip/basic/supplemental.py

@@ -55,15 +55,29 @@ def whichchain(atom):
     return atom.GetResidue().GetChain() if atom.GetResidue() is not None else None
 
 
-def residue_belongs_to_receptor(res, config):
+def residue_belongs_to_receptor(res, regions=None):
     """tests whether the residue is defined as receptor and is not part of a peptide or residue ligand."""
-    if config.CHAINS:
+    if regions:
+        ligand_region, bs_region = regions
+        chain = res.GetChain()
+        num = res.GetNum()
+        if ligand_region and bs_region:  # both ligand and receptor region were defined
+            if num in ligand_region.get(chain, []):
+                return False  # residue belongs to ligand
+            if num in bs_region.get(chain, []):
+                return True  # residue belongs to receptor and not to ligand
+            return False
+        else:
+            return num not in ligand_region.get(chain, [])
+
+    elif config.CHAINS:
         if config.CHAINS[0] and config.CHAINS[1]:  # if receptor and ligand chains were given
             return res.GetChain() in config.CHAINS[0] and res.GetChain() not in config.CHAINS[1]
             # True if residue is part of receptor chains and not of ligand chains
         if config.CHAINS[1]:  # if only ligand chains were given
             return res.GetChain() not in config.CHAINS[1]  # True if residue is not part of ligand chains
         return False  # if only receptor chains were given or both is empty
+
     return res.GetChain() not in config.PEPTIDES  # True if residue is not part of peptide ligand.
 
 
@@ -184,9 +198,17 @@ def cluster_doubles(double_list):
 # File operations
 #################
 
-def tilde_expansion(folder_path):
+def tilde_expansion(folder_paths):
     """Tilde expansion, i.e. converts '~' in paths into <value of $HOME>."""
-    return os.path.expanduser(folder_path) if '~' in folder_path else folder_path
+    if isinstance(folder_paths, list):
+        expanded_paths = []
+        for p in folder_paths:
+            if "~" in p:
+                p = os.path.expanduser(p)
+            expanded_paths.append(p)
+        return expanded_paths
+    else:
+        return os.path.expanduser(folder_paths) if "~" in folder_paths else folder_paths
 
 
 def folder_exists(folder_path):
@@ -231,6 +253,18 @@ def start_pymol(quiet=False, options='-p', run=False):
         pymol.cmd.feedback('disable', 'all', 'everything')
 
 
+def select_region(region):
+    """region is a dictionary with chains as keys and a list of residue numbers as values."""
+    selection = f"(chain "
+    for i, (chain, res_numbers) in enumerate(region.items()):
+        selection += f"{chain} and not resn HOH and resi {'+'.join(map(str, res_numbers))}"
+        if not i == len(region) - 1:
+            selection += ") or (chain "
+        else:
+            selection += ")"
+    return selection
+
+
 def nucleotide_linkage(residues):
     """Support for DNA/RNA ligands by finding missing covalent linkages to stitch DNA/RNA together."""
 

plip/exchange/report.py

@@ -2,6 +2,7 @@
 from operator import itemgetter
 
 import lxml.etree as et
+import gzip
 
 from plip.basic import config
 from plip.basic.config import __version__
@@ -91,20 +92,31 @@ def get_bindingsite_data(self):
             else:
                 self.txtreport.append('No interactions detected.')
 
-    def write_xml(self, as_string=False):
+    def write_xml(self, as_string: bool = False):
         """Write the XML report"""
         if not as_string:
-            et.ElementTree(self.xmlreport).write('{}/{}.xml'.format(self.outpath, self.outputprefix), pretty_print=True,
-                                                 xml_declaration=True)
+            tree = et.ElementTree(self.xmlreport)
+            if config.COMPRESS:
+                with gzip.open(f"{self.outpath}{self.outputprefix}.xml.gz", "wb") as xml_file:
+                    tree.write(xml_file, pretty_print=True, xml_declaration=True, encoding="utf-8")
+            else:
+                tree.write(f"{self.outpath}{self.outputprefix}.xml", pretty_print=True, xml_declaration=True,
+                           encoding="utf-8")
         else:
             output = et.tostring(self.xmlreport, pretty_print=True)
             print(output.decode('utf8'))
 
-    def write_txt(self, as_string=False):
+    def write_txt(self, as_string: bool = False):
         """Write the TXT report"""
         if not as_string:
-            with open('{}/{}.txt'.format(self.outpath, self.outputprefix), 'w') as f:
-                [f.write(textline + '\n') for textline in self.txtreport]
+            if config.COMPRESS:
+                with gzip.open(f"{self.outpath}{self.outputprefix}.txt.gz", "wb") as txt_file:
+                    for textline in self.txtreport:
+                        txt_file.write((textline + '\n').encode('utf-8'))
+            else:
+                with open(f"{self.outpath}{self.outputprefix}.txt", 'w') as txt_file:
+                    for textline in self.txtreport:
+                        txt_file.write(textline + '\n')
         else:
             output = '\n'.join(self.txtreport)
             print(output)
@@ -280,7 +292,7 @@ def __init__(self, plcomplex):
                                       '%.2f' % halogen.distance, '%.2f' % halogen.don_angle, '%.2f' % halogen.acc_angle,
                                       halogen.don_orig_idx, halogen.donortype,
                                       halogen.acc_orig_idx, halogen.acctype,
-                                      halogen.acc.o.coords, halogen.don.x.coords))
+                                      halogen.don.x.coords, halogen.acc.o.coords))
 
         ###################
         # METAL COMPLEXES #