Biological assemblies verified

.github/workflows/python-package.yml

@@ -15,8 +15,8 @@ jobs:
     steps:
     - uses: actions/checkout@v4
     - run: pip install --user ruff
-    - run: ruff --exit-zero --line-length=320 --target-version=py38 --statistics . | sort -k 2
-    - run: ruff --ignore=E402,E501,E701,E722,E741,F401,F403,F841
+    - run: ruff check --exit-zero --line-length=320 --target-version=py38 --statistics . | sort -k 2
+    - run: ruff check --ignore=E402,E501,E701,E722,E741,F401,F403,F841
                 --output-format=github --target-version=py38 .
 
   build:

packman/__init__.py

@@ -13,4 +13,4 @@
 
 
 #VERSION CHANGE HERE CHANGES IT IN docs AND setup.py
-__version__='1.4.12'
+__version__='1.4.13'

packman/apps/dci.py

@@ -42,7 +42,7 @@ class DCI():
 
     def __init__(self, mol, cutoff = 7.0, chain = None, n_com = None):
         self.molObj = mol
-        assert type( self.molObj ) == Protein, "mol should be a packman.molecule.Protein object."
+        assert isinstance(self.molObj, Protein), "mol should be a packman.molecule.Protein object."
 
         if chain:
             self.atoms = [i for i in self.molObj[0][chain].get_calpha()]

packman/molecule/molecule.py

@@ -18,6 +18,7 @@
 
 import numpy
 import logging
+from typing import List
 
 from .protein import Protein
 from .model import Model
@@ -486,7 +487,7 @@ def load_structure(filename: str, ftype: str= 'cif') -> Protein:
 ##################################################################################################
 '''
 
-def download_structure(pdbid: str, save_name: str=None, ftype: str='cif'):
+def download_structure(pdbid: str, save_name: str=None, ftype: str='cif', biological_assembly: bool = False):
     """This function downloads the 3D protein structure.
 
     Example::
@@ -495,16 +496,23 @@ def download_structure(pdbid: str, save_name: str=None, ftype: str='cif'):
         molecule.download_structure('1prw')
 
     Args:
-        pdbid     (str) : A Unique 4 Letter PDB ID (eg.. 1PRW) 
-        save_name (str) : Save name of the downloaded file (extension will be added automatically depending on the ftype argument).
-        ftype     (str) : Format name ('.cif' or '.pdb')
+        pdbid               (str) : A Unique 4 Letter PDB ID (eg.. 1PRW) 
+        save_name           (str) : Save name of the downloaded file (extension will be added automatically depending on the ftype argument).
+        ftype               (str) : Format name ('cif' or 'pdb')
+        biological_assembly (bool) : Download biological assemblies in lieu of PDB entry. (Default: False)
     """
     import urllib.request as ur
 
     if(ftype == 'cif'):
-        response=ur.urlopen('https://files.rcsb.org/view/'+pdbid+'.cif')
+        if(biological_assembly):
+            response=ur.urlopen('https://files.rcsb.org/view/'+pdbid+'-assembly1.cif')
+        else:
+            response=ur.urlopen('https://files.rcsb.org/view/'+pdbid+'.cif')
     elif(ftype == 'pdb'):
-        response=ur.urlopen('https://files.rcsb.org/view/'+pdbid+'.pdb')
+        if(biological_assembly):
+            response=ur.urlopen('https://files.rcsb.org/view/'+pdbid+'.pdb1')
+        else:
+            response=ur.urlopen('https://files.rcsb.org/view/'+pdbid+'.pdb')
     else:
         logging.warning('Please provide appropriate "ftype" argument. (cif/pdb).')
         return
@@ -519,4 +527,44 @@ def download_structure(pdbid: str, save_name: str=None, ftype: str='cif'):
             open(save_name+'.'+ftype,'wb').write( response.read() )
         except(IOError):
             None
-    return True
+    return True
+
+def batch_download(entry_list: List[str], save_location: str = 'structure_files', ftype: str='cif', biological_assembly: bool = False) -> bool:
+    '''This function downloads structures from PDB database parallelly.
+
+    Degree of parallelism depends on your CPU count. Duplicates will be removed automatically.
+
+    Example::
+        from packman import molecule
+        molecule.batch_download(['1prw', '1exr', '4hla'])
+
+    Args:
+        entry_list (List[str]) : List of PDBIDS
+        save_location (str) : Location where the downloaded files will be stored.
+        save_name           (str) : Save name of the downloaded file (extension will be added automatically depending on the ftype argument).
+        ftype               (str) : Format name ('cif' or 'pdb')
+        biological_assembly (bool) : Download biological assemblies in lieu of PDB entry. (Default: False)
+
+    '''
+    import os
+    import multiprocessing
+    from multiprocessing.dummy import Pool
+    from tqdm import tqdm
+
+    def single_download(entry):
+        try:
+            download_structure(entry)
+            return entry, True
+        except:
+            return entry, False
+
+    if not os.path.exists(save_location):
+        os.makedirs(save_location)
+
+    multiprocessing_input = list(set(entry_list))
+
+    # Multiprocessing
+    pool = Pool( multiprocessing.cpu_count() )
+    for result in tqdm(pool.imap_unordered( single_download, multiprocessing_input ), total=len(multiprocessing_input)):
+        if(result[1] is False):
+            print('\n',result[0],' failed to download.')

packman/utilities/utilities.py

@@ -66,7 +66,7 @@ def superimporse(reference: 'Chain', target: 'Chain', use: str='calpha', ids: Li
     Bm = numpy.subtract(atoms2_location, Centroid2)
 
     #Dot is matrix multiplication for array
-    H = numpy.mat(Bm.T) * numpy.mat(Am)
+    H = numpy.asmatrix(Bm.T) * numpy.asmatrix(Am)
 
     #Find Rotation
     U, S, Vt = numpy.linalg.svd(H)

setup.py

@@ -71,5 +71,5 @@ def get_version(rel_path):
       entry_points = {
               'console_scripts': SCRIPTS,
                 },
-    install_requires = ['numpy', 'scipy', 'networkx', 'mlxtend', 'scikit-learn'],
+    install_requires = ['numpy', 'scipy', 'networkx', 'mlxtend', 'scikit-learn', 'tqdm', 'typing_extensions'],
       )