EntDetect 1.2.0__py3-none-any.whl

EntDetect/utilities.py

@@ -0,0 +1,201 @@
+import logging
+import pandas as pd
+import numpy as np
+from Bio.PDB import PDBParser, PDBIO
+import pathlib
+import os
+from EntDetect._logging import setup_logger
+
+class PDBcleaner:
+    """
+    Class to clean a PDB before entanglement analysis by: 
+        1. Checking for duplicate residues
+    """
+
+    #############################################################
+    def __init__(self, pdb:str, outdir:str='./', log_level:int=logging.INFO, logdir:str=None) -> None:
+        """
+        Load the PDB file and initate the PDBcleaner class
+        """
+        self.outdir = outdir
+        self.logger = setup_logger('PDBcleaner', outdir=logdir if logdir is not None else outdir, log_level=log_level)
+
+        parser = PDBParser()
+        structure = parser.get_structure('protein', pdb)
+        self.logger.debug(f'structure: {structure}')
+        self.structure = structure
+        self.pdb_filename = pathlib.Path(pdb).stem
+        self.logger.debug(f'pdb_filename: {self.pdb_filename}')
+
+        ## make a tmp directory to populate with cleaned PDBs if it doesnt already exists
+        if not os.path.exists(outdir):
+            os.mkdir(outdir)
+    #############################################################
+
+    #############################################################
+    def remove_duplicates(self, pdb:str='None'):
+        """
+        Remove duplicate residues that are present in the PDB
+        """
+        ## load the PDB file if provided
+        if pdb != 'None':
+            self.logger.debug(f'Reading PDB file: {pdb}')
+            parser = PDBParser()
+            structure = parser.get_structure('protein', pdb)
+            self.logger.debug(f'structure: {structure}')
+            self.structure = structure
+            self.pdb_filename = pathlib.Path(pdb).stem
+            self.logger.debug(f'pdb_filename: {self.pdb_filename}')
+
+        ## define the output pdb and directories
+        clean_outdir = os.path.join(self.outdir, 'cleanPDB_tmp/')
+        if not os.path.exists(clean_outdir):
+            os.mkdir(clean_outdir)
+            self.logger.debug(f'Made directory: {clean_outdir}')
+
+        output_pdb = os.path.join(clean_outdir, f'{self.pdb_filename}_removed_duplicates.pdb')
+
+        # Iterate over residues and identify disulfide bonds
+        for model in self.structure:
+            self.logger.debug(f'Model: {model}')
+
+            for chain in model:
+                self.logger.debug(f'    Chain: {chain}')
+                residues_to_keep = []
+
+                for residue in chain:
+                    resname = residue.get_resname()
+                    self.logger.debug(f'        Residue: {residue} {residue.get_id()} {resname} {residue.__repr__}')
+
+                    ## check if there are any residues with alternate locs
+                    residue_alts = False
+                    for atom in residue:
+                        self.logger.debug(f'            Atom: {atom} {atom.get_altloc()}')
+                        if atom.get_altloc() != ' ':
+                            residue_alts = True
+                    self.logger.debug(f'            residue_alts: {residue_alts}')
+
+                    ## if there are no alternate locs and this residues is not an insertion then keep it
+                    hetflag, resseq, icode = residue.id
+                    if icode == ' ' and residue_alts == False and hetflag == ' ':  # Keep only residues with no insertion code
+                        residues_to_keep.append(residue)
+
+
+                # Remove all residues from the chain, then re-add only the ones without insertion code
+                for residue in list(chain):
+                    chain.detach_child(residue.id)
+                for residue in residues_to_keep:
+                    chain.add(residue)
+
+        # Save filtered structure
+        io = PDBIO()
+        io.set_structure(self.structure)
+        io.save(output_pdb)
+        self.logger.info(f'SAVED: {output_pdb}')
+
+        return output_pdb
+        #############################################################
+
+    #############################################################
+    def remove_incomplete(self, pdb:str='None'):
+        """
+        Remove incomplete residues that are present in the PDB
+        """
+        expected_heavy_atoms = {
+            "ALA": 5,
+            "ARG": 11,
+            "ASN": 8,
+            "ASP": 8,
+            "CYS": 6,
+            "GLU": 9,
+            "GLN": 9,
+            "GLY": 4,
+            "HIS": 10,
+            "ILE": 8,
+            "LEU": 8,
+            "LYS": 9,
+            "MET": 8,
+            "PHE": 11,
+            "PRO": 7,
+            "SER": 6,
+            "THR": 7,
+            "TRP": 14,
+            "TYR": 12,
+            "VAL": 7,
+        }
+
+        ## load the PDB file if provided
+        if pdb != 'None':
+            self.logger.debug(f'Reading PDB file: {pdb}')
+            parser = PDBParser()
+            structure = parser.get_structure('protein', pdb)
+            self.logger.debug(f'structure: {structure}')
+            self.structure = structure
+            self.pdb_filename = pathlib.Path(pdb).stem
+            self.logger.debug(f'pdb_filename: {self.pdb_filename}')
+
+        ## define the output pdb and directories
+        clean_outdir = os.path.join(self.outdir, 'cleanPDB_tmp/')
+        if not os.path.exists(clean_outdir):
+            os.mkdir(clean_outdir)
+            self.logger.debug(f'Made directory: {clean_outdir}')
+
+        output_pdb = os.path.join(clean_outdir, f'{self.pdb_filename}_removed_incomplete.pdb')
+
+        # Iterate over residues and identify disulfide bonds
+        for model in self.structure:
+            self.logger.debug(f'Model: {model}')
+
+            for chain in model:
+                self.logger.debug(f'    Chain: {chain}')
+                residues_to_keep = []
+
+                for residue in chain:
+                    resname = residue.get_resname()
+                    self.logger.debug(f'        Residue: {residue} {residue.get_id()} {resname} {residue.__repr__}')
+
+                    ## check if the residue is complete
+                    residue_complete = False
+                    if resname in expected_heavy_atoms:
+                        num_heavy_atoms = sum(1 for atom in residue if atom.element != 'H')
+                        self.logger.debug(f'            Number of heavy atoms: {num_heavy_atoms}')
+                        if num_heavy_atoms == expected_heavy_atoms[resname]:
+                            residue_complete = True
+                            self.logger.debug(f'            Complete residue: {residue} with {num_heavy_atoms} heavy atoms, expected {expected_heavy_atoms[resname]}')
+                        else:
+                            self.logger.debug(f'            Incomplete residue: {residue} with {num_heavy_atoms} heavy atoms, expected {expected_heavy_atoms[resname]}')
+                    else:
+                        self.logger.debug(f'            Unknown residue type: {resname}, keeping it by default')
+                        residue_complete = False
+
+                    ## check if there are any residues with alternate locs
+                    residue_alts = False
+                    for atom in residue:
+                        self.logger.debug(f'            Atom: {atom} {atom.get_altloc()}')
+                        if atom.get_altloc() != ' ':
+                            residue_alts = True
+                    self.logger.debug(f'            residue_alts: {residue_alts}')
+
+                    ## if there are no alternate locs and this residues is not an insertion then keep it
+                    hetflag, resseq, icode = residue.id
+                    if icode == ' ' and residue_alts == False and hetflag == ' ' and residue_complete:  # Keep only residues with no insertion code
+                        residues_to_keep.append(residue)
+
+
+                # Remove all residues from the chain, then re-add only the ones without insertion code
+                for residue in list(chain):
+                    chain.detach_child(residue.id)
+                for residue in residues_to_keep:
+                    chain.add(residue)
+
+        # Save filtered structure
+        io = PDBIO()
+        io.set_structure(self.structure)
+        io.save(output_pdb)
+        self.logger.info(f'SAVED: {output_pdb}')
+
+        return output_pdb
+        #############################################################
+
+#####################################################################
+#####################################################################

entdetect-1.2.0.dist-info/METADATA

@@ -0,0 +1,26 @@
+Metadata-Version: 2.4
+Name: EntDetect
+Version: 1.2.0
+Summary: Entanglement Detection in Protein Structures
+License-File: LICENSE
+Requires-Dist: biopython
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: pandas
+Requires-Dist: MDAnalysis
+Requires-Dist: mdtraj
+Requires-Dist: parmed
+Requires-Dist: numba
+Requires-Dist: topoly
+Requires-Dist: geom_median
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scikit-learn
+Requires-Dist: networkx
+Requires-Dist: pyyaml
+Requires-Dist: tqdm
+Requires-Dist: requests
+Requires-Dist: statsmodels
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: summary

entdetect-1.2.0.dist-info/RECORD

@@ -0,0 +1,45 @@
+EntDetect/__init__.py,sha256=3SOShWtCJih2HZ0k1U-GRu6LuQAzr_LCSZEiLFnAw0c,307
+EntDetect/_logging.py,sha256=9yn8bpAHO-6gBBQZVjP7fvWxryTVn3iqfwzWPzMymA8,2195
+EntDetect/change_resolution.py,sha256=GTB2WccnlOf1oaIatlnC9usyRbIix-qrDX2hP-V2jfU,117853
+EntDetect/clustering.py,sha256=fBMpiJVMfy_lo23jWjlzQWtFLJWOOUJ7lMwJm_5eXiA,135711
+EntDetect/compare_sim2exp.py,sha256=TjqrELfU_ypY78oCS-r0ttzWhCH5egteguXiZ2B1WFs,99754
+EntDetect/entanglement_features.py,sha256=yjvfiNT7UiptL-ULDByEpHqFQJ9D_8JM7hxiS-oUH34,22493
+EntDetect/gaussian_entanglement.py,sha256=rfYCrY1P99DmpVE0paxdsrdg6qPduCBvcCbXpcngq0k,103081
+EntDetect/order_params.py,sha256=68oq6vE21qCfbezpeF7OHBDoZEAxKmoIU3dm4WxeqR0,51960
+EntDetect/statistics.py,sha256=FQZsVowGuTBJ0WBdS47P0kYE6YOVTn4nu_cHgK9HIjM,65481
+EntDetect/utilities.py,sha256=wF9lH43bJk1E7eY3wZK8UluQxErlWTxOONCKXlCU08k,8535
+EntDetect/Jwalk/GridTools.py,sha256=e0oVNk_q0Oj-gDNickqAN7mRZehR3XeOZkVySn7-MHU,18660
+EntDetect/Jwalk/PDBTools.py,sha256=Oam_vWoQ3q1iH7UR3pU4ccOJViUhv58UEaGnCWMZiC0,16322
+EntDetect/Jwalk/SASDTools.py,sha256=werscmfo6eR-1eKJtJWkPahAQztvB1ueMUP_jNlsdv0,22709
+EntDetect/Jwalk/SurfaceTools.py,sha256=DSgO6NaP6OCH5thxjqICJFkDVVSt_vh4BgPn4eKpyz4,6290
+EntDetect/Jwalk/__init__.py,sha256=jMzpd8yB8quFVqLKt8q8tffCfpYwRudyOVhaPCjKuek,873
+EntDetect/Jwalk/naccess.config.txt,sha256=ZLXV2ULm5kjPGq7ABO4YYx7Jc1eu6mAlk76JpsP2Vz4,2780
+EntDetect/resources/__init__.py,sha256=lrlePz5pb7PFp3-EpTdwbNyznTxN3sP4-WiApVYDIX8,438
+EntDetect/resources/calc_K.pl,sha256=6si6voV3VCoN32CKah9yVJAwFOgIqy-z1U6x2nILs1o,15713
+EntDetect/resources/calc_Q.pl,sha256=OMsy86ZPRl1lmWUpLBhlHqfDvkUgoNYov4xureCywfQ,23338
+EntDetect/resources/pulchra,sha256=eO7nNusOVRJRhCOodhiySQCpgVLM_228etI4obajF5M,3598552
+EntDetect/resources/stride,sha256=gViu_Lgc71njrF_WJ5nPlhumh8DB3u9BADVJLZyOWlU,160608
+EntDetect/resources/__pycache__/__init__.cpython-311.pyc,sha256=C3M2sgGloRNhyO-HGCVoteJ0FAXLYxZiqO9_sDxD6mc,449
+EntDetect/resources/shared_files/__init__.py,sha256=-C1lxAgxJOoF_daSJCGf2Qid6u9__hUJoe_C-rGkC3g,102
+EntDetect/resources/shared_files/bt_contact_potential.dat,sha256=dABkMtqnj--wAwPMejMFmCcjP5u_z0N1uh8z72OgPSQ,1384
+EntDetect/resources/shared_files/karanicolas_dihe_parm.dat,sha256=tA-xnBq5bYDB5VGoTQGCStBpwlmVuZfiwJPn489_6i4,57600
+EntDetect/resources/shared_files/kgs_contact_potential.dat,sha256=FwsIIseSmgUH07P3IAMXMignhHq-jtPHl8Nh8lSTz8c,1168
+EntDetect/resources/shared_files/mj_contact_potential.dat,sha256=KNBwAwZctCZdzmhZkirVHHDggIgKa_CEtHx-pMI_Hog,1303
+entdetect-1.2.0.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+scripts/__init__.py,sha256=_rbb5_TMoSLkMNpZ4PbaD1GDTiiewYSGy_aKfsOH6PI,132
+scripts/convert_cor_psf_to_pdb.py,sha256=ySxnvJYOspd3pC_t3iljo5AiXBXjaOC_Gii5XYx5QG8,2963
+scripts/run_Foldingpathway.py,sha256=5trkrU5cgDZVjJ4fy2FKZ-in2Y6KsSqV4HbxxOGKVyI,8451
+scripts/run_MSM.py,sha256=ST4kCQy7rf88h9w7_TRaGJKRYVqECxKtu44F2Un3H7g,7591
+scripts/run_OP_on_simulation_traj.py,sha256=4ODQFEyloybfIO_mGIPnhe_OBrFGw23EYD6agX_QsIU,9923
+scripts/run_change_resolution.py,sha256=FvfjUNsEqeLrP0VjasOgmPnhfiZugDFmz9sBMlltBPc,2214
+scripts/run_compare_sim2exp.py,sha256=SWlzfed37oN88DZ1k_s6KnctwG89ZOrr1v5GPbRHd_E,10300
+scripts/run_montecarlo.py,sha256=Tz1dFvhUSdons8R-REsL9RUDBjGTvZ398OX5aeij5lI,5690
+scripts/run_nativeNCLE.py,sha256=KFKKQ1nTUhBB1DbANfUh433cCW_HG_0BALgX9zx1dBA,9493
+scripts/run_nonnative_entanglement_clustering.py,sha256=md-IRSK-3z8jnqx7iOmnmPm7uQO4a-omGHDXxe5Tr3A,5825
+scripts/run_population_modeling.py,sha256=yZm0vMEwIK4qQUJGoK36Tt821LYf55b1CPDzOmgv0jk,4222
+scripts/run_workflow4_nativeNCLE_batch.py,sha256=RBsRcIuCg4qT9imqhYJ4Ow4ajx2y1wXpreA78QM5rbE,16556
+entdetect-1.2.0.dist-info/METADATA,sha256=KVTSuIVKsDNvbGUo3vdb9CW3y6K_GhlCOGxwuZffVdA,614
+entdetect-1.2.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+entdetect-1.2.0.dist-info/entry_points.txt,sha256=tn3EH7khcG4MH6AlYPkCjfIDB4AJwwlSuDvlk7i3tdk,588
+entdetect-1.2.0.dist-info/top_level.txt,sha256=hucW5IQiJAKoqBMvgmFHSRbxr5Eox7caYQB2sdtLlVU,18
+entdetect-1.2.0.dist-info/RECORD,,

entdetect-1.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

entdetect-1.2.0.dist-info/entry_points.txt

@@ -0,0 +1,11 @@
+[console_scripts]
+convert_cor_psf_to_pdb = scripts.convert_cor_psf_to_pdb:main
+run_Foldingpathway = scripts.run_Foldingpathway:main
+run_MSM = scripts.run_MSM:main
+run_OP_on_simulation_traj = scripts.run_OP_on_simulation_traj:main
+run_change_resolution = scripts.run_change_resolution:main
+run_compare_sim2exp = scripts.run_compare_sim2exp:main
+run_montecarlo = scripts.run_montecarlo:main
+run_nativeNCLE = scripts.run_nativeNCLE:main
+run_nonnative_entanglement_clustering = scripts.run_nonnative_entanglement_clustering:main
+run_population_modeling = scripts.run_population_modeling:main