gemmi-protools 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

gemmi_protools/__init__.py

@@ -1,8 +1,8 @@
 """
 @Author: Luo Jiejian
 """
-from .reader import StructureParser
-from .convert import gemmi2bio, bio2gemmi
-from .align import StructureAligner
-from .ppi import ppi_interface_residues
-from .dockq import dockq_score, dockq_score_interface
+from gemmi_protools.io.convert import gemmi2bio, bio2gemmi
+from gemmi_protools.io.reader import StructureParser
+from gemmi_protools.utils.align import StructureAligner
+from gemmi_protools.utils.ppi import ppi_interface_residues
+from gemmi_protools.utils.dockq import dockq_score, dockq_score_interface

gemmi_protools/io/__init__.py

@@ -0,0 +1,3 @@
+"""
+@Author: Luo Jiejian
+"""

gemmi_protools/{cif_opts.py → io/cif_opts.py}

@@ -9,7 +9,7 @@ import gemmi
 import pandas as pd
 from typeguard import typechecked
 
-from .struct_info import Entity
+from gemmi_protools.io.struct_info import Entity
 
 
 @typechecked

gemmi_protools/{parser.py → io/parser.py}

@@ -8,9 +8,9 @@ from typing import Union, Optional, Dict, List
 import gemmi
 from typeguard import typechecked
 
-from .cif_opts import _cif_entity_info, _is_cif, _get_cif_resolution
-from .pdb_opts import _pdb_entity_info, _is_pdb, _get_pdb_resolution
-from .struct_info import Entity
+from gemmi_protools.io.cif_opts import _cif_entity_info, _is_cif, _get_cif_resolution
+from gemmi_protools.io.pdb_opts import _pdb_entity_info, _is_pdb, _get_pdb_resolution
+from gemmi_protools.io.struct_info import Entity
 
 
 @typechecked
@@ -134,14 +134,19 @@ def pdb_parser(path: Union[str, pathlib.Path]):
         block = struct.make_mmcif_block()
         ent_t = _cif_entity_info(block)
         rec = defaultdict(list)
+
         for cn, middle_eid in ent_t.polymer2eid.items():
             rec[middle_eid].append(cn)
 
         _mapper = _assign_digital_entity_names(struct)
         _mapper_n = dict()
+
         for middle_eid, new_eid in _mapper.items():
-            old_eid = str(",".join(rec[middle_eid]))
-            _mapper_n[old_eid] = new_eid
+            if middle_eid in rec:
+                mid = rec[middle_eid]
+                mid.sort()
+                old_eid = str(",".join(mid))
+                _mapper_n[old_eid] = new_eid
 
         if _mapper_n:
             _update_entity_names(ent_0, _mapper_n)

gemmi_protools/{pdb_opts.py → io/pdb_opts.py}

@@ -10,8 +10,8 @@ from typing import Dict, Union, List
 
 from typeguard import typechecked
 
-from .parse_pdb_header import _parse_pdb_header_list
-from .struct_info import Entity
+from gemmi_protools.io.parse_pdb_header import _parse_pdb_header_list
+from gemmi_protools.io.struct_info import Entity
 
 
 @typechecked
@@ -119,6 +119,8 @@ def _compound_source_string(entity: Entity) -> List[str]:
         entity2polymer[v].append(k)
     entity_labels = list(entity2polymer.keys())
     entity_labels.sort()
+    for v in entity2polymer.values():
+        v.sort()
 
     values = []
     for i, el in enumerate(entity_labels):
@@ -136,9 +138,9 @@ def _compound_source_string(entity: Entity) -> List[str]:
     compound_molecule = "COMPND {n_line:>3} MOLECULE: {molecule};"
     compound_chain = "COMPND {n_line:>3} CHAIN: {chain};"
 
-    i = 0
+    i = 1
     for val in values:
-        if i == 0:
+        if i == 1:
             outputs.append(compound_mol0.format(**val))
             i += 1
             for c_str in [compound_molecule, compound_chain]:

gemmi_protools/{reader.py → io/reader.py}

@@ -11,13 +11,13 @@ import gemmi
 import numpy as np
 from typeguard import typechecked
 
-from .cif_opts import _cif_block_for_output, _is_cif
-from .parser import (_assign_digital_entity_names, _ent_from_structure,
-                     pdb_parser, cif_parser, _chain_type, _chain_names2one_letter,
-                     _assert_unique_chain_names_in_models, get_assembly)
-from .pdb_opts import _compound_source_string, _is_pdb
-from .peptide import nucleic_3to1_mapper, protein_3to1_mapper
-from .struct_info import Info
+from gemmi_protools.io.cif_opts import _cif_block_for_output, _is_cif
+from gemmi_protools.io.parser import (_assign_digital_entity_names, _ent_from_structure,
+                                      pdb_parser, cif_parser, _chain_type, _chain_names2one_letter,
+                                      _assert_unique_chain_names_in_models, get_assembly)
+from gemmi_protools.io.pdb_opts import _compound_source_string, _is_pdb
+from gemmi_protools.io.peptide import nucleic_3to1_mapper, protein_3to1_mapper
+from gemmi_protools.io.struct_info import Info
 
 
 class StructureParser(object):
@@ -419,3 +419,27 @@ class StructureParser(object):
         else:
             one_letter_code = ""
         return one_letter_code
+
+    def clean_structure(self, keep_ligand=True):
+        """
+        (1) remove_alternative_conformations
+        (2) remove_hydrogens
+        (3) remove_water
+        (4) remove_empty_chains
+
+        :return:
+        """
+        self.set_default_model()
+        self.STRUCT.remove_alternative_conformations()
+        self.STRUCT.remove_hydrogens()
+
+        if keep_ligand:
+            self.STRUCT.remove_waters()
+        else:
+            self.STRUCT.remove_ligands_and_waters()
+
+        self.STRUCT.remove_empty_chains()
+
+        # update information
+        self.update_entity()
+        self.update_full_sequences()

gemmi_protools/utils/__init__.py

@@ -0,0 +1,3 @@
+"""
+@Author: Luo Jiejian
+"""

gemmi_protools/{align.py → utils/align.py}

@@ -15,8 +15,8 @@ import numpy as np
 from Bio.PDB import Superimposer
 from typeguard import typechecked
 
-from .convert import gemmi2bio, bio2gemmi
-from .reader import StructureParser
+from gemmi_protools.io.convert import gemmi2bio, bio2gemmi
+from gemmi_protools.io.reader import StructureParser
 
 
 class StructureAligner(object):

gemmi_protools/{dockq.py → utils/dockq.py}

@@ -13,7 +13,7 @@ from typing import Optional, Union
 import pandas as pd
 from typeguard import typechecked
 
-from .reader import StructureParser
+from gemmi_protools.io.reader import StructureParser
 
 
 @typechecked

gemmi_protools/utils/fixer.py

@@ -0,0 +1,231 @@
+"""
+@Author: Luo Jiejian
+@Date: 2025/1/21
+"""
+import gzip
+import io
+import os
+import pathlib
+import shutil
+import subprocess
+import time
+import uuid
+from typing import Union, Optional
+
+import pdbfixer
+from openmm import app
+from typeguard import typechecked
+
+from gemmi_protools.io.cif_opts import _is_cif
+from gemmi_protools.io.pdb_opts import _is_pdb
+
+
+@typechecked
+def _load_by_pbdfixer(path: Union[str, pathlib.Path]) -> pdbfixer.PDBFixer:
+    cur_path = pathlib.Path(path)
+    if _is_pdb(path) or _is_cif(path):
+        s1 = cur_path.suffixes[-1]
+        s2 = "".join(cur_path.suffixes[-2:])
+
+        if s1 in [".pdb", ".cif"]:
+            # s1 suffix
+            fixer = pdbfixer.PDBFixer(filename=path)
+        else:
+            # s2 suffix
+            with gzip.open(path, "rb") as gz_handle:
+                with io.TextIOWrapper(gz_handle, encoding="utf-8") as text_io:
+                    if s2 == ".pdb.gz":
+                        fixer = pdbfixer.PDBFixer(pdbfile=text_io)
+                    else:
+                        fixer = pdbfixer.PDBFixer(pdbxfile=text_io)
+    else:
+        raise ValueError("Only support .cif, .cif.gz, .pdb or .pdb.gz file, but got %s" % path)
+    return fixer
+
+
+@typechecked
+def clean_structure(input_file: Union[str, pathlib.Path],
+                    output_file: Union[str, pathlib.Path],
+                    add_missing_residue: bool = False,
+                    add_missing_atoms: str = "heavy",
+                    keep_heterogens: str = "all",
+                    replace_nonstandard: bool = True,
+                    ph: Union[float, int] = 7.0
+                    ):
+    """
+
+    :param input_file: str, Input structure file, support file format .cif, .cif.gz, .pdb or .pdb.gz
+    :param output_file: str, Output structure file, support file format .cif, .pdb
+    :param add_missing_residue: default False
+    :param add_missing_atoms: default heavy, accepted values 'all', 'heavy', 'hydrogen', 'none'
+        all: add missing heavy and hydrogen atoms
+        heavy: add missing heavy atoms only
+        hydrogen: add missing hydrogen atoms only
+        none: not add missing atoms
+
+    :param keep_heterogens: default all, accepted values 'all', 'water', 'none'
+            all: keep all heterogens
+            water: only keep water
+            none: remove all heterogens
+    :param replace_nonstandard: default True, replace all non-standard residues to standard ones
+    :param ph: default 7.0, ph values to add missing hydrogen atoms
+    :return:
+        str, status message of fixing
+        if successful, return Finish, otherwise message of error
+    """
+    assert add_missing_atoms in ['all', 'heavy', 'hydrogen', 'none']
+    assert keep_heterogens in ['all', 'water', 'none']
+
+    try:
+        ######################################################
+        # load structure
+        ######################################################
+        fixer = _load_by_pbdfixer(input_file)
+
+        ######################################################
+        # replace non-standard residues
+        ######################################################
+        if replace_nonstandard:
+            fixer.findNonstandardResidues()
+            fixer.replaceNonstandardResidues()
+
+        ######################################################
+        # remove heterogens
+        ######################################################
+        if keep_heterogens == 'none':
+            fixer.removeHeterogens(keepWater=False)
+        elif keep_heterogens == 'water':
+            fixer.removeHeterogens(keepWater=True)
+
+        ######################################################
+        # missing residue
+        ######################################################
+        if add_missing_residue:
+            fixer.findMissingResidues()
+        else:
+            fixer.missingResidues = {}
+
+        ######################################################
+        # missing atoms
+        ######################################################
+        fixer.findMissingAtoms()
+        if add_missing_atoms not in ['all', 'heavy']:
+            fixer.missingAtoms = {}
+            fixer.missingTerminals = {}
+        fixer.addMissingAtoms()
+        if add_missing_atoms in ['all', 'hydrogen']:
+            fixer.addMissingHydrogens(ph)
+
+        ######################################################
+        # output
+        ######################################################
+        out_dir = os.path.dirname(output_file)
+        if not os.path.isdir(out_dir):
+            os.makedirs(out_dir)
+
+        suffix = pathlib.Path(output_file).suffix
+        assert suffix in [".pdb", ".cif"], "output file must be .cif or .pdb"
+
+        with open(output_file, 'w') as out_handle:
+            if suffix == ".pdb":
+                app.PDBFile.writeFile(fixer.topology, fixer.positions, out_handle, keepIds=True)
+            else:
+                app.PDBxFile.writeFile(fixer.topology, fixer.positions, out_handle, keepIds=True)
+
+        msg_str = "Finished"
+    except Exception as e:
+        msg_str = str(e)
+
+    return dict(input=input_file, msg=msg_str)
+
+
+@typechecked
+def move_with_overwrite(src_folder: str, dst_folder: str, filename: str):
+    assert os.path.isdir(src_folder)
+    assert os.path.isdir(dst_folder)
+
+    src_path = os.path.join(src_folder, filename)
+    dst_path = os.path.join(dst_folder, filename)
+
+    if os.path.exists(dst_path):
+        os.remove(dst_path)
+    shutil.move(src_path, dst_folder)
+
+
+@typechecked
+def repair_structure(input_file: Union[str, pathlib.Path],
+                     out_dir: Union[str, pathlib.Path],
+                     temp_dir: Union[str, pathlib.Path],
+                     foldx_path: Optional[str] = None,
+                     timeout=3600):
+    if not os.path.isdir(out_dir):
+        raise NotADirectoryError(out_dir)
+
+    if not os.path.isdir(temp_dir):
+        raise NotADirectoryError(temp_dir)
+
+    in_path = pathlib.Path(input_file).expanduser().resolve()
+    pdb_dir = str(in_path.parent)
+    pdb_file = str(in_path.name)
+    if not os.path.isfile(input_file):
+        raise FileNotFoundError(input_file)
+
+    assert pdb_dir != str(out_dir), "output directory can't be the directory of input_file"
+
+    stem_name = in_path.stem
+
+    # create temp dir
+    sub_temp_dir = os.path.join(temp_dir, "%s_%s" % (stem_name, str(uuid.uuid4())))
+
+    if os.path.isdir(sub_temp_dir):
+        shutil.rmtree(sub_temp_dir)
+
+    os.makedirs(sub_temp_dir)
+
+    if foldx_path is None:
+        foldx_path = shutil.which("foldx")
+
+    if foldx_path is None:
+        raise RuntimeError("path of foldx is not set or found in PATH")
+
+    old_dir = os.getcwd()
+    command_settings = ["cd %s" % sub_temp_dir,
+                        "&&",
+                        foldx_path,
+                        "-c RepairPDB",
+                        "--pdb %s" % pdb_file,
+                        "--pdb-dir %s" % pdb_dir,
+                        "--output-dir %s" % sub_temp_dir,
+                        "&&",
+                        "cd %s" % old_dir
+                        ]
+
+    start = time.time()
+
+    try:
+        result = subprocess.run(" ".join(command_settings), shell=True, check=True,
+                                stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+                                timeout=timeout)
+        # Return a tuple of the file name and the stdout or stderr if command fails
+        if result.returncode == 0:
+            msg_str = "Finished"
+        else:
+            msg_str = result.stderr
+
+        result_file = os.path.join(sub_temp_dir, "%s_Repair.pdb" % stem_name)
+        fxout_file = os.path.join(sub_temp_dir, "%s_Repair.fxout" % stem_name)
+        if os.path.exists(result_file) and os.path.exists(fxout_file):
+            move_with_overwrite(sub_temp_dir, out_dir, "%s_Repair.pdb" % stem_name)
+            move_with_overwrite(sub_temp_dir, out_dir, "%s_Repair.fxout" % stem_name)
+    except subprocess.CalledProcessError as e:
+        # Handle errors in the called executable
+        msg_str = e.stderr
+    except Exception as e:
+        # Handle other exceptions such as file not found or permissions issues
+        msg_str = str(e).encode()
+    finally:
+        # clean sub temp
+        if os.path.isdir(sub_temp_dir):
+            shutil.rmtree(sub_temp_dir)
+    end = time.time()
+    return dict(input=input_file, msg=msg_str, use_time=round(end - start, 1))

gemmi_protools/{ppi.py → utils/ppi.py}

@@ -7,7 +7,7 @@ from typing import Union, List
 import numpy as np
 from scipy.spatial import cKDTree
 
-from .reader import StructureParser
+from gemmi_protools.io.reader import StructureParser
 
 
 def _ppi_atoms(struct, chains):

{gemmi_protools-0.1.4.dist-info → gemmi_protools-0.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gemmi_protools
-Version: 0.1.4
+Version: 0.1.6
 Summary: An Enhanced tool to process PDB structures based on Gemmi
 Author-email: Luo Jiejian <luojiejian12@mails.ucas.ac.cn>
 License-Expression: MIT

gemmi_protools-0.1.6.dist-info/RECORD

@@ -0,0 +1,20 @@
+gemmi_protools/__init__.py,sha256=hwUw-EieCG0kwzHjTjzHF9Bc3D-J5R_l6G8PCcFegkw,331
+gemmi_protools/io/__init__.py,sha256=F6e1xNT_7lZAWQgNIneH06o2qtWYrHNr_xPUPTwwx5E,29
+gemmi_protools/io/cif_opts.py,sha256=TKND91aRGB5hYNdTFElCKMGabCg4klLk_c1evC3WZuA,6368
+gemmi_protools/io/convert.py,sha256=780sQcwhslUD4Hj5UZMVlQdbicniJ6jNjncTl_7jaMk,3841
+gemmi_protools/io/parse_pdb_header.py,sha256=UOGMsE3-d3APhO7zaAEE0NT31n-iqt55VpDh_RPOicI,14223
+gemmi_protools/io/parser.py,sha256=NCLc9IHH-tb2hIm0jZeKu2nVw2Isr-n-pH4l7JbKA5w,9130
+gemmi_protools/io/pdb_opts.py,sha256=laUqxlecOe6goax12q8EJGZuZbHyIGsXVucMV3gVrgg,5741
+gemmi_protools/io/peptide.py,sha256=a2wiEutJmvhl6gDCIzzqRCbmyknk2mwgy2FZ53lXclU,750
+gemmi_protools/io/reader.py,sha256=oaJ5TTWLFCZ3tDq3R5dAyBqm4Q2sxmfl4D8cGvSOdl0,16060
+gemmi_protools/io/struct_info.py,sha256=9nBj1Zer03S8_Wks7L7uRlc9PlbfCKzoaT32pKR58X8,2769
+gemmi_protools/utils/__init__.py,sha256=F6e1xNT_7lZAWQgNIneH06o2qtWYrHNr_xPUPTwwx5E,29
+gemmi_protools/utils/align.py,sha256=CZcrvjy-ZbX2u7OAn-YGblbxaj9YFUDX4CFZcpbpnB8,6959
+gemmi_protools/utils/dockq.py,sha256=XmMwVEy-H4p6sH_HPcDWA3TP77OWdih0fE_BQJDr4pU,4189
+gemmi_protools/utils/fixer.py,sha256=f1MAeYkFukijaBwTdINO0733Qbe5B9xSgRCE69nHkN4,8396
+gemmi_protools/utils/ppi.py,sha256=VWYsdxWwQoS1xwEYj5KB96Zz3F8r5Eyuw6NT3ReD-wc,2330
+gemmi_protools-0.1.6.dist-info/licenses/LICENSE,sha256=JuQvKcgj6n11y5y6nXr9rABv3gJSswc4eTCd5WZBtSY,1062
+gemmi_protools-0.1.6.dist-info/METADATA,sha256=N8Os-XHbUKuRDyQw0Z3MjtYy5Z5fqLFpP1sxEZnoEbU,567
+gemmi_protools-0.1.6.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
+gemmi_protools-0.1.6.dist-info/top_level.txt,sha256=P12mYJi5O5EKIn5u-RFaWxuix431CgLacSRD7rBid_U,15
+gemmi_protools-0.1.6.dist-info/RECORD,,

{gemmi_protools-0.1.4.dist-info → gemmi_protools-0.1.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.7.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

gemmi_protools-0.1.4.dist-info/RECORD

@@ -1,17 +0,0 @@
-gemmi_protools/__init__.py,sha256=SvBS-OBVhYsoHCWw4Rwp-6p8vaFhJC9FQMlx0vYpITQ,237
-gemmi_protools/align.py,sha256=LoN2xlZbvEwceQiz6F_VQBxlsNTKfGnJQ1LM937t1qw,6925
-gemmi_protools/cif_opts.py,sha256=bfJuUQSYzz_703cIgxgvEVxXalfVYEZwpVjuYEB9O2U,6351
-gemmi_protools/convert.py,sha256=780sQcwhslUD4Hj5UZMVlQdbicniJ6jNjncTl_7jaMk,3841
-gemmi_protools/dockq.py,sha256=JGPQ7Xs7gz9wubVVT9WSP5lZsLnfgcUH-_nLJ3c8I3U,4172
-gemmi_protools/parse_pdb_header.py,sha256=UOGMsE3-d3APhO7zaAEE0NT31n-iqt55VpDh_RPOicI,14223
-gemmi_protools/parser.py,sha256=QIJCOfK8FaFbLMvBG82zTOAjIvQJcf2WRwuFSxj4zvc,8982
-gemmi_protools/pdb_opts.py,sha256=NbXLDNNVF7tuG_bUM0Infylf5aYnOCP2Pd-ndqm5bK4,5652
-gemmi_protools/peptide.py,sha256=a2wiEutJmvhl6gDCIzzqRCbmyknk2mwgy2FZ53lXclU,750
-gemmi_protools/ppi.py,sha256=nRzRWv28SDjVt6hMShRL_QYKFsBO1xA5jSGIQrN0JBg,2313
-gemmi_protools/reader.py,sha256=u7872K-XeUW_sr0E1SaQWrPVWm88jPBUN8LLzf0flM0,15321
-gemmi_protools/struct_info.py,sha256=9nBj1Zer03S8_Wks7L7uRlc9PlbfCKzoaT32pKR58X8,2769
-gemmi_protools-0.1.4.dist-info/licenses/LICENSE,sha256=JuQvKcgj6n11y5y6nXr9rABv3gJSswc4eTCd5WZBtSY,1062
-gemmi_protools-0.1.4.dist-info/METADATA,sha256=aKz2slj7fXafD3SnNaI0apr7PIxK87FFXnnwHcCVfvw,567
-gemmi_protools-0.1.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-gemmi_protools-0.1.4.dist-info/top_level.txt,sha256=P12mYJi5O5EKIn5u-RFaWxuix431CgLacSRD7rBid_U,15
-gemmi_protools-0.1.4.dist-info/RECORD,,