gemmi-protools 0.1.8__py3-none-any.whl → 0.1.10__py3-none-any.whl

gemmi_protools/io/cif_opts.py

@@ -135,6 +135,14 @@ def _cif_entity_info(block: gemmi.cif.Block) -> Entity:
 def _cif_block_for_output(structure: gemmi.Structure, entity: Entity) -> gemmi.cif.Block:
     block = structure.make_mmcif_block()
 
+    reflns = block.find_mmcif_category(category="_reflns.")
+    if "_reflns.d_resolution_high" not in list(reflns.tags) or "_reflns.d_resolution_low" not in list(reflns.tags):
+        reflns.erase()
+
+        resolution = "%.2f" % structure.resolution
+        reflns_loop = block.init_loop(prefix="_reflns.", tags=["d_resolution_high", "d_resolution_low"])
+        reflns_loop.add_row([resolution, resolution])
+
     ta = block.find_mmcif_category(category="_entity.")
     da = pd.DataFrame(list(ta), columns=list(ta.tags))
     if "_entity.id" in da.columns:

gemmi_protools/io/parser.py

@@ -2,7 +2,7 @@
 @Author: Luo Jiejian
 """
 import pathlib
-from collections import defaultdict, Counter
+from collections import Counter
 from typing import Union, Optional, Dict, List
 
 import gemmi
@@ -114,6 +114,19 @@ def _update_entity_names(entity: Entity, mapper: Dict[str, str]):
             tmp[mapper[key]] = entity[super_key][key]
         entity.__setattr__(super_key, tmp)
 
+    new_polymer2eid = dict()
+    for c, old_eid in entity.polymer2eid.items():
+        new_polymer2eid[c] = mapper[old_eid]
+    entity.__setattr__(name="polymer2eid", value=new_polymer2eid)
+
+
+def _melt_dict(inputs: dict):
+    outputs = dict()
+    for keys, val in inputs.items():
+        for k in keys.split(","):
+            outputs[k] = val
+    return outputs
+
 
 @typechecked
 def pdb_parser(path: Union[str, pathlib.Path]):
@@ -126,39 +139,34 @@ def pdb_parser(path: Union[str, pathlib.Path]):
         struct = gemmi.read_structure(str(path))
         struct.resolution = _get_pdb_resolution(struct.raw_remarks)
         ent_0 = _pdb_entity_info(path)
+        ch2desc = _melt_dict(ent_0.eid2desc)
+        ch2specie = _melt_dict(ent_0.eid2specie)
+        ch2taxid = _melt_dict(ent_0.eid2taxid)
 
         struct.setup_entities()
-
-        # pdb have "A,B,C" chains
-        # after setup, entities will merge
         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()
+        # set non-polymer entity names
+        non_polymer_entities = [e.name for e in struct.entities if e.polymer_type.name == "Unknown"]
+        for k in non_polymer_entities:
+            assert k in ent_t.eid2desc
+            if ent_t.eid2desc[k] == "?":
+                ent_t.eid2desc[k] = k
 
-        for middle_eid, new_eid in _mapper.items():
-            if middle_eid in rec:
-                mid = rec[middle_eid]
-                mid.sort()
-                old_eid = str(",".join(mid))
-                _mapper_n[old_eid] = new_eid
+        for k in ent_t.eid2desc.keys():
+            if k not in non_polymer_entities:
+                ent_t.eid2desc[k] = ch2desc.get(k, "?")
 
-        if _mapper_n:
-            _update_entity_names(ent_0, _mapper_n)
+        polymer_chs_used_as_eid = set(ch2specie.keys()).intersection(ent_t.eid2desc.keys())
+        for k in polymer_chs_used_as_eid:
+            ent_t.eid2specie[k] = ch2specie.get(k, "?")
+            ent_t.eid2taxid[k] = ch2taxid.get(k, "?")
 
-        ent_1 = _ent_from_structure(struct)
+        m = _assign_digital_entity_names(struct)
+        _update_entity_names(ent_t, m)
 
-        # update ent_0 with ent_1
-        for super_key in ["eid2desc", "polymer2eid"]:
-            for key, val in ent_1[super_key].items():
-                if key not in ent_0[super_key]:
-                    ent_0[super_key][key] = val
-        return struct, ent_0
+        return struct, ent_t
     else:
         raise ValueError("Only support .pdb or .pdb.gz file, but got %s" % path)
 

gemmi_protools/io/reader.py

@@ -83,6 +83,19 @@ class StructureParser(object):
     def to_pdb(self, outfile: str, write_minimal_pdb=False):
         compound_source = _compound_source_string(self.ENTITY)
         struct = self.STRUCT.clone()
+
+        rs = "REMARK   2 RESOLUTION.    %.2f ANGSTROMS." % struct.resolution
+        resolution_remarks = ["%-80s" % "REMARK   2",
+                              "%-80s" % rs]
+
+        resolution_remark_exist = False
+        for line in struct.raw_remarks:
+            if "REMARK   2 RESOLUTION" in line:
+                resolution_remark_exist = True
+
+        if not resolution_remark_exist:
+            struct.raw_remarks = resolution_remarks + struct.raw_remarks
+
         struct.raw_remarks = compound_source + struct.raw_remarks
         if write_minimal_pdb:
             struct.write_minimal_pdb(outfile)

gemmi_protools/utils/fixer.py

@@ -6,33 +6,35 @@ import gzip
 import io
 import os
 import pathlib
+import re
 import shutil
 import subprocess
 import time
 import uuid
-from typing import Union, Optional
+from typing import Union
 
+import openmm
 import pdbfixer
 from openmm import app
-import openmm
 from typeguard import typechecked
 
+from gemmi_protools import StructureParser
 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], use_platform=True) -> pdbfixer.PDBFixer:
+def _load_by_pbdfixer(path: Union[str, pathlib.Path], cpu_platform=True) -> pdbfixer.PDBFixer:
     """
 
     Args:
         path:
-        use_platform: default True, if False, auto select platform
+        cpu_platform: default True, if False, auto select platform
 
     Returns:
 
     """
-    if use_platform:
+    if cpu_platform:
         platform = openmm.Platform.getPlatformByName('CPU')
     else:
         platform = None
@@ -66,9 +68,8 @@ def clean_structure(input_file: Union[str, pathlib.Path],
                     keep_heterogens: str = "all",
                     replace_nonstandard: bool = True,
                     ph: Union[float, int] = 7.0,
-                    check_mode: bool = True,
-                    threshold: float = 0.3,
-                    use_platform=True
+                    cpu_platform=True,
+                    clean_connect=True
                     ):
     """
 
@@ -87,9 +88,8 @@ def clean_structure(input_file: Union[str, pathlib.Path],
             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
-    :param check_mode: default True to check the ratio of residues with missing atoms
-    :param threshold: float, default 0.3, only use when check_mode=True
-    :param use_platform: default True to use CPU platform, if False, auto select platform
+    :param cpu_platform: default True to use CPU platform, if False, auto select platform
+    :param clean_connect: default True to clean CONECT lines in output pdb
 
     :return:
         str, status message of fixing
@@ -102,16 +102,14 @@ def clean_structure(input_file: Union[str, pathlib.Path],
         ######################################################
         # load structure
         ######################################################
-        fixer = _load_by_pbdfixer(input_file, use_platform=use_platform)
+        fixer = _load_by_pbdfixer(input_file, cpu_platform)
 
         ######################################################
         # check
         ######################################################
         fixer.findMissingResidues()
         fixer.findMissingAtoms()
-        ratio = len(fixer.missingAtoms) / fixer.topology.getNumResidues()
-        if ratio > threshold:
-            return dict(input=input_file, msg="Too many residues with missing atoms: %.2f" % ratio)
+        ratio = "%.2f" % (len(fixer.missingAtoms) / fixer.topology.getNumResidues(),)
 
         ######################################################
         # replace non-standard residues
@@ -166,73 +164,94 @@ def clean_structure(input_file: Union[str, pathlib.Path],
         msg_str = "Finished"
     except Exception as e:
         msg_str = str(e)
+        ratio = "*"
+    else:
+        if clean_connect:
+            output_lines = []
+            with open(output_file, "r") as in_handle:
+                for line in in_handle:
+                    if not re.match("CONECT", line):
+                        output_lines.append(line)
+            with open(output_file, "w") as out_handle:
+                print("".join(output_lines), file=out_handle)
 
-    return dict(input=input_file, msg=msg_str)
+    return dict(input=input_file, msg=msg_str, res_ratio_with_missing_atoms=ratio)
 
 
 @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)
-
+def repair_structure(input_file: str,
+                     output_file: str,
+                     complex_with_dna: bool = False,
+                     complex_with_rna: bool = False,
+                     timeout: Union[int, float] = 3600):
+    """
 
-@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):
+    :param input_file: .pdb or .cif or .pdb.gz or .cif.gz
+    :param output_file: .pdb file
+    :param complex_with_dna: bool, default False, not debug yet
+    :param complex_with_rna: bool, default False, not debug yet
+    :param timeout: float or int
+    :return:
+    """
+    ############################################################
+    # Check and convert input_file to .pdb if not
+    ############################################################
+    assert os.path.splitext(output_file)[1] == ".pdb", "output_file Not .pdb: %s" % output_file
+    assert _is_cif(input_file) or _is_pdb(input_file), "Not .pdb or .cif or .pdb.gz or .cif.gz: %s" % input_file
+
+    # input_file and output_file can't be the same path
+    p_in = pathlib.Path(input_file).expanduser().resolve()
+    p_out = pathlib.Path(output_file).expanduser().resolve()
+
+    assert str(p_in) != str(p_out), "input_file and output_file can't be the same path"
+    ############################################################
+    # Config Path
+    ############################################################
+    file_name = os.path.basename(input_file)
+    stem_name = os.path.splitext(file_name)[0]
+
+    in_dir = os.path.dirname(input_file)
+    out_dir = os.path.dirname(output_file)
     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())))
+        os.makedirs(out_dir)
+
+    temp_dir = os.path.join(out_dir, "_RepairTemp_%s" % str(uuid.uuid4()))
+    if os.path.isdir(temp_dir):
+        shutil.rmtree(temp_dir)
+    os.makedirs(temp_dir)
+
+    if os.path.splitext(input_file)[1] != ".pdb":
+        # convert to .pdb
+        st = StructureParser()
+        st.load_from_file(input_file)
+        file_name_r = "%s.pdb" % stem_name
+        in_dir_r = temp_dir
+        st.to_pdb(os.path.join(in_dir_r, file_name_r))
+    else:
+        file_name_r = file_name
+        in_dir_r = in_dir
 
-    if os.path.isdir(sub_temp_dir):
-        shutil.rmtree(sub_temp_dir)
+    foldx_path = shutil.which("foldx")
+    if foldx_path is None:
+        raise RuntimeError("path of foldx is not set or found in PATH")
 
-    os.makedirs(sub_temp_dir)
+    cwd_dir = os.getcwd()
 
-    if foldx_path is None:
-        foldx_path = shutil.which("foldx")
+    repair_cmd = [foldx_path,
+                  "-c RepairPDB",
+                  "--pdb %s" % file_name_r,
+                  "--pdb-dir %s" % in_dir_r,
+                  "--output-dir %s" % temp_dir
+                  ]
+    if complex_with_dna:
+        repair_cmd.append("--complexWithDNA true")
 
-    if foldx_path is None:
-        raise RuntimeError("path of foldx is not set or found in PATH")
+    if complex_with_rna:
+        repair_cmd.append("--complexWithRNA true")
 
-    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
-                        ]
+    command_settings = ["cd %s &&" % temp_dir] + repair_cmd + ["&& cd %s" % cwd_dir]
 
     start = time.time()
-
     try:
         result = subprocess.run(" ".join(command_settings), shell=True, check=True,
                                 stdout=subprocess.PIPE, stderr=subprocess.PIPE,
@@ -241,22 +260,19 @@ def repair_structure(input_file: Union[str, pathlib.Path],
         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
+            msg_str = str(result.stderr)
     except Exception as e:
-        # Handle other exceptions such as file not found or permissions issues
-        msg_str = str(e).encode()
+        msg_str = str(e)
+    else:
+        if msg_str == "Finished":
+            # just keep .pdb, ignore .fxout
+            result_file = os.path.join(temp_dir, "%s_Repair.pdb" % stem_name)
+            if os.path.exists(result_file):
+                shutil.move(result_file, output_file)
+            else:
+                msg_str = "result file not found"
     finally:
-        # clean sub temp
-        if os.path.isdir(sub_temp_dir):
-            shutil.rmtree(sub_temp_dir)
+        if os.path.isdir(temp_dir):
+            shutil.rmtree(temp_dir)
     end = time.time()
-    return dict(input=input_file, msg=msg_str, use_time=round(end - start, 1))
+    return dict(input=input_file, output=output_file, msg=msg_str, use_time=round(end - start, 1))

{gemmi_protools-0.1.8.dist-info → gemmi_protools-0.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gemmi_protools
-Version: 0.1.8
+Version: 0.1.10
 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-0.1.8.dist-info → gemmi_protools-0.1.10.dist-info}/RECORD

@@ -1,20 +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/cif_opts.py,sha256=ZSZTbey3SvHyHaJ1T7m432Vg9oraYB1Jgay6ikIvWeQ,6779
 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/parser.py,sha256=HFc4Kovr6rxEpLAEDUtF_e-RnA5OsWMeMFjuVNm7UYY,9507
 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/reader.py,sha256=lI9JTXqsct3D719qVN7Dsvg-zHudElojpW5-odtXa8A,16527
 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=oiNtLCjQLFk4JHeO4exEkMH8QoEiKsJZIJRebkGGfBM,9545
+gemmi_protools/utils/fixer.py,sha256=RDmpoZpTrGdwuJQTTK1eif132MHV1I-T6Nt47ezgxTM,10236
 gemmi_protools/utils/ppi.py,sha256=VWYsdxWwQoS1xwEYj5KB96Zz3F8r5Eyuw6NT3ReD-wc,2330
-gemmi_protools-0.1.8.dist-info/licenses/LICENSE,sha256=JuQvKcgj6n11y5y6nXr9rABv3gJSswc4eTCd5WZBtSY,1062
-gemmi_protools-0.1.8.dist-info/METADATA,sha256=j0xy5aqbEvdlqoNrEdCSiBpmLVOpe3URit-85PBWa1s,567
-gemmi_protools-0.1.8.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
-gemmi_protools-0.1.8.dist-info/top_level.txt,sha256=P12mYJi5O5EKIn5u-RFaWxuix431CgLacSRD7rBid_U,15
-gemmi_protools-0.1.8.dist-info/RECORD,,
+gemmi_protools-0.1.10.dist-info/licenses/LICENSE,sha256=JuQvKcgj6n11y5y6nXr9rABv3gJSswc4eTCd5WZBtSY,1062
+gemmi_protools-0.1.10.dist-info/METADATA,sha256=0xlRghvF1tEfCJi6OxLEGCIsJctUat4y2Sgt18tSrU0,568
+gemmi_protools-0.1.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+gemmi_protools-0.1.10.dist-info/top_level.txt,sha256=P12mYJi5O5EKIn5u-RFaWxuix431CgLacSRD7rBid_U,15
+gemmi_protools-0.1.10.dist-info/RECORD,,

{gemmi_protools-0.1.8.dist-info → gemmi_protools-0.1.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.8.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any