gemmi-protools 0.1.16__py3-none-any.whl → 1.0.0__py3-none-any.whl

gemmi_protools/utils/dockq.py

@@ -1,139 +0,0 @@
-"""
-@Author: Luo Jiejian
-"""
-import json
-import os
-import pathlib
-import shutil
-import subprocess
-import tempfile
-import uuid
-from typing import Optional, Union
-
-import pandas as pd
-from typeguard import typechecked
-
-from gemmi_protools.io.reader import StructureParser
-
-
-@typechecked
-def _read_model(model_file: Union[str, pathlib.Path]):
-    st = StructureParser()
-    st.load_from_file(model_file)
-    st.set_default_model()
-    return st
-
-
-@typechecked
-def dockq_score(query_model: Union[str, pathlib.Path],
-                native_model: Union[str, pathlib.Path],
-                mapping: Optional[str] = None):
-    dockq_program = shutil.which("DockQ")
-    if dockq_program is None:
-        raise RuntimeError("DockQ is need")
-
-    q_st = _read_model(query_model)
-    n_st = _read_model(native_model)
-
-    tmp_dir = os.path.join(tempfile.gettempdir(), str(uuid.uuid4()))
-    os.makedirs(tmp_dir)
-
-    result_file = os.path.join(tmp_dir, "result.json")
-    q_file = os.path.join(tmp_dir, "q.pdb")
-    n_file = os.path.join(tmp_dir, "n.pdb")
-    q_st.to_pdb(q_file, write_minimal_pdb=True)
-    n_st.to_pdb(n_file, write_minimal_pdb=True)
-    if mapping is None:
-        cid = "".join(n_st.chain_ids)
-        mapping = cid + ":" + cid
-
-    _command = "%s --mapping %s --json %s %s %s" % (dockq_program, mapping, result_file, q_file, n_file)
-    metrics = ['DockQ', 'F1', 'chain1', 'chain2']
-
-    try:
-        _ = subprocess.run(_command, shell=True, check=True,
-                           stdout=subprocess.PIPE, stderr=subprocess.PIPE,
-                           timeout=300.0)
-    except subprocess.CalledProcessError as e:
-        # Handle errors in the called executable
-        msg = e.stderr.decode()
-        outputs = pd.DataFrame(columns=metrics)
-    except Exception as e:
-        # Handle other exceptions such as file not found or permissions issues
-        msg = str(e)
-        outputs = pd.DataFrame(columns=metrics)
-    else:
-        with open(result_file, "r") as fin:
-            vals = json.load(fin)
-        msg = "Finished"
-        result = []
-        for v in vals["best_result"].values():
-            result.append(v)
-        outputs = pd.DataFrame(result)[metrics]
-    finally:
-        if os.path.isdir(tmp_dir):
-            shutil.rmtree(tmp_dir)
-
-    return dict(value=outputs,
-                msg=msg,
-                mapping=mapping,
-                model=query_model,
-                native=native_model
-                )
-
-
-def dockq_score_interface(query_model: Union[str, pathlib.Path],
-                          native_model: Union[str, pathlib.Path],
-                          chains_a: str,
-                          chains_b: str):
-    ppi_if = chains_a + "@" + chains_b
-    chs_a = list(chains_a)
-    chs_b = list(chains_b)
-
-    # if multiple chains, merge to one
-    q_st = _read_model(query_model)
-    n_st = _read_model(native_model)
-
-    for c in chs_a + chs_b:
-        if c not in q_st.chain_ids:
-            raise RuntimeError("Chain %s is not in the query model: %s" % (c, query_model))
-
-    for c in chs_a + chs_b:
-        if c not in n_st.chain_ids:
-            raise RuntimeError("Chain %s is not in the native model: %s" % (c, native_model))
-
-    if len(chs_a) > 1:
-        q_st.merge_chains(chs_a)
-        n_st.merge_chains(chs_a)
-
-    if len(chs_b) > 1:
-        q_st.merge_chains(chs_b)
-        n_st.merge_chains(chs_b)
-
-    tmp_dir = os.path.join(tempfile.gettempdir(), str(uuid.uuid4()))
-    os.makedirs(tmp_dir)
-
-    q_file = os.path.join(tmp_dir, "qm.pdb")
-    n_file = os.path.join(tmp_dir, "nm.pdb")
-    q_st.to_pdb(q_file, write_minimal_pdb=True)
-    n_st.to_pdb(n_file, write_minimal_pdb=True)
-
-    chs = chs_a[0] + chs_b[0]
-    result = dockq_score(q_file, n_file, mapping="%s:%s" % (chs, chs))
-
-    if len(result["value"]) > 0:
-        q_score = round(result["value"].iloc[0]["DockQ"], 4)
-        f1 = round(result["value"].iloc[0]["F1"], 4)
-    else:
-        q_score = ""
-        f1 = ""
-
-    if os.path.isdir(tmp_dir):
-        shutil.rmtree(tmp_dir)
-
-    return dict(DockQ=q_score,
-                F1=f1,
-                interface=ppi_if,
-                model=query_model,
-                native=native_model
-                )

gemmi_protools/utils/fixer.py

@@ -1,274 +0,0 @@
-"""
-@Author: Luo Jiejian
-@Date: 2025/1/21
-"""
-import gzip
-import io
-import os
-import pathlib
-import re
-import shutil
-import subprocess
-import time
-import uuid
-from typing import Union
-
-import openmm
-import pdbfixer
-from openmm import app
-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], cpu_platform=True) -> pdbfixer.PDBFixer:
-    """
-
-    Args:
-        path:
-        cpu_platform: default True, if False, auto select platform
-
-    Returns:
-
-    """
-    if cpu_platform:
-        platform = openmm.Platform.getPlatformByName('CPU')
-    else:
-        platform = None
-
-    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, platform=platform)
-        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, platform=platform)
-                    else:
-                        fixer = pdbfixer.PDBFixer(pdbxfile=text_io, platform=platform)
-    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,
-                    cpu_platform=True,
-                    clean_connect=True
-                    ):
-    """
-
-    :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
-    :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
-        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, cpu_platform)
-
-        ######################################################
-        # check
-        ######################################################
-        fixer.findMissingResidues()
-        fixer.findMissingAtoms()
-        ratio = "%.2f" % (len(fixer.missingAtoms) / fixer.topology.getNumResidues(),)
-
-        ######################################################
-        # 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)
-        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, res_ratio_with_missing_atoms=ratio)
-
-
-@typechecked
-def repair_structure(input_file: str,
-                     output_file: str,
-                     complex_with_dna: bool = False,
-                     complex_with_rna: bool = False,
-                     timeout: Union[int, float] = 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
-    ############################################################
-    input_file = str(pathlib.Path(input_file).expanduser().resolve())
-    output_file = str(pathlib.Path(output_file).expanduser().resolve())
-    # input_file and output_file can't be the same path
-    assert input_file != output_file, "input_file and output_file can't be the same path"
-
-    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
-
-    ############################################################
-    # Config Path
-    ############################################################
-    out_dir = os.path.dirname(output_file)
-    if not os.path.isdir(out_dir):
-        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)
-
-    # for fix the filename bug of foldx
-    # rename the input always and save to .pdb
-    # convert to .pdb
-    st = StructureParser()
-    st.load_from_file(input_file)
-    # if exist non-1-letter chain ID, rename
-    org2new = st.make_chain_names_to_one_letter()
-
-    file_name_r = "in.pdb"
-    in_dir_r = temp_dir
-    st.to_pdb(os.path.join(in_dir_r, file_name_r))
-
-    foldx_path = shutil.which("foldx")
-    if foldx_path is None:
-        raise RuntimeError("path of foldx is not set or found in PATH")
-
-    cwd_dir = os.getcwd()
-
-    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 complex_with_rna:
-        repair_cmd.append("--complexWithRNA true")
-
-    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,
-                                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 = str(result.stderr)
-    except Exception as e:
-        msg_str = str(e)
-    else:
-        if msg_str == "Finished":
-            # just keep .pdb, ignore .fxout
-            result_file = os.path.join(temp_dir, "in_Repair.pdb")
-            if os.path.exists(result_file):
-                shutil.move(result_file, output_file)
-            else:
-                msg_str = "result file not found"
-    finally:
-        if os.path.isdir(temp_dir):
-            shutil.rmtree(temp_dir)
-    end = time.time()
-    return dict(input=input_file, output=output_file, msg=msg_str, use_time=round(end - start, 1))

gemmi_protools/utils/ppi.py

@@ -1,74 +0,0 @@
-"""
-@Author: Luo Jiejian
-"""
-import pathlib
-from typing import Union, List
-
-import numpy as np
-from scipy.spatial import cKDTree
-
-from gemmi_protools.io.reader import StructureParser
-
-
-def _ppi_atoms(struct, chains):
-    """
-    Load atoms for N and O of backbone and N, O, P, S of side chains, only for PPI searching
-    :param struct:
-    :param chains:
-    :return:
-    """
-    protein_atoms = ['N', 'ND1', 'ND2', 'NE', 'NE1', 'NE2', 'NH1', 'NH2', 'NZ',
-                     'O', 'OD1', 'OD2', 'OE1', 'OE2', 'OG', 'OG1', 'OH',
-                     'SD', 'SG']
-    xna_atoms = ['N1', 'N2', 'N3', 'N4', 'N6', 'N7', 'N9',
-                 'O2', "O2'", "O3'", 'O4', "O4'", "O5'", 'O6',
-                 'OP1', 'OP2', 'OP3', 'P']
-    pro_chs = []
-    xna_chs = []
-    for c in chains:
-        t = struct.chain_types.get(c, "")
-        if t == "protein":
-            pro_chs.append(c)
-        elif t in ["dna", "rna"]:
-            xna_chs.append(c)
-
-    pro_coord, pro_id = struct.get_atom_coords(pro_chs, protein_atoms)
-    xna_coord, xna_id = struct.get_atom_coords(xna_chs, xna_atoms)
-    return np.concatenate([pro_coord, xna_coord], axis=0), np.concatenate([pro_id, xna_id], axis=0)
-
-
-def ppi_interface_residues(in_file: Union[str, pathlib.Path],
-                           chains_x: List[str],
-                           chains_y: List[str],
-                           threshold: float = 4.0):
-    """
-    identify PPI among protein, DNA, RNA
-    :param in_file:
-    :param chains_x:
-    :param chains_y:
-    :param threshold:
-    :return:
-     PPI residues of chains_x, PPI residues of chains_y
-    """
-
-    st = StructureParser()
-    st.load_from_file(in_file)
-    st.set_default_model()
-    st.STRUCT.remove_alternative_conformations()
-    st.STRUCT.remove_ligands_and_waters()
-    st.STRUCT.remove_hydrogens()
-    st.STRUCT.remove_empty_chains()
-    st.update_entity()
-
-    x_coord, x_id = _ppi_atoms(st, chains_x)
-    y_coord, y_id = _ppi_atoms(st, chains_y)
-
-    kd_tree_x = cKDTree(x_coord)
-    kd_tree_y = cKDTree(y_coord)
-
-    pairs = kd_tree_x.sparse_distance_matrix(kd_tree_y, threshold, output_type='coo_matrix')
-
-    x_res = np.unique(x_id[pairs.row][["ch_name", 'res_num', 'res_icode', 'res_name']])
-    y_res = np.unique(y_id[pairs.col][["ch_name", 'res_num', 'res_icode', 'res_name']])
-
-    return x_res, y_res

gemmi_protools-0.1.16.dist-info/METADATA

@@ -1,29 +0,0 @@
-Metadata-Version: 2.4
-Name: gemmi_protools
-Version: 0.1.16
-Summary: An Enhanced tool to process PDB structures based on Gemmi
-Author: Luo Jiejian
-Author-email: Luo Jiejian <luojiejian12@mails.ucas.ac.cn>
-License-Expression: MIT
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: gemmi>=0.7.0
-Requires-Dist: pandas>=2.2.3
-Requires-Dist: typeguard>=4.1.2
-Requires-Dist: numpy
-Requires-Dist: biopython>=1.84
-Requires-Dist: scipy>=1.14.1
-Requires-Dist: dockq
-Requires-Dist: hmmer
-Dynamic: author
-Dynamic: license-file
-
-# An Enhanced tool to process PDB structures based on Gemmi
-
-# Install
-```commandline
-conda create -n gp python=3.10 anarci -c bioconda
-conda activate gp
-pip install gemmi_protools
-```

gemmi_protools-0.1.16.dist-info/RECORD

@@ -1,26 +0,0 @@
-gemmi_protools/__init__.py,sha256=hwUw-EieCG0kwzHjTjzHF9Bc3D-J5R_l6G8PCcFegkw,331
-gemmi_protools/data/MHC/MHC_combined.hmm,sha256=w0_vzPiEWne_d_kYmqR0OiSsCOpQioItKy3Zq-JMsH4,159451
-gemmi_protools/data/MHC/MHC_combined.hmm.h3f,sha256=QGG4l-v76RYtysJ5rybnz5v6VgJg2RjoQQHUVWL5jmg,45522
-gemmi_protools/data/MHC/MHC_combined.hmm.h3i,sha256=yn-700hoBSJB39Tj8Ia8UhSZWpYiCZFNcbnYAFNjReI,300
-gemmi_protools/data/MHC/MHC_combined.hmm.h3m,sha256=CvNMCsobQiX-wL7iB4CreNcbpnElE31NmmjmMR0iYVI,66174
-gemmi_protools/data/MHC/MHC_combined.hmm.h3p,sha256=-mK278pRedG3-KL-DtuVAQy7La9DgXg5FcP89D6X3Ck,78325
-gemmi_protools/io/__init__.py,sha256=F6e1xNT_7lZAWQgNIneH06o2qtWYrHNr_xPUPTwwx5E,29
-gemmi_protools/io/cif_opts.py,sha256=cYEhubRP2rymbwSlB3ZQPGUFQiXGb2UQ0gdXdTd3c-I,6646
-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=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=2AXg1JdYT2LxL6jWVsJkLHQREwAoYR7V-g-hQVgSgGg,16237
-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=wyJDawxW10kdYWEM1F_LUEc3Qo-3_I7P5hFk-r-yqgY,7432
-gemmi_protools/utils/dockq.py,sha256=XmMwVEy-H4p6sH_HPcDWA3TP77OWdih0fE_BQJDr4pU,4189
-gemmi_protools/utils/fixer.py,sha256=yP9pTJ67n7z56UFfe2-eEsS3jkJfG2lP4KAEpXxlrnE,10142
-gemmi_protools/utils/pdb_annot.py,sha256=nnRlLpjczhCP1ojEgsO3FuVgfsyleDZ34QxqyI8-wr0,11143
-gemmi_protools/utils/ppi.py,sha256=VWYsdxWwQoS1xwEYj5KB96Zz3F8r5Eyuw6NT3ReD-wc,2330
-gemmi_protools-0.1.16.dist-info/licenses/LICENSE,sha256=JuQvKcgj6n11y5y6nXr9rABv3gJSswc4eTCd5WZBtSY,1062
-gemmi_protools-0.1.16.dist-info/METADATA,sha256=wxrsd_ApvtPBm1rLrPjFCx8mTt3boSg4-7wlx6mJaZU,750
-gemmi_protools-0.1.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-gemmi_protools-0.1.16.dist-info/top_level.txt,sha256=P12mYJi5O5EKIn5u-RFaWxuix431CgLacSRD7rBid_U,15
-gemmi_protools-0.1.16.dist-info/RECORD,,