rdworks 0.25.7__py3-none-any.whl → 0.35.1__py3-none-any.whl

rdworks/xtb/wrapper.py

@@ -0,0 +1,304 @@
+import os
+import resource
+import subprocess
+import json
+import tempfile
+import logging
+
+from pathlib import Path
+from types import SimpleNamespace
+
+from rdkit import Chem
+from rdkit.Geometry import Point3D
+
+
+main_logger = logging.getLogger()
+
+# In ASE, the default energy unit is eV (electron volt).
+# It will be converted to kcal/mol
+# CODATA 2018 energy conversion factor
+hartree2ev = 27.211386245988
+hartree2kcalpermol = 627.50947337481
+ev2kcalpermol = 23.060547830619026
+
+
+class GFN2xTB:
+    def __init__(self, molecule: Chem.Mol | None = None, ncores: int = 4):
+        if isinstance(molecule, Chem.Mol):
+            assert molecule.GetConformer().Is3D(), "requires 3D coordinates"
+            self.rdmol = molecule
+            self.natoms = molecule.GetNumAtoms()
+            self.symbols = [ atom.GetSymbol() for atom in molecule.GetAtoms() ]
+            self.positions = molecule.GetConformer().GetPositions().tolist()
+
+        # Parallelisation
+        os.environ['OMP_STACKSIZE'] = '4G'
+        os.environ['OMP_NUM_THREADS'] = f'{ncores},1'
+        os.environ['OMP_MAX_ACTIVE_LEVELS'] = '1'
+        os.environ['MKL_NUM_THREADS'] = f'{ncores}'
+        
+        # unlimit the system stack
+        resource.setrlimit(resource.RLIMIT_STACK, (resource.RLIM_INFINITY, resource.RLIM_INFINITY))
+
+
+    def version(self) -> str | None:
+        """Check xtb version.
+
+        Returns:
+            str | None: version statement.
+        """
+        cmd = ['xtb', '--version']
+        proc = subprocess.run(cmd, capture_output=True, text=True)
+        assert proc.returncode == 0, "GFN2xTB() Error: xtb not available"
+        for line in proc.stdout.split('\n'):
+            line = line.strip()
+            if 'version' in line:
+                return line
+        
+        return None
+
+
+    def to_xyz(self) -> str:
+        """Export to XYZ formatted string.
+
+        Returns:
+            str: XYZ formatted string
+        """
+        lines = [f'{self.natoms}', ' ']
+        for e, (x, y, z) in zip(self.symbols, self.positions):
+            lines.append(f'{e:5} {x:23.14f} {y:23.14f} {z:23.14f}')
+        
+        return '\n'.join(lines)
+
+
+    def load_xyz(self, geometry_path: Path) -> Chem.Mol:
+        """Load geometry.
+
+        Args:
+            geometry_path (Path): pathlib.Path to the xyz 
+
+        Returns:
+            Chem.Mol: rdkit Chem.Mol object.
+        """
+        rdmol_opt = Chem.Mol(self.rdmol)
+        with open(geometry_path, 'r') as f:
+            for lineno, line in enumerate(f):
+                if lineno == 0:
+                    assert int(line.strip()) == self.natoms
+                    continue
+                elif lineno == 1: # comment or title
+                    continue
+                (symbol, x, y, z) = line.strip().split()
+                x, y, z = float(x), float(y), float(z)
+                atom = rdmol_opt.GetAtomWithIdx(lineno-2)
+                assert symbol == atom.GetSymbol()
+                rdmol_opt.GetConformer().SetAtomPosition(atom.GetIdx(), Point3D(x, y, z))
+        
+        return rdmol_opt
+
+
+    def load_wbo(self, wbo_path: Path) -> dict[tuple[int, int], float]:
+        """Load Wiberg bond order.
+
+        Args:
+            wbo_path (Path): path to the wbo file.
+
+        Returns:
+            dict(tuple[int, int], float): { (i, j) : wbo, ... } where i and j are atom indices for a bond.
+        """
+
+        with open(wbo_path, 'r') as f:
+            # Wiberg bond order (WBO)
+            Wiberg_bond_orders = {}
+            for line in f:
+                line = line.strip()
+                if line:
+                    # wbo output has 1-based indices
+                    (i, j, wbo) = line.split()
+                    # changes to 0-based indices
+                    i = int(i) - 1
+                    j = int(j) - 1
+                    # wbo ouput indices are ascending order
+                    ij = (i, j) if i < j else (j, i)
+                    Wiberg_bond_orders[ij] = float(wbo)
+
+            return Wiberg_bond_orders
+
+
+    def singlepoint(self, water: str | None = None, verbose: bool = False) -> SimpleNamespace:
+        """Calculate single point energy.
+        
+        Total energy from xtb output in atomic units (Eh, hartree) is converted to kcal/mol.
+
+        Args:
+            water (str, optional) : water solvation model (choose 'gbsa' or 'alpb')
+                alpb: ALPB solvation model (Analytical Linearized Poisson-Boltzmann).
+                gbsa: generalized Born (GB) model with Surface Area contributions.
+
+        Returns:
+            SimpleNamespace(PE(total energy in kcal/mol), charges, wbo) 
+        """
+
+        with tempfile.TemporaryDirectory() as temp_dir: # tmpdir is a string
+            workdir = Path(temp_dir)
+            if verbose:
+                main_logger.info(f'xtb.singlepoint workdir= {temp_dir}')
+            
+            geometry_path = workdir / 'geometry.xyz'
+            xtbout_path = workdir / 'xtbout.json'
+            wbo_path = workdir / 'wbo'
+            
+            with open(geometry_path, 'w') as geometry:
+                geometry.write(self.to_xyz())
+            
+            cmd = ['xtb', geometry_path.as_posix()]
+            
+            options = ['--gfn', '2', '--json']
+            
+            if water is not None and isinstance(water, str):
+                if water == 'gbsa':
+                    options += ['--gbsa', 'H2O']
+                elif water == 'alpb':
+                    options += ['--alpb', 'water']
+            
+            # 'xtbout.json', 'xtbrestart', 'xtbtopo.mol', 'charges', and 'wbo' files will be 
+            # created in the current working directory.
+            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True)
+
+            # if proc.returncode == 0:
+            #     print("Standard Output:")
+            #     print(proc.stdout)
+            # else:
+            #     print("Error:")
+            #     print(proc.stderr)
+            
+            if proc.returncode == 0 and xtbout_path.is_file():
+                with open(xtbout_path, 'r') as f:
+                    datadict = json.load(f) # takes the file object as input
+
+                Wiberg_bond_orders = self.load_wbo(wbo_path)
+
+                return SimpleNamespace(
+                    PE = datadict['total energy'] * hartree2kcalpermol, 
+                    charges = datadict['partial charges'], 
+                    wbo = Wiberg_bond_orders, 
+                    ) 
+        
+        # something went wrong if it reaches here          
+        return SimpleNamespace()
+                        
+
+
+    def optimize(self, water: str | None = None, verbose: bool = False) -> SimpleNamespace:
+        """Optimize geometry.
+
+        Fortran runtime errror:
+            At line 852 of file ../src/optimizer.f90 (unit = 6, file = 'stdout')
+            Fortran runtime error: Missing comma between descriptors
+            (1x,"("f7.2"%)")
+                        ^
+            Error termination.
+
+        Args:
+            water (str, optional) : water solvation model (choose 'gbsa' or 'alpb')
+                alpb: ALPB solvation model (Analytical Linearized Poisson-Boltzmann).
+                gbsa: generalized Born (GB) model with Surface Area contributions.
+
+        Returns:
+            (total energy in kcal/mol, optimized geometry)
+        """
+        with tempfile.TemporaryDirectory() as temp_dir: # tmpdir is a string
+            workdir = Path(temp_dir)
+            if verbose:
+                main_logger.info(f'xtb.optimize workdir= {temp_dir}')
+            
+            geometry_path = workdir / 'geometry.xyz'
+            xtbout_path = workdir / 'xtbout.json'
+            xtbopt_path = workdir / 'xtbopt.xyz'
+            wbo_path = workdir / 'wbo'
+            
+            with open(geometry_path, 'w') as geometry:
+                geometry.write(self.to_xyz())
+
+            cmd = ['xtb', geometry_path.as_posix()]
+
+            options = ['--opt', '--gfn', '2', '--json']
+
+            if water is not None and isinstance(water, str):
+                if water == 'gbsa':
+                    options += ['--gbsa', 'H2O']
+                elif water == 'alpb':
+                    options += ['--alpb', 'water']
+
+            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True)
+
+            if proc.returncode == 0 and xtbout_path.is_file():
+                with open(xtbout_path, 'r') as f:
+                    datadict = json.load(f) # takes the file object as input
+                
+                Wiberg_bond_orders = self.load_wbo(wbo_path)
+                rdmol_opt = self.load_xyz(xtbopt_path)
+            
+                return SimpleNamespace(
+                        PE = datadict['total energy'] * hartree2kcalpermol,
+                        charges = datadict['partial charges'],
+                        wbo = Wiberg_bond_orders,
+                        geometry = rdmol_opt,
+                )
+
+        # something went wrong if it reaches here
+        return SimpleNamespace()
+    
+
+    def esp(self, water: str | None = None, verbose: bool = False) -> None:
+        """Calculate electrostatic potential
+        
+        Example:
+            v = py3Dmol.view()
+            v.addVolumetricData(dt,
+                                "cube.gz", {
+                                    'isoval': 0.005,
+                                    'smoothness': 2,
+                                    'opacity':.9,
+                                    'voldata': esp,
+                                    'volformat': 'cube.gz',
+                                    'volscheme': {
+                                        'gradient':'rwb',
+                                        'min':-.1,
+                                        'max':.1,
+                                        }
+                                    });
+            v.addModel(dt,'cube')
+            v.setStyle({'stick':{}})
+            v.zoomTo()
+            v.show()
+        """
+        with tempfile.TemporaryDirectory() as temp_dir: # tmpdir is a string
+            workdir = Path(temp_dir)
+            if verbose:
+                main_logger.info(f'xtb.optimize workdir= {temp_dir}')
+            
+            geometry_path = workdir / 'geometry.xyz'
+            xtb_esp_dat = workdir / 'xtb_esp_dat'
+
+            with open(geometry_path, 'w') as geometry:
+                geometry.write(self.to_xyz())
+
+            cmd = ['xtb', geometry_path.as_posix()]
+
+            options = ['--esp', '--gfn', '2']
+
+            if water is not None and isinstance(water, str):
+                if water == 'gbsa':
+                    options += ['--gbsa', 'H2O']
+                elif water == 'alpb':
+                    options += ['--alpb', 'water']
+
+            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True)
+            # output files: xtb_esp.cosmo, xtb_esp.dat, xtb_esp_profile.dat
+
+            if proc.returncode == 0 and xtb_esp_dat.is_file():
+                with open(xtb_esp_dat, 'r') as f:
+                    pass
+        
+        return None

{rdworks-0.25.7.dist-info → rdworks-0.35.1.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.25.7
-Summary: Cheminformatics and AI/ML Work Built on RDKit
+Version: 0.35.1
+Summary: Frequently used tasks built on RDKit and other tools
 Author-email: Sung-Hun Bae <sunghun.bae@gmail.com>
 Maintainer-email: Sung-Hun Bae <sunghun.bae@gmail.com>
 License-Expression: MIT
@@ -10,7 +10,7 @@ Project-URL: Repository, https://github.com/sunghunbae/rdworks.git
 Project-URL: Issues, https://github.com/sunghunbae/rdworks/issues
 Project-URL: Changelog, https://github.com/sunghunbae/rdworks/blob/master/CHANGELOG.md
 Project-URL: Documentation, https://sunghunbae.github.io/rdworks/
-Keywords: neural-network-potential,cheminformatics,rdkit
+Keywords: cheminformatics,rdkit
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python :: 3
@@ -18,18 +18,15 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy
-Requires-Dist: scipy
-Requires-Dist: scikit-learn
+Requires-Dist: rdkit>=2024
+Requires-Dist: cdpkit
 Requires-Dist: pandas
 Requires-Dist: seaborn
-Requires-Dist: networkx
 Requires-Dist: tqdm
-Requires-Dist: psutil
 Requires-Dist: ase
-Requires-Dist: rdkit>=2023
+Requires-Dist: mendeleev
+Requires-Dist: scour
 Requires-Dist: bitarray
-Requires-Dist: cdpkit
 Requires-Dist: pytest
 Dynamic: license-file
 

{rdworks-0.25.7.dist-info → rdworks-0.35.1.dist-info}/RECORD

@@ -1,20 +1,21 @@
-rdworks/__init__.py,sha256=dZaI7Hby8O_6cqWwxH9ea5_w5sLsHo3AVgUff8uXEzU,1561
-rdworks/conf.py,sha256=c7BFSZ_WhlqJJjtqca2yS7c8OdWUz1XZwR4n3CewqB8,14563
+rdworks/__init__.py,sha256=UPZKHw1RajTvab15-wzdsP4UjD27yQT0n6Q5waUaJQE,1368
+rdworks/conf.py,sha256=BPp_uZAXXOU53tKzjZz8SsUdAvi7aK1s_zCeHfiRATk,21744
 rdworks/descriptor.py,sha256=34T_dQ6g8v3u-ym8TLKbQtxIIV5TEo-d3pdedq3o-cg,2106
-rdworks/display.py,sha256=_OSARhvAPL9MZq4MHzNWS3eU3FiOThVGHhhB2PUEuZE,6736
+rdworks/display.py,sha256=JR0gR26UpH-JCxVOaqXZCUj2MiGZSrx9Me87FncspVI,13469
 rdworks/ionized.py,sha256=5oIjMRpkX792RIpEEE2Ir96icfFaN_h21mSihhfQPAw,6713
 rdworks/matchedseries.py,sha256=A3ON4CUpQV159mu9VqgNiJ8uoQ9ePOry9d3ra4NCAgc,10377
-rdworks/mol.py,sha256=aeTMesuG6QbyOR71gWRhoBp_1A7EdrKDzDCBfXLqtZ8,64965
-rdworks/mollibr.py,sha256=o3O1-Fz4J9QpCT15n7h-MygBFKNP-P3v8jEni36itCM,33553
+rdworks/mol.py,sha256=5ZaBIpCnKIqxbIZM0IAJ2uG5fEIlZotw1Lb2QT_IXe0,71145
+rdworks/mollibr.py,sha256=X4UBO6Ga-QmNS7RwUiaDYAx0Q5hnWs71yTkEpH02Qb4,37696
 rdworks/pka.py,sha256=NVJVfpcNEMlX5QRyLBgUM7GIT7VMjO-llAR4LWc8J2c,1656
-rdworks/readin.py,sha256=7j0r0U6BifZCAQ74Z5fFqmiq25mYClnenii0CtBCINI,11805
+rdworks/readin.py,sha256=0bnVcZcAmSLqc6zu1mYcv0LdBv2agQfOpKGwpSRL9VE,11742
 rdworks/rgroup.py,sha256=ivF2gzmRtt339rxEnkv2KfnCs0CUdBbnSje7Y54rtFI,57996
-rdworks/scaffold.py,sha256=LTazmJ5uydUZSo-i4XDowGO7Bvx3M9H1Ke-XfS5UP94,22023
-rdworks/std.py,sha256=0EIrI_49npO0-XlJiMYuBo_SIhqzj8qD8YijunfWJXE,6096
+rdworks/scaffold.py,sha256=60T5YacyxZsEpDo_J5Qxulm2YNQO4EQR8PcNUwjn1QU,22026
+rdworks/std.py,sha256=p-Ha8uJla_6bDLkf-zvdsCeXqrV8jJTLYiV6IkSW9FE,7147
 rdworks/stereoisomers.py,sha256=g8hhPI-mbYX-MzbF1uAqo5fDZOCNiKYjxI-kLBGdGgg,4980
 rdworks/tautomers.py,sha256=gtZHZJ-aJbryhBdljHbfjx7xhVW3u_OzdYPtwPail54,610
-rdworks/units.py,sha256=2bkig_WyjkmdgCQIKL96VZwBAinFlIXDvJaEAaYEjAk,4240
-rdworks/utils.py,sha256=puIMK41sry8FKGQ9-RrlqSYUQhiMtaE18C1HIZsVHlI,16794
+rdworks/torsion.py,sha256=Y0QOi5JEc7-0YpJ7b0rzA1UuuJxymzjm9Ap-9u8udfg,18429
+rdworks/units.py,sha256=nljKPHcr6IWoAp0CkL7y1gSNDd6a07NeVfxXwSMuHQM,365
+rdworks/utils.py,sha256=IxgFniUvjXlJuNJ1Sx9hsJknNNSglP6qzFyz8vdgDcw,13406
 rdworks/xml.py,sha256=aaMhwVRGvt1VzasaKDnkYnZ4kp2cIgvGb1CsmMgwQ_c,10704
 rdworks/autograph/__init__.py,sha256=0Qfjwo0h4Q0n08zsqHRbuNOZms6MuNXnWErnQpQ6Px0,140
 rdworks/autograph/autograph.py,sha256=frjsUaCTOD-Z1lYPzOxRoTtqMMiYroWAy6tSwKn3CUA,8769
@@ -62,8 +63,10 @@ rdworks/predefined/misc/makexml.py,sha256=T9c6ssKYdDzMkkcaCjEUe59nVPJfwJEoHm6Rhk
 rdworks/predefined/misc/reactive-part-2.xml,sha256=0vNTMwWrrQmxBpbgbyRHx8sVs83cqn7xsfr5qqrelRA,3676
 rdworks/predefined/misc/reactive-part-3.xml,sha256=LgWHSEbRTVmgBoIO45xbTo1xQJs0Xu51j3JnIapRYo4,3094
 rdworks/predefined/misc/reactive.xml,sha256=syedoQ6VYUfRLnxy99ObuDniJ_a_WhrWAJbTKFfJ6VY,11248
-rdworks-0.25.7.dist-info/licenses/LICENSE,sha256=UOkJSBqYyQUvtCp7a-vdCANeEcLE2dnTie_eB1By5SY,1074
-rdworks-0.25.7.dist-info/METADATA,sha256=MPPTPV31tli5A7BDNvxgk6v8Zc-E_et8eIrP22C7gkU,1271
-rdworks-0.25.7.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
-rdworks-0.25.7.dist-info/top_level.txt,sha256=05C98HbvBK2axUBogC_hAT_CdpOeQYGnQ6vRAgawr8s,8
-rdworks-0.25.7.dist-info/RECORD,,
+rdworks/xtb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+rdworks/xtb/wrapper.py,sha256=I0nW89vlJZ5Za5pCjIpjsEOFbTm7HpeNGiPgssheWn8,11350
+rdworks-0.35.1.dist-info/licenses/LICENSE,sha256=UOkJSBqYyQUvtCp7a-vdCANeEcLE2dnTie_eB1By5SY,1074
+rdworks-0.35.1.dist-info/METADATA,sha256=cmN6_DkuVc8s0zE1LClwGTv2RGbwP6lrVxPOt2hST5k,1183
+rdworks-0.35.1.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+rdworks-0.35.1.dist-info/top_level.txt,sha256=05C98HbvBK2axUBogC_hAT_CdpOeQYGnQ6vRAgawr8s,8
+rdworks-0.35.1.dist-info/RECORD,,

{rdworks-0.25.7.dist-info → rdworks-0.35.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.0)
+Generator: setuptools (80.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any