mlatom 3.8.0__tar.gz → 3.9.0__tar.gz

{mlatom-3.8.0/src/mlatom.egg-info → mlatom-3.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlatom
-Version: 3.8.0
+Version: 3.9.0
 Summary: A Package for Atomistic Simulations with Machine Learning
 Home-page: http://mlatom.com
 Author: Pavlo O. Dral
@@ -27,7 +27,7 @@ Requires-Dist: tqdm
 # About Program
 MLatom: a Package for Atomistic Simulations with Machine Learning
 
-Version 3.8.0
+Version 3.9.0
 
 **Official website**: http://mlatom.com/    
 **Manual**: http://mlatom.com/manual/  
@@ -60,7 +60,7 @@ When this Software or its derivatives are used in scientific publications, it sh
 * Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Mario Barbatti, Olexandr Isayev, Cheng Wang, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Lina Zhang, Shuang Zhang, Arif Ullah, Quanhao Zhang, Yanchi Ou. [MLatom 3: A Platform for Machine Learning-enhanced Computational Chemistry Simulations and Workflows](https://doi.org/10.1021/acs.jctc.3c01203).   *J. Chem. Theory Comput.* **2024**, *20*, 1193--1213.                                                                                               
 * Pavlo O. Dral, Fuchun Ge, Bao-Xin Xue, Yi-Fan Hou, Max Pinheiro Jr, Jianxing Huang, Mario Barbatti. [MLatom 2: An Integrative Platform for Atomistic Machine Learning](http://doi.org/10.1007/s41061-021-00339-5). *Top. Curr. Chem.* **2021**, *379*, 27.       
 * Pavlo O. Dral. [MLatom: A Program Package for Quantum Chemical Research Assisted by Machine Learning](http://dx.doi.org/10.1002/jcc.26004). *J. Comput. Chem.* **2019**, *40*, 2339--2347.                                                                                      
-* Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang, Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.8.0, Xiamen University, Xiamen, China, 2013-2024.
+* Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang, Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.9.0, Xiamen University, Xiamen, China, 2013-2024.
   [MLatom.com](http://mlatom.com).
                                                                       
 The citations for MLatom's interfaces and features shall be eventually

{mlatom-3.8.0 → mlatom-3.9.0}/README.md

@@ -1,7 +1,7 @@
 # About Program
 MLatom: a Package for Atomistic Simulations with Machine Learning
 
-Version 3.8.0
+Version 3.9.0
 
 **Official website**: http://mlatom.com/    
 **Manual**: http://mlatom.com/manual/  
@@ -34,7 +34,7 @@ When this Software or its derivatives are used in scientific publications, it sh
 * Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Mario Barbatti, Olexandr Isayev, Cheng Wang, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Lina Zhang, Shuang Zhang, Arif Ullah, Quanhao Zhang, Yanchi Ou. [MLatom 3: A Platform for Machine Learning-enhanced Computational Chemistry Simulations and Workflows](https://doi.org/10.1021/acs.jctc.3c01203).   *J. Chem. Theory Comput.* **2024**, *20*, 1193--1213.                                                                                               
 * Pavlo O. Dral, Fuchun Ge, Bao-Xin Xue, Yi-Fan Hou, Max Pinheiro Jr, Jianxing Huang, Mario Barbatti. [MLatom 2: An Integrative Platform for Atomistic Machine Learning](http://doi.org/10.1007/s41061-021-00339-5). *Top. Curr. Chem.* **2021**, *379*, 27.       
 * Pavlo O. Dral. [MLatom: A Program Package for Quantum Chemical Research Assisted by Machine Learning](http://dx.doi.org/10.1002/jcc.26004). *J. Comput. Chem.* **2019**, *40*, 2339--2347.                                                                                      
-* Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang, Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.8.0, Xiamen University, Xiamen, China, 2013-2024.
+* Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang, Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.9.0, Xiamen University, Xiamen, China, 2013-2024.
   [MLatom.com](http://mlatom.com).
                                                                       
 The citations for MLatom's interfaces and features shall be eventually

{mlatom-3.8.0 → mlatom-3.9.0}/setup.py

@@ -43,7 +43,7 @@ with open(os.path.join(here, 'README.md')) as f:
 
 setup(
     name = pkg_name,
-    version = "3.8.0",
+    version = "3.9.0",
     author = "Pavlo O. Dral",
     author_email = "admin@mlatom.com",
     license = 'MIT (modified)',

{mlatom-3.8.0 → mlatom-3.9.0}/src/mlatom/MLatom.py

@@ -4,7 +4,7 @@
   !---------------------------------------------------------------------------!
   !                                                                           !
   !     MLatom: a Package for Atomistic Simulations with Machine Learning     !
-  !                             MLatom 3.8.0                                  !
+  !                             MLatom 3.9.0                                  !
   !                                   @                                       !
   !                 Xiamen Atomistic Computing Suite (XACS)                   !
   !                                                                           !
@@ -36,7 +36,7 @@
   ! Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang,  !
   ! Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou,      !
   ! MLatom: A Package for Atomistic Simulations with Machine Learning,        !
-  ! version 3.8.0, Xiamen University, Xiamen, China, 2013-2024.               !
+  ! version 3.9.0, Xiamen University, Xiamen, China, 2013-2024.               !
   !                                                                           !
   ! The citations for MLatom's interfaces and features shall be eventually    !
   ! included too. See header.py, ref.json and http://mlatom.com.              !

{mlatom-3.8.0 → mlatom-3.9.0}/src/mlatom/data.py

@@ -10,7 +10,7 @@
 '''
 
 from __future__ import annotations
-from typing import Any, Union, Dict, List
+from typing import Any, Union, Dict, List, Optional, Iterable
 import uuid, copy, os, json
 import numpy as np
 from . import constants
@@ -117,16 +117,70 @@ class molecule:
         multiplicity: The multiplicity of the molecule.
            
     '''
-    def __init__(self, charge: int = 0, multiplicity: int = 1, atoms: List[atom] = None): 
+    def __init__(self, charge: int = 0, multiplicity: int = 1, atoms: List[atom] = None, pbc: Optional[Union[np.ndarray, bool]] = None, cell: Optional[np.ndarray] = None): 
         self.id = str(uuid.uuid4())
         self.charge = charge
         self.multiplicity = multiplicity
+        self.pbc = pbc
+        self.cell = cell
         if atoms is None:
             self.atoms = []
         else:
             self.atoms = atoms
         
         self.electronic_states = []
+    
+    @property
+    def pbc(self):
+        '''
+        The periodic boundary conditions of the molecule. Setting it with ``mol.pbc = True`` is equal to ``mol.pbc = [True, True, True]``.
+        '''
+        return self._pbc
+    
+    @pbc.setter
+    def pbc(self, pbc):
+        if pbc is not None:
+            if isinstance(pbc, bool):
+                pbc = [pbc] * 3
+            pbc = np.array(pbc, bool)
+            assert pbc.shape == (3,), 'please provide a valid pbc'
+        self._pbc = pbc
+    
+    @property
+    def cell(self):
+        '''
+        The matrix of 3 vectors that defines the unicell. The setter of it simply wraps `ase.geometry.cell.cellpar_to_cell() <https://wiki.fysik.dtu.dk/ase/ase/geometry.html#ase.geometry.cellpar_to_cell>`_.
+        '''
+        return self._cell
+    
+    @cell.setter
+    def cell(self, cell):
+        # reinvent the wheel with premade spokes from ASE
+        if cell is not None:
+            from ase.geometry.cell import cellpar_to_cell 
+            cell = cellpar_to_cell(cell)
+        self._cell = cell
+        
+    @property 
+    def cell_coordinates(self) -> np.ndarray:
+        '''
+        The relative coordinates in the cell.
+        '''
+        assert self.cell is not None, 'make sure this molecule has a valid cell'
+        inverse_cell = np.linalg.inv(self.cell)
+        return self.xyz_coordinates @ inverse_cell
+        
+    @cell_coordinates.setter
+    def cell_coordinates(self, value):
+        assert self.cell is not None, 'make sure this molecule has a valid cell'
+        self.xyz_coordinates = value @ self.cell
+            
+    def map_to_unicell(self):
+        '''
+        Map all atoms outside the unicell into it.
+        '''
+        self.cell_coordinates -= np.floor(self.cell_coordinates) * self.pbc
+        
 
     def read_from_xyz_file(self, filename: str, format: Union[str, None] = None) -> molecule:
         '''
@@ -509,6 +563,108 @@ class molecule:
         new_molecule.id = str(uuid.uuid4())
         return new_molecule
     
+    def proliferate(
+            self, 
+            shifts: Optional[Iterable] = None, 
+            XYZshifts: Optional[Iterable] = None, 
+            Xshifts: Optional[Iterable] = [0], 
+            Yshifts: Optional[Iterable] = [0], 
+            Zshifts: Optional[Iterable] = [0],
+            PBC_constrained: bool = True,
+        ) -> molecule: 
+        '''
+        Proliferate the unicell by specified shifts along cell vectors (called X/Y/Z here). 
+        
+        Returns a new :class:`molecule` object.
+        
+        Arguments:
+            shifts (Iterable, optional): The list of shifts to perform. Each shift should be a 3D vector that indicates the coefficient applies to the corresponding cell vector.
+            XYZshifts (Iterable, optional): Generate all possible shifts with given shift coefficients in all three directions when a list is specified. When a list of 3 lists is specified, it's equal to setting X/Y/Zshifts
+            Xshifts (Iterable, optional): Specify all possible shift coefficients in the direction of the first cell vector.
+            Yshifts (Iterable, optional): Specify all possible shift coefficients in the direction of the second cell vector.
+            Zshifts (Iterable, optional): Specify all possible shift coefficients in the direction of the third cell vector.
+            PBC_constrained (bool): Controls whether the shifts in some directions are disabled where corresponding PBC is false. Only applies to XYZshifts.
+            
+        .. note::
+            
+           Priorities for different types of shifts:
+                ``shifts`` > ``XYZshifts`` > ``X/Y/Zshifts`` 
+        
+        Examples:
+
+            Single H atom in the centre of a cubic cell (2x2x2):
+
+            .. code-block:: python
+                
+                mol = ml.molecule.from_numpy(np.ones((1, 3)), np.array([1])) 
+                mol.pbc = True 
+                mol.cell = 2 
+            
+            Proliferate to get two periods in all three directions,
+            with shifts:
+
+            .. code-block:: python
+                
+                new_mol = mol.proliferate(
+                    shifts = [
+                        [0, 0, 0],
+                        [1, 0, 0],
+                        [0, 1, 0],
+                        [0, 0, 1],
+                        [1, 1, 0],
+                        [1, 0, 1],
+                        [0, 1, 1],
+                        [1, 1, 1],
+                    ]
+                )
+            
+            with XYZshifts:
+
+            .. code-block:: python
+                
+                new_mol = mol.proliferate(XYZshifts=range(2))
+                # or
+                new_mol = mol.proliferate(XYZshifts=[range(2)]*3)
+                
+                
+            with X/Y/Zshifts:
+
+            .. code-block:: python
+                
+                new_mol = mol.proliferate(Xshifts=range(2), Yshifts=(0, 1), Zshifts=[0, 1]))
+            
+            All scripts above will make ``new_mol.xyz_coordinates`` be:
+            
+            .. code-block:: python
+            
+                array([[1., 1., 1.],
+                       [3., 1., 1.],
+                       [1., 3., 1.],
+                       [3., 3., 1.],
+                       [1., 1., 3.],
+                       [3., 1., 3.],
+                       [1., 3., 3.],
+                       [3., 3., 3.]])
+                
+        '''
+        if shifts is None:
+            if XYZshifts is not None:
+                XYZshifts = np.array(XYZshifts)
+                if XYZshifts.ndim == 1:
+                    XYZshifts = np.repeat(XYZshifts[np.newaxis], 3, 0)
+                assert XYZshifts.ndim ==2, 'provide valid XYZshifts'
+                Xshifts, Yshifts, Zshifts = XYZshifts
+                if PBC_constrained:
+                    Xshifts = Xshifts if self.pbc[0] else [0]
+                    Yshifts = Yshifts if self.pbc[1] else [0]
+                    Zshifts = Zshifts if self.pbc[2] else [0]
+            shifts = [np.array([i, j, k]) for k in Zshifts for j in Yshifts  for i in Xshifts]
+            
+        xyzs = []
+        for shift in shifts:
+            xyzs.append(self.xyz_coordinates + shift @ self.cell)
+        return self.from_numpy(np.concatenate(xyzs, 0), np.repeat(self.atomic_numbers, len(shifts)))
+    
     def dump(self, filename=None, format='json'):
         '''
         Dump the current molecule object into a file. Only in json format, which is supported now.
@@ -1188,6 +1344,16 @@ class molecular_database:
     def filter_by_property(self, property_name):
         return molecular_database(self[~np.isnan(self.get_properties(property_name))])
     
+    def proliferate(self, *args, **kwargs) -> molecular_database:
+        '''
+        Proliferate the unicell by specified shifts along cell vectors.
+        
+        Returns a new :class:`molecular_databse` object.
+        
+        Check :meth:`molecule.proliferate` for details on options.
+        '''
+        return molecular_database([mol.proliferate(*args, **kwargs) for mol in self])
+    
     def dump(self, filename=None, format=None):
         '''
         Dump the molecular database to a file.
@@ -1280,6 +1446,19 @@ class molecular_database:
     def xyz_coordinates(self, value):
         for i, mol in enumerate(self):
             mol.xyz_coordinates = value[i]
+            
+    def _is_uniform_cell(self):
+        cells = self.get_properties('cell')
+        pbcs = self.get_properties('pbc')
+        try:
+            if set(cells) == {None} and set(pbcs) == {None}:
+                return True
+        except:
+            try:
+                if np.max(np.std(cells, 0)) == 0 and np.max(np.std(pbcs, 0)):
+                    return True
+            except:
+                return False
 
 def class_instance_to_dict(inst):
     dd = copy.deepcopy(inst.__dict__)
@@ -1578,6 +1757,12 @@ class molecular_trajectory():
         for istep in self.steps:
             xyz_string += istep.molecule.get_xyz_string()
         return xyz_string
+    
+    def to_database(self) -> molecular_database:
+        '''
+        Return a molecular database that formed by the molecules in the trajectory.
+        '''
+        return molecular_database([step.molecule for step in self.steps])
 
 class molecular_trajectory_step(object):
     def __init__(self, step=None, molecule=None):

{mlatom-3.8.0 → mlatom-3.9.0}/src/mlatom/functionsGICnet.py

@@ -1,4 +1,4 @@
-import tensorflow as tf
+
 import numpy as np
 import scipy 
 import os
@@ -6,6 +6,14 @@ import sys
 import rmsd
 from multiprocessing import Manager, Pool, Process
 
+if 'TFPATH' in os.environ:
+    import importlib
+    sys.path.insert(0, os.environ['TFPATH'])
+    import tensorflow as tf
+    sys.path.pop(0)
+else:
+    import tensorflow as tf
+    
 refTrio=np.array([[0.,0.,1.],[0.,1.,0.],[1.,0.,0.]],dtype=np.float32)
 refTrioV=np.zeros((3,3),dtype=np.float32)
     

{mlatom-3.8.0 → mlatom-3.9.0}/src/mlatom/initial_conditions.py

@@ -187,7 +187,7 @@ def generate_initial_conditions(molecule=None, generation_method=None, number_of
             init_cond_db.add_xyz_vectorial_properties_from_file(file_with_initial_xyz_velocities, xyz_vectorial_property='xyz_velocities')
         elif generation_method.casefold() == 'random'.casefold():
             for irepeat in range(number_of_initial_conditions):
-                new_molecule = molecule.copy(atomic_labels = ['xyz_coordinates'], molecular_labels = [])
+                new_molecule = molecule.copy()
                 velocities = generate_random_velocities(new_molecule,eliminate_angular_momentum,degrees_of_freedom,temp=initial_temperature,ekin=initial_kinetic_energy)
                 for iatom in range(Natoms):
                     new_molecule.atoms[iatom].xyz_velocities = velocities[iatom]

{mlatom-3.8.0 → mlatom-3.9.0}/src/mlatom/interfaces/torchani_interface.py

@@ -434,12 +434,20 @@ class ani(models.ml_model, models.torchani_model):
         molDB, property_to_predict, xyz_derivative_property_to_predict, hessian_to_predict = \
             super().predict(molecular_database=molecular_database, molecule=molecule, calculate_energy=calculate_energy, calculate_energy_gradients=calculate_energy_gradients, calculate_hessian=calculate_hessian, property_to_predict = property_to_predict, xyz_derivative_property_to_predict = xyz_derivative_property_to_predict, hessian_to_predict = hessian_to_predict)
         
+        if not molDB._is_uniform_cell():
+            batch_size = 1
+        
         for batch in molDB.batches(batch_size):
             for properties in molDB2ANIdata(batch).species_to_indices(self.species_order).collate(batch_size):
                 species = properties['species'].to(self.device)
-                xyz_coordinates = properties['coordinates'].float().to(self.device).requires_grad_(bool(xyz_derivative_property_to_predict or hessian_to_predict))
+                xyz_coordinates = properties['coordinates'].float().to(self.device)
                 break
-            ANI_NN_energies = self.energy_shifter(self.model((species, xyz_coordinates))).energies
+            pbc = torch.tensor(batch[0].pbc).to(self.device) if batch[0].pbc is not None else None
+            cell = torch.tensor(batch[0].cell).float().to(self.device) if batch[0].cell is not None else None
+            if pbc is not None and cell is not None:
+                xyz_coordinates = torchani.utils.map2central(cell, xyz_coordinates, pbc)
+            xyz_coordinates = xyz_coordinates.requires_grad_(bool(xyz_derivative_property_to_predict or hessian_to_predict))
+            ANI_NN_energies = self.energy_shifter(self.model((species, xyz_coordinates), pbc=pbc, cell=cell)).energies
             if property_to_predict: 
                 batch.add_scalar_properties(ANI_NN_energies.detach().cpu().numpy(), property_to_predict)
             if xyz_derivative_property_to_predict or hessian_to_predict:
@@ -665,14 +673,23 @@ class ani_child(models.torchani_model):
         ) -> None:
         molDB = super().predict(molecular_database=molecular_database, molecule=molecule)
 
+        if not molDB._is_uniform_cell():
+            batch_size = 1
+
         for batch in molDB.batches(batch_size):
             for properties in molDB2ANIdata(batch).species_to_indices('periodic_table').collate(batch_size):
                 species = properties['species'].to(self.device)
                 if torchani.utils.PERIODIC_TABLE[0] == 'H':
                     species += 1
-                xyz_coordinates = properties['coordinates'].to(self.device).float().to(self.device).requires_grad_(calculate_energy_gradients or calculate_hessian)
+                xyz_coordinates = properties['coordinates'].float().to(self.device)
                 break
-            ANI_NN_energies = self.model((species, xyz_coordinates)).energies
+            pbc = torch.tensor(batch[0].pbc).to(self.device) if batch[0].pbc is not None else None
+            cell = torch.tensor(batch[0].cell).float().to(self.device) if batch[0].cell is not None else None
+            if pbc is not None and cell is not None:
+                xyz_coordinates = torchani.utils.map2central(cell, xyz_coordinates, pbc)
+            xyz_coordinates = xyz_coordinates.requires_grad_(calculate_energy_gradients or calculate_hessian)
+            
+            ANI_NN_energies = self.model((species, xyz_coordinates), pbc=pbc, cell=cell).energies
             if calculate_energy: 
                 batch.add_scalar_properties(ANI_NN_energies.detach().cpu().numpy(), 'energy')
             if calculate_energy_gradients or calculate_hessian:

{mlatom-3.8.0 → mlatom-3.9.0}/src/mlatom/simulations.py

@@ -110,10 +110,10 @@ class optimize_geometry():
             raise ValueError('molecule and initial_molecule cannot be used at the same time')
         overwrite = False
         if not initial_molecule is None:
-            self.initial_molecule = initial_molecule.copy(atomic_labels=['xyz_coordinates'],molecular_labels=['number'])
+            self.initial_molecule = initial_molecule.copy()
         if not molecule is None:
             overwrite = True
-            self.initial_molecule = molecule.copy(atomic_labels=['xyz_coordinates'],molecular_labels=['number'])
+            self.initial_molecule = molecule.copy()
         
         self.ts = ts
         if program != None:

{mlatom-3.8.0 → mlatom-3.9.0/src/mlatom.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlatom
-Version: 3.8.0
+Version: 3.9.0
 Summary: A Package for Atomistic Simulations with Machine Learning
 Home-page: http://mlatom.com
 Author: Pavlo O. Dral
@@ -27,7 +27,7 @@ Requires-Dist: tqdm
 # About Program
 MLatom: a Package for Atomistic Simulations with Machine Learning
 
-Version 3.8.0
+Version 3.9.0
 
 **Official website**: http://mlatom.com/    
 **Manual**: http://mlatom.com/manual/  
@@ -60,7 +60,7 @@ When this Software or its derivatives are used in scientific publications, it sh
 * Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Mario Barbatti, Olexandr Isayev, Cheng Wang, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Lina Zhang, Shuang Zhang, Arif Ullah, Quanhao Zhang, Yanchi Ou. [MLatom 3: A Platform for Machine Learning-enhanced Computational Chemistry Simulations and Workflows](https://doi.org/10.1021/acs.jctc.3c01203).   *J. Chem. Theory Comput.* **2024**, *20*, 1193--1213.                                                                                               
 * Pavlo O. Dral, Fuchun Ge, Bao-Xin Xue, Yi-Fan Hou, Max Pinheiro Jr, Jianxing Huang, Mario Barbatti. [MLatom 2: An Integrative Platform for Atomistic Machine Learning](http://doi.org/10.1007/s41061-021-00339-5). *Top. Curr. Chem.* **2021**, *379*, 27.       
 * Pavlo O. Dral. [MLatom: A Program Package for Quantum Chemical Research Assisted by Machine Learning](http://dx.doi.org/10.1002/jcc.26004). *J. Comput. Chem.* **2019**, *40*, 2339--2347.                                                                                      
-* Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang, Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.8.0, Xiamen University, Xiamen, China, 2013-2024.
+* Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Shuang Zhang, Lina Zhang, Arif Ullah, Quanhao Zhang, Sebastian V. Pios, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.9.0, Xiamen University, Xiamen, China, 2013-2024.
   [MLatom.com](http://mlatom.com).
                                                                       
 The citations for MLatom's interfaces and features shall be eventually