mlatom 3.2.0__tar.gz → 3.4.0__tar.gz

{mlatom-3.2.0/src/mlatom.egg-info → mlatom-3.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlatom
-Version: 3.2.0
+Version: 3.4.0
 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 3.2.0
+Version 3.4.0
 
 **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, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.2.0, 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 3.4.0, Xiamen University, Xiamen, China, 2013-2024.
   [MLatom.com](http://mlatom.com).
                                                                       
 The citations for MLatom's interfaces and features shall be eventually
@@ -109,7 +109,7 @@ Citations mentioned above should be included. For convenience, below we provide
     }
 
     @misc{MLatomProg,
-    author = {Dral, Pavlo O. and Ge, Fuchun and Hou, Yi-Fan and Zheng, Peikun and Chen, Yuxinxin and Xue, Bao-Xin and Pinheiro Jr, Max and Su, Yuming and Dai, Yiheng and Chen, Yangtao and Zhang, Shuang and Zhang, Lina and Ullah, Arif and Zhang, Quanhao and Ou, Yanchi},
+    author = {Dral, Pavlo O. and Ge, Fuchun and Hou, Yi-Fan and Zheng, Peikun and Chen, Yuxinxin and Xue, Bao-Xin and Pinheiro Jr, Max and Su, Yuming and Dai, Yiheng and Chen, Yangtao and Zhang, Shuang and Zhang, Lina and Ullah, Arif and Zhang, Quanhao and Pios, Sebastian V. and Ou, Yanchi},
     title = {MLatom: A Package for Atomistic Simulations with Machine Learning},
     year = {2013--2024},
     type = {Computer Program}

{mlatom-3.2.0 → mlatom-3.4.0}/README.md

@@ -1,7 +1,7 @@
 # About Program
 MLatom: a Package for Atomistic Simulations with Machine Learning
 
-Version 3.2.0
+Version 3.4.0
 
 **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, Yanchi Ou, MLatom: A Package for Atomistic Simulations with Machine Learning,  version 3.2.0, 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 3.4.0, Xiamen University, Xiamen, China, 2013-2024.
   [MLatom.com](http://mlatom.com).
                                                                       
 The citations for MLatom's interfaces and features shall be eventually
@@ -83,7 +83,7 @@ Citations mentioned above should be included. For convenience, below we provide
     }
 
     @misc{MLatomProg,
-    author = {Dral, Pavlo O. and Ge, Fuchun and Hou, Yi-Fan and Zheng, Peikun and Chen, Yuxinxin and Xue, Bao-Xin and Pinheiro Jr, Max and Su, Yuming and Dai, Yiheng and Chen, Yangtao and Zhang, Shuang and Zhang, Lina and Ullah, Arif and Zhang, Quanhao and Ou, Yanchi},
+    author = {Dral, Pavlo O. and Ge, Fuchun and Hou, Yi-Fan and Zheng, Peikun and Chen, Yuxinxin and Xue, Bao-Xin and Pinheiro Jr, Max and Su, Yuming and Dai, Yiheng and Chen, Yangtao and Zhang, Shuang and Zhang, Lina and Ullah, Arif and Zhang, Quanhao and Pios, Sebastian V. and Ou, Yanchi},
     title = {MLatom: A Package for Atomistic Simulations with Machine Learning},
     year = {2013--2024},
     type = {Computer Program}

{mlatom-3.2.0 → mlatom-3.4.0}/setup.py

@@ -43,7 +43,7 @@ with open(os.path.join(here, 'README.md')) as f:
 
 setup(
     name = pkg_name,
-    version = "3.2.0",
+    version = "3.4.0",
     author = "Pavlo O. Dral",
     author_email = "admin@mlatom.com",
     license = 'MIT (modified)',

{mlatom-3.2.0 → mlatom-3.4.0}/src/mlatom/MLatom.py

@@ -4,7 +4,7 @@
   !---------------------------------------------------------------------------!
   !                                                                           !
   !     MLatom: a Package for Atomistic Simulations with Machine Learning     !
-  !                             MLatom 3.2.0                                  !
+  !                             MLatom 3.4.0                                  !
   !                                   @                                       !
   !                 Xiamen Atomistic Computing Suite (XACS)                   !
   !                                                                           !
@@ -32,15 +32,11 @@
   ! Shuang Zhang, Arif Ullah, Quanhao Zhang, Yanchi Ou.                       !
   ! 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, Top. Curr. Chem. 2021, 379, 27            !
-  ! Pavlo O. Dral, 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, Yanchi Ou,           !
+  ! 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 3.2.0, Xiamen University, Xiamen, China, 2013-2024.               !
+  ! version 3.4.0, 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-3.2.0 → mlatom-3.4.0}/src/mlatom/MLtasks.py

@@ -367,7 +367,10 @@ def geomopt(args):
     molDB = loading_data(XYZfile=args.XYZfile, charges=args.charges, multiplicities=args.multiplicities)
     model = loading_model(args)
     fname = args.optXYZ
-    if os.path.exists(fname): stopper.stopMLatom(f'File {fname} already exists; please delete or rename it')
+    # if os.path.exists(fname): stopper.stopMLatom(f'File {fname} already exists; please delete or rename it')
+    if os.path.exists(fname): 
+        os.remove(fname)
+        print(f' * Warning * File {fname} already exists; MLatom will overwrite {fname}')
     db_opt = data.molecular_database()
     kwargs = {}
     if args.optProg:        kwargs['program'] = args.optprog
@@ -375,16 +378,28 @@ def geomopt(args):
     if args.ase.fmax:       kwargs['convergence_criterion_for_forces'] = float(args.ase.fmax)
     if args.ase.steps:      kwargs['maximum_number_of_steps'] = int(args.ase.steps)
     if args.ase.optimizer:  kwargs['optimization_algorithm'] = args.ase.optimizer
+    if len(molDB.molecules)<=10: 
+        kwargs['print_properties'] = 'all'
+    else:
+        kwargs['print_properties'] = 'min'
+    if args.printall:       kwargs['print_properties'] = 'all'
+    if args.printmin:       kwargs['print_properties'] = None
+    if args.dumpopttrajs:
+        kwargs['dump_trajectory_interval'] = 1
+    else:
+        kwargs['dump_trajectory_interval'] = None
+    kwargs['format'] = 'json'
     for imol, mol in enumerate(molDB):
         mol.number = imol+1
+        print(' %s ' % ('='*78))
+        print(' Optimization of molecule %d' % (imol+1))
+        print(' %s \n' % ('='*78))
+        kwargs['filename'] = f'opttraj{imol+1}.json'
         geomopt = simulations.optimize_geometry(model=model,
                                         initial_molecule=mol,
                                         **kwargs)
         db_opt.molecules.append(geomopt.optimized_molecule)
-        print(' %s ' % ('='*78))
-        print(' Optimization of molecule %d' % (imol+1))
-        print(' %s \n' % ('='*78))
-        print(f'   {"Iteration":^10s}    {"Energy (Hartree)":^25s}') # units?
+        print(f'\n\n   {"Iteration":^10s}    {"Energy (Hartree)":^25s}')
         for step in geomopt.optimization_trajectory.steps:
             print('   %10d    %25.13f' % (step.step+1, step.molecule.energy))
         if args.AIQM1 or args.AIQM1DFT or args.AIQM1DFTstar:
@@ -522,6 +537,8 @@ def MLTPA(args):
 # Reusable functions below. Name with -ing form
 def loading_data(XYZfile, Yfile=None, YgradXYZfile=None, charges=None, multiplicities=None):
     assert XYZfile, 'please provide data file(s) needed.'
+    if not os.path.exists(XYZfile):
+        stopper.stopMLatom(f'xyz file {XYZfile} is not found!')
     molecular_database = data.molecular_database.from_xyz_file(XYZfile)
     if Yfile: 
         molecular_database.add_scalar_properties_from_file(Yfile)

{mlatom-3.2.0 → mlatom-3.4.0}/src/mlatom/__init__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-from . import data, models, plot, simulations, stats, xyz
+from . import data, models, plot, simulations, stats, xyz, namd, constants
 from .simulations import optimize_geometry, irc, freq, thermochemistry, md, generate_initial_conditions, vibrational_spectrum
 from .data import atom, molecule, molecular_database
 from .models import methods

{mlatom-3.2.0 → mlatom-3.4.0}/src/mlatom/aiqm1.py

@@ -11,16 +11,13 @@ import numpy as np
 import os
 from . import data, models, stopper
 
-try: 
-    import torch
-    import torchani
-    from torchani.utils import ChemicalSymbolsToInts
-except:
-    raise ValueError('Please install all Python modules required for TorchANI')
+import torch
+import torchani
+from torchani.utils import ChemicalSymbolsToInts
 
 class aiqm1(models.torchani_model):
     """
-    The Artificial intelligence–quantum mechanical method as in the `AIQM1 paper`_.
+    The Artificial intelligence-quantum mechanical method as in the `AIQM1 paper`_.
 
     Arguments:
         method (str, optional): AIQM method used. Currently supports AIQM1, AIQM1\@DFT*, and AIQM1\@DFT. Default value: AIQM1.
@@ -69,50 +66,67 @@ class aiqm1(models.torchani_model):
         self.aiqm1_model = models.model_tree_node(name=modelname, children=aiqm1_children, operator='sum')
     
     def predict(self, molecular_database=None, molecule=None,
-                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False):
-        if molecular_database != None:
-            molDB = molecular_database
-        elif molecule != None:
-            molDB = data.molecular_database()
-            molDB.molecules.append(molecule)
-        else:
-            errmsg = 'Either molecule or molecular_database should be provided in input'
-            raise ValueError(errmsg)
-        
+                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False, nstates=1, current_state=0, **kwargs):
+        molDB = super().predict(molecular_database=molecular_database, molecule=molecule)
+        if 'nthreads' in self.__dict__: self.aiqm1_model.nthreads = self.nthreads
         for mol in molDB.molecules:
             self.predict_for_molecule(molecule=mol,
-                                    calculate_energy=calculate_energy, calculate_energy_gradients=calculate_energy_gradients, calculate_hessian=calculate_hessian)
+                                    calculate_energy=calculate_energy, calculate_energy_gradients=calculate_energy_gradients, calculate_hessian=calculate_hessian, nstates=nstates, 
+                                    current_state=current_state,
+                                    **kwargs)
         
     def predict_for_molecule(self, molecule=None,
-                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False):
+                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False, nstates=1, current_state=0, **kwargs):
         
         for atom in molecule.atoms:
             if not atom.atomic_number in [1, 6, 7, 8]:
-                print(' * Warning * Molecule contains elements other than CHNO, no calculations performed')
-                return
+                errmsg = ' * Warning * Molecule contains elements other than CHNO, no calculations performed'
+                # print(errmsg)
+                raise ValueError(errmsg)
         
+        if nstates >1:
+            mol_copy = molecule.copy()
+            mol_copy.electronic_states = []
+            for _ in range(nstates - len(molecule.electronic_states)):
+                molecule.electronic_states.append(mol_copy.copy())
+        
+        # for molecule in molecules:
         if len(molecule.atoms) == 1:
             molecule.energy = self.atomic_energies[self.method][molecule.atoms[0].atomic_number]
             standard_atom = data.atom(atomic_number=molecule.atoms[0].atomic_number)
             if molecule.charge != 0 or molecule.multiplicity != standard_atom.multiplicity:
                 odm2model = models.methods(method='ODM2*', program=self.qm_program)
                 mol_odm2 = molecule.copy()
-                odm2model.predict(molecule=mol_odm2)
+                odm2model.predict(molecule=mol_odm2, nstates=nstates, **kwargs)
                 mol_standard_odm2 = molecule.copy() ; mol_standard_odm2.charge = 0; mol_standard_odm2.multiplicity=standard_atom.multiplicity
-                odm2model.predict(molecule=mol_standard_odm2)
+                odm2model.predict(molecule=mol_standard_odm2, nstates=nstates, **kwargs)
                 molecule.energy = molecule.energy + mol_odm2.energy - mol_standard_odm2.energy
         else:
+            if nstates > 1 and isinstance(calculate_energy_gradients, list): 
+                if any(calculate_energy_gradients):
+                    calculate_energy_gradients = [True] * nstates
             self.aiqm1_model.predict(molecule=molecule,
-                                    calculate_energy=calculate_energy, calculate_energy_gradients=calculate_energy_gradients, calculate_hessian=calculate_hessian)
+                                    calculate_energy=calculate_energy, calculate_energy_gradients=calculate_energy_gradients, calculate_hessian=calculate_hessian, nstates=nstates, 
+                                    current_state=current_state,
+                                    **kwargs)
             
             properties = [] ; atomic_properties = []
+            
+            calculate_energy_gradients = bool(np.array(calculate_energy_gradients).any())
+            calculate_hessian = bool(np.array(calculate_hessian).any())
             if calculate_energy: properties.append('energy')
             if calculate_energy_gradients: atomic_properties.append('energy_gradients')
             if calculate_hessian: properties.append('hessian')
             modelname = self.method.lower().replace('*','star').replace('@','at')
-            molecule.__dict__[f'{modelname}_nn'].standard_deviation(properties=properties+atomic_properties)
 
-class atomic_energy_shift():
+            if nstates >1:
+                for mol_el_st in molecule.electronic_states:
+                    mol_el_st.__dict__[f'{modelname}_nn'].standard_deviation(properties=properties+atomic_properties)
+            else:
+                molecule.__dict__[f'{modelname}_nn'].standard_deviation(properties=properties+atomic_properties)
+            
+
+class atomic_energy_shift(models.model):
     atomic_energy_shifts = {'AIQM1': {1: -4.29365862e-02, 6: -3.34329586e+01, 7: -4.69301173e+01, 8: -6.29634763e+01},
                             'AIQM1@DFT': {1: -4.27888067e-02, 6: -3.34869833e+01, 7: -4.69896148e+01, 8: -6.30294433e+01}}
     atomic_energy_shifts['AIQM1@DFT*'] = atomic_energy_shifts['AIQM1@DFT']
@@ -121,30 +135,35 @@ class atomic_energy_shift():
         self.method = method
         
     def predict(self, molecular_database=None, molecule=None,
-                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False):
-        if molecular_database != None:
-            molDB = molecular_database
-        elif molecule != None:
-            molDB = data.molecular_database()
-            molDB.molecules.append(molecule)
-        else:
-            errmsg = 'Either molecule or molecular_database should be provided in input'
-            raise ValueError(errmsg)
+                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False, nstates=1, **kwargs):
+        molDB = super().predict(molecular_database=molecular_database, molecule=molecule)
+        calculate_energy_gradients = bool(np.array(calculate_energy_gradients).any())
+        calculate_hessian = bool(np.array(calculate_hessian).any())
          
         for mol in molDB.molecules:
-            if calculate_energy:
-                sae = 0.0
-                for atom in mol.atoms:
-                    sae += self.atomic_energy_shifts[self.method][atom.atomic_number]
-                mol.energy = sae
-            if calculate_energy_gradients:
-                for atom in mol.atoms:
-                    atom.energy_gradients = np.zeros(3)
-            if calculate_hessian:
-                ndim = len(mol.atoms) * 3
-                mol.hessian = np.zeros(ndim*ndim).reshape(ndim,ndim)
+            molecules = [mol]
 
-class ani_nns_in_aiqm1():
+            if nstates >1:
+                mol_copy = mol.copy()
+                mol_copy.electronic_states = []
+                for _ in range(nstates - len(mol.electronic_states)):
+                    mol.electronic_states.append(mol_copy.copy())
+                molecules = mol.electronic_states
+            
+            for mol in molecules:
+                if calculate_energy:
+                    sae = 0.0
+                    for atom in mol.atoms:
+                        sae += self.atomic_energy_shifts[self.method][atom.atomic_number]
+                    mol.energy = sae
+                if calculate_energy_gradients:
+                    for atom in mol.atoms:
+                        atom.energy_gradients = np.zeros(3)
+                if calculate_hessian:
+                    ndim = len(mol.atoms) * 3
+                    mol.hessian = np.zeros(ndim*ndim).reshape(ndim,ndim)
+
+class ani_nns_in_aiqm1(models.torchani_model):
     species_order = [1, 6, 7, 8]
     
     def __init__(self, method='AIQM1', model_index = 0):
@@ -225,34 +244,39 @@ class ani_nns_in_aiqm1():
         self.nn = nn
     
     def predict(self, molecular_database=None, molecule=None,
-                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False):
-        if molecular_database != None:
-            molDB = molecular_database
-        elif molecule != None:
-            molDB = data.molecular_database()
-            molDB.molecules.append(molecule)
-        else:
-            errmsg = 'Either molecule or molecular_database should be provided in input'
-            raise ValueError(errmsg)
+                calculate_energy=True, calculate_energy_gradients=False, calculate_hessian=False, nstates=1, **kwargs):
+        molDB = super().predict(molecular_database=molecular_database, molecule=molecule)
         
+        calculate_energy_gradients = bool(np.array(calculate_energy_gradients).any())
+        calculate_hessian = bool(np.array(calculate_hessian).any())
         species_to_tensor = ChemicalSymbolsToInts(self.species_order)
         
         for mol in molDB.molecules:
-            atomic_numbers = np.array([atom.atomic_number for atom in mol.atoms])
-            xyz_coordinates = torch.tensor(np.array(mol.xyz_coordinates).astype('float')).to(self.device).requires_grad_(calculate_energy_gradients or calculate_hessian)
-            xyz_coordinates = xyz_coordinates.unsqueeze(0)
-            species = species_to_tensor(atomic_numbers).to(self.device).unsqueeze(0)
-            ANI_NN_energy = self.model((species, xyz_coordinates)).energies
-            if calculate_energy: mol.energy = float(ANI_NN_energy)
-            if calculate_energy_gradients or calculate_hessian:
-                ANI_NN_energy_gradients = torch.autograd.grad(ANI_NN_energy.sum(), xyz_coordinates, create_graph=True, retain_graph=True)[0]
-                if calculate_energy_gradients:
-                    grads = ANI_NN_energy_gradients[0].detach().cpu().numpy()
-                    for iatom in range(len(mol.atoms)):
-                        mol.atoms[iatom].energy_gradients = grads[iatom]
-            if calculate_hessian:
-                ANI_NN_hessian = torchani.utils.hessian(xyz_coordinates, energies=ANI_NN_energy)
-                mol.hessian = ANI_NN_hessian[0].detach().cpu().numpy()
+            molecules = [mol]
+
+            if nstates >1:
+                mol_copy = mol.copy()
+                mol_copy.electronic_states = []
+                for _ in range(nstates - len(mol.electronic_states)):
+                    mol.electronic_states.append(mol_copy.copy())
+                molecules = mol.electronic_states
+            
+            for mol in molecules:
+                atomic_numbers = np.array([atom.atomic_number for atom in mol.atoms])
+                xyz_coordinates = torch.tensor(np.array(mol.xyz_coordinates).astype('float')).to(self.device).requires_grad_(calculate_energy_gradients or calculate_hessian)
+                xyz_coordinates = xyz_coordinates.unsqueeze(0)
+                species = species_to_tensor(atomic_numbers).to(self.device).unsqueeze(0)
+                ANI_NN_energy = self.model((species, xyz_coordinates)).energies
+                if calculate_energy: mol.energy = float(ANI_NN_energy)
+                if calculate_energy_gradients or calculate_hessian:
+                    ANI_NN_energy_gradients = torch.autograd.grad(ANI_NN_energy.sum(), xyz_coordinates, create_graph=True, retain_graph=True)[0]
+                    if calculate_energy_gradients:
+                        grads = ANI_NN_energy_gradients[0].detach().cpu().numpy()
+                        for iatom in range(len(mol.atoms)):
+                            mol.atoms[iatom].energy_gradients = grads[iatom]
+                if calculate_hessian:
+                    ANI_NN_hessian = torchani.utils.hessian(xyz_coordinates, energies=ANI_NN_energy)
+                    mol.hessian = ANI_NN_hessian[0].detach().cpu().numpy()
 
 if __name__ == '__main__':
     pass

{mlatom-3.2.0 → mlatom-3.4.0}/src/mlatom/args_class.py

@@ -202,53 +202,53 @@ class ArgsBase():
     @staticmethod
     def _args_extractor(string: str) -> List[str]:
         pair_dict = {'(': ')', '[': ']', '{': '}', '<': '>', "'": "'", '"': '"'}
-        pair_level = 0
         pair_right: List[str] = []
         tmp = ''
-        prev = ''
+        comment = False
         out_string_list: List[str] = []
         for chr in string:
             pair_right_last = pair_right[-1] if pair_right else ''
+            if chr == '#':
+                comment = True
+            if chr == '\n':
+                comment = False
+            if comment:
+                continue
             if chr in pair_dict.keys() and chr != pair_right_last:
-                pair_level += 1
                 pair_right.append(pair_dict[chr])
             elif chr == pair_right_last:
-                pair_level -= 1
                 pair_right.pop()
-            elif chr == ' ' and pair_level == 0 and prev.strip():  # end
-                out_string_list.append(tmp)
-                tmp = ''
-                prev = chr
-                continue
-            if '"' in pair_right or "'" in pair_right:
+            if pair_right:
                 tmp += chr
+            elif chr in [' ', '\n'] and tmp:  # end
+                out_string_list.append(tmp.strip())
+                tmp = ''
             else:
                 tmp += chr.strip()
-            prev = chr
-        if pair_level:
+        if pair_right:
             stopper.stopMLatom(f'pair character unmatched args: "{tmp}"')
         else:
             if tmp: out_string_list.append(tmp)
+        
         return out_string_list
     
     def parse_input_file(self, file: str):
-        try:
-            with open(file) as f:
-                content = f.read().splitlines()
-        except:
-            self._raise_error(f'can not open file {file}! exit!'); exit()
+        with open(file) as f:
+            content = self._args_extractor(f.read())
         self.parse_input_content(content)
     
     def parse_input_content(self, content: Union[List[str], str]):
-        help = False
         if type(content) is str:
-            content = content.splitlines()
-        for c in self._clean_input_content(content):
+            content = [content]
+        _content = []
+        for c in content:
+            _content.extend(self._args_extractor(c) if '\n' not in c else [c])
+        for c in _content:
             splitted = c.split('=')
             if len(splitted) == 1:
                 key = splitted[0]
                 if key.lower() in ['help', '-help', '-h', '--help']:
-                    help = True
+                    self._print_doc()
                 elif key.lower() in self.ignore_list:
                     pass
                 else:
@@ -265,8 +265,6 @@ class ArgsBase():
                     self.data[key] = value
             else:
                 self._raise_error(f'error happends at your input file, error content:\n    {c}')
-        if help:
-            self._print_doc()
     
     @classmethod
     def _multi_level_dict(cls, key: str, value: Any) -> Tuple[str, Union[AttributeDict, Dict[str, Union[str, Dict[str, Any]]]]]:
@@ -283,19 +281,7 @@ class ArgsBase():
         try: Doc.printDoc(self.args_dict)
         except: self._warning_print('Doc not imported')
         stopper.stopMLatom('')
-    
-    @classmethod
-    def _clean_input_content(cls, content: List[str]) -> List[str]:
-        to_return: List[str] = []
-        for c in content:
-            usable = c.split('#')[0].strip()
-            while usable.find(' =') != -1:
-                usable = usable.replace(' =', '=')
-            while usable.find('= ') != -1:
-                usable = usable.replace('= ', '=')
-            to_return.extend(cls._args_extractor(usable))
-        return to_return
-    
+
     @property
     def args_dict(self) -> Dict[str, Any]:
         return AttributeDict.normal_dict(self.data)
@@ -616,6 +602,14 @@ class mlatom_args(ArgsBase):
             'DOF':-6,
             'linear':0,
         })
+        # geomopt output
+        self.add_default_dict_args(
+            [
+                'printall',                # print out all information in geometry optimization
+                'printmin',                # print out minimal infomation in geometry optimization        
+                'dumpopttrajs'             # whether to dump optimization trajectory
+            ], ''
+        )
     
         self.defualt_args2pass = self.args_string_list(['', None])
 
@@ -628,23 +622,35 @@ class mlatom_args(ArgsBase):
         if len(argsraw) == 0:
             Doc.printDoc({})
             stopper.stopMLatom('At least one option should be provided')
-        elif len(argsraw) == 1:
-            if os.path.exists(argsraw[0]):
-                # self.parse_input_file(argsraw[0])
-                self.argsraw = []
-                with open(argsraw[0]) as f:
-                    content = f.read().splitlines()
-                    for c in self._clean_input_content(content):
-                        self.argsraw += [c]
-                self.parse_input_content(self.argsraw)
-            else:
-                self.parse_input_content(argsraw[0])
-        elif len(argsraw) >= 2:
+        elif len(argsraw) == 1 and os.path.exists(argsraw[0]):
+            self.parse_input_file(argsraw[0])
+        else:
             self.parse_input_content(argsraw)
         
         self._post_operations()
+            
+    def _post_operations(self):
+        if not self.MLprog:
+            if self.MLmodelType :
+                try: self.MLprog = default_MLprog[self.MLmodelType.lower()]
+                except: stopper.stopMLatom('Unkown MLmodelType')
+            else:
+                self.MLprog = 'MLatomF'
         self._checkArgs()
         self._check_hyperopt()
+        self._multi_lines_to_file()
+
+    def _multi_lines_to_file(self):
+        import hashlib
+        for arg in self.args2pass:
+            if '\n' in arg:
+                key, value = arg.split('=')
+                tmpfile = f"{key}_{hashlib.md5(value.encode('utf-8')).hexdigest()[:6]}"
+                if 'xyz' in key.lower():
+                    tmpfile += '.xyz'
+                with open(tmpfile, 'w') as f:
+                    f.write(value.strip("'").strip('"').strip() + '\n')
+                self.parse_input_content([f'{key}={tmpfile}'])
 
     def _check_hyperopt(self):
         self.hyperparameter_optimization = {
@@ -660,14 +666,6 @@ class mlatom_args(ArgsBase):
                 self._hyperopt_str_dict[key.split('.')[-1]] = value
         if self._hyperopt_str_dict:
             self.hyperparameter_optimization['optimization_algorithm'] = self.hyperopt.algorithm
-            
-    def _post_operations(self):
-        if not self.MLprog:
-            if self.MLmodelType :
-                try: self.MLprog = default_MLprog[self.MLmodelType.lower()]
-                except: stopper.stopMLatom('Unkown MLmodelType')
-            else:
-                self.MLprog = 'MLatomF'
 
     def _checkArgs(self):
         if not self._task:

{mlatom-3.2.0 → mlatom-3.4.0}/src/mlatom/conversions.py

@@ -2,7 +2,7 @@ import numpy as np
 
 def smi2xyz(smi_strings):
     from openbabel import pybel as pb
-    if type(smi_strings) == str:
+    if isinstance(smi_strings, str):
         smi_strings =  smi_strings.strip().split('\n')
     xyz_strings = []
     for smi_string in smi_strings:
@@ -13,7 +13,7 @@ def smi2xyz(smi_strings):
 
 def xyz2smi(xyz_strings):
     from openbabel import pybel as pb
-    if type(xyz_strings) == str:
+    if isinstance(xyz_strings, str):
         xyz_strings = split_xyz_string(xyz_strings)
     smi_strings = []
     for string in xyz_strings: