Merge pull request #15 from sandipgiri576/master

new descriptor
anooplab · Aug 19, 2024 · 239564b · 239564b
2 parents 3f58f9a + 1e1739c
commit 239564b
Show file tree

Hide file tree

Showing 48 changed files with 273 additions and 5 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,2 @@
+ pyar.egg-info/
+test/
diff --git a/pyar.egg-info/PKG-INFO b/pyar.egg-info/PKG-INFO
@@ -0,0 +1,22 @@
+Metadata-Version: 2.1
+Name: pyar
+Version: 1.0
+Summary: A Python Code for Aggregation and Reaction
+Home-page: https://github.com/anooplab/pyar
+Author: Anoop et al
+Author-email: [email protected]
+License: GPL v3
+Keywords: computational chemistry global minima aggregation automated reaction
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Requires-Python: >=3.6
+License-File: LICENSE
+
+UNKNOWN
+
diff --git a/pyar.egg-info/SOURCES.txt b/pyar.egg-info/SOURCES.txt
@@ -0,0 +1,109 @@
+LICENSE
+MANIFEST.in
+README.md
+setup.py
+pyar/Molecule.py
+pyar/__init__.py
+pyar/aggregator.py
+pyar/checkpt.py
+pyar/checkvalidity.py
+pyar/crawler.py
+pyar/file_manager.py
+pyar/optimiser.py
+pyar/property.py
+pyar/reactor.py
+pyar/representations.py
+pyar/scan.py
+pyar/similarity.py
+pyar/tabu.py
+pyar.egg-info/PKG-INFO
+pyar.egg-info/SOURCES.txt
+pyar.egg-info/dependency_links.txt
+pyar.egg-info/requires.txt
+pyar.egg-info/top_level.txt
+pyar/AIMNet2/__init__.py
+pyar/AIMNet2/calculators/__init__.py
+pyar/AIMNet2/calculators/afir_aimnet.py
+pyar/AIMNet2/calculators/aimnet2_ase_opt.py
+pyar/AIMNet2/calculators/aimnet2ase.py
+pyar/AIMNet2/models/__init__.py
+pyar/AIMNet2/models/aimnet2_wb97m-d3_0.jpt
+pyar/afir/__init__.py
+pyar/afir/restraints.py
+pyar/data/__init__.py
+pyar/data/atomic_data.py
+pyar/data/defualt_parameters.py
+pyar/data/new_atomic_data.py
+pyar/data/units.py
+pyar/data_analysis/__init__.py
+pyar/data_analysis/clustering.py
+pyar/interface/ASE.py
+pyar/interface/__init__.py
+pyar/interface/aimnet_2.py
+pyar/interface/aiqm1_mlatom.py
+pyar/interface/ani.py
+pyar/interface/babel.py
+pyar/interface/gaussian.py
+pyar/interface/mlatom_aiqm1.py
+pyar/interface/mlopt.py
+pyar/interface/mopac.py
+pyar/interface/orca.py
+pyar/interface/psi4.py
+pyar/interface/turbomole.py
+pyar/interface/xtb.py
+pyar/interface/xtb_aimnet2.py
+pyar/interface/xtb_aiqm1.py
+pyar/interface/xtbturbo.py
+pyar/mlatom/MLTPA.py
+pyar/mlatom/ML_NEA.py
+pyar/mlatom/MLatom.py
+pyar/mlatom/MLtasks.py
+pyar/mlatom/__init__.py
+pyar/mlatom/aiqm1.py
+pyar/mlatom/args_class.py
+pyar/mlatom/ccsdtstarcbs.py
+pyar/mlatom/composite_methods.py
+pyar/mlatom/constants.py
+pyar/mlatom/conversions.py
+pyar/mlatom/data.py
+pyar/mlatom/doc.py
+pyar/mlatom/environment_variables.py
+pyar/mlatom/header.py
+pyar/mlatom/initial_conditions.py
+pyar/mlatom/interface_MLatomF.py
+pyar/mlatom/kreg_api.py
+pyar/mlatom/mlatom_gui.py
+pyar/mlatom/models-old.py
+pyar/mlatom/models.py
+pyar/mlatom/plot.py
+pyar/mlatom/shell_cmd.py
+pyar/mlatom/simulations.py
+pyar/mlatom/sliceData.py
+pyar/mlatom/stats.py
+pyar/mlatom/stopper.py
+pyar/mlatom/thermostat.py
+pyar/mlatom/utils.py
+pyar/mlatom/xyz.py
+pyar/mlatom/aiqm1_model/__init__.py
+pyar/mlatom/interfaces/__init__.py
+pyar/mlatom/interfaces/ase_interface.py
+pyar/mlatom/interfaces/dftd4_interface.py
+pyar/mlatom/interfaces/dpmd_interface.py
+pyar/mlatom/interfaces/gap_interface.py
+pyar/mlatom/interfaces/gaussian_interface.py
+pyar/mlatom/interfaces/mndo_interface.py
+pyar/mlatom/interfaces/orca_interface.py
+pyar/mlatom/interfaces/physnet_interface.py
+pyar/mlatom/interfaces/pyscf_interface.py
+pyar/mlatom/interfaces/sgdml_interface.py
+pyar/mlatom/interfaces/sparrow_interface.py
+pyar/mlatom/interfaces/torchani_interface.py
+pyar/mlatom/interfaces/xtb_interface.py
+pyar/scripts/__init__.py
+pyar/scripts/pyar-cli
+pyar/scripts/pyar-clustering
+pyar/scripts/pyar-descriptor
+pyar/scripts/pyar-optimiser
+pyar/scripts/pyar-similarity
+pyar/scripts/pyar-tabu
+test/test-descriptor.py
diff --git a/pyar.egg-info/dependency_links.txt b/pyar.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/pyar.egg-info/requires.txt b/pyar.egg-info/requires.txt
@@ -0,0 +1,10 @@
+numpy
+scikit-learn
+scipy
+pandas
+matplotlib
+pyh5md
+h5py
+networkx
+DBCV@ git+https://github.com/christopherjenness/DBCV.git
+dscribe
diff --git a/pyar.egg-info/top_level.txt b/pyar.egg-info/top_level.txt
@@ -0,0 +1 @@
+pyar
diff --git a/pyar/AIMNet2/__pycache__/__init__.cpython-37.pyc b/pyar/AIMNet2/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/AIMNet2/calculators/__pycache__/__init__.cpython-37.pyc b/pyar/AIMNet2/calculators/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/AIMNet2/calculators/__pycache__/aimnet2_ase_opt.cpython-37.pyc b/pyar/AIMNet2/calculators/__pycache__/aimnet2_ase_opt.cpython-37.pyc
diff --git a/pyar/AIMNet2/calculators/__pycache__/aimnet2ase.cpython-37.pyc b/pyar/AIMNet2/calculators/__pycache__/aimnet2ase.cpython-37.pyc
diff --git a/pyar/__pycache__/Molecule.cpython-37.pyc b/pyar/__pycache__/Molecule.cpython-37.pyc
diff --git a/pyar/__pycache__/__init__.cpython-37.pyc b/pyar/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/__pycache__/aggregator.cpython-37.pyc b/pyar/__pycache__/aggregator.cpython-37.pyc
diff --git a/pyar/__pycache__/file_manager.cpython-37.pyc b/pyar/__pycache__/file_manager.cpython-37.pyc
diff --git a/pyar/__pycache__/optimiser.cpython-37.pyc b/pyar/__pycache__/optimiser.cpython-37.pyc
diff --git a/pyar/__pycache__/property.cpython-37.pyc b/pyar/__pycache__/property.cpython-37.pyc
diff --git a/pyar/__pycache__/representations.cpython-37.pyc b/pyar/__pycache__/representations.cpython-37.pyc
diff --git a/pyar/__pycache__/scan.cpython-37.pyc b/pyar/__pycache__/scan.cpython-37.pyc
diff --git a/pyar/__pycache__/similarity.cpython-37.pyc b/pyar/__pycache__/similarity.cpython-37.pyc
diff --git a/pyar/__pycache__/tabu.cpython-37.pyc b/pyar/__pycache__/tabu.cpython-37.pyc
diff --git a/pyar/data/__pycache__/__init__.cpython-37.pyc b/pyar/data/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/data/__pycache__/defualt_parameters.cpython-37.pyc b/pyar/data/__pycache__/defualt_parameters.cpython-37.pyc
diff --git a/pyar/data/__pycache__/new_atomic_data.cpython-37.pyc b/pyar/data/__pycache__/new_atomic_data.cpython-37.pyc
diff --git a/pyar/data_analysis/__pycache__/__init__.cpython-37.pyc b/pyar/data_analysis/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/data_analysis/__pycache__/clustering.cpython-37.pyc b/pyar/data_analysis/__pycache__/clustering.cpython-37.pyc
diff --git a/pyar/data_analysis/clustering.py b/pyar/data_analysis/clustering.py
@@ -126,6 +126,7 @@ def choose_geometries(list_of_molecules, features='mbtr', maximum_number_of_seed
         dt_array = np.array(dt)
     elif features == 'mbtr':
         dt = [pyar.representations.mbtr_descriptor(i.atoms_list, i.coordinates) for i in list_of_molecules]
+        # dt = [d.get_k2()['element_Z'] for d in dt] 
     elif features == 'soap':
         dt = [pyar.representations.soap_descriptor(i.atoms_list, i.coordinates) for i in list_of_molecules]
         dt = [d.todense() for d in dt]  # Convert sparse arrays to dense arrays
@@ -145,9 +146,7 @@ def choose_geometries(list_of_molecules, features='mbtr', maximum_number_of_seed
 
     dt = np.around(dt, decimals=5)
 
-    # df = pd.DataFrame(dt)
-    # df.to_csv("features.csv")
-    # Assuming 'dt' is a list of LMBTR descriptors for multiple molecules
+
     dt_array = np.array(dt)
 
     # Reshape the array into a 2-dimensional array
@@ -157,8 +156,7 @@ def choose_geometries(list_of_molecules, features='mbtr', maximum_number_of_seed
     df = pd.DataFrame(dt_reshaped)
     df.to_csv("features.csv")
 
-    # scale_it = RobustScaler()
-    # dt = scale_it.fit_transform(dt)
+
     scale_it = RobustScaler()
     dt = scale_it.fit_transform(dt_reshaped)
 

diff --git a/pyar/interface/__pycache__/__init__.cpython-37.pyc b/pyar/interface/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/interface/__pycache__/aimnet_2.cpython-37.pyc b/pyar/interface/__pycache__/aimnet_2.cpython-37.pyc
diff --git a/pyar/interface/__pycache__/xtb.cpython-37.pyc b/pyar/interface/__pycache__/xtb.cpython-37.pyc
diff --git a/pyar/interface/__pycache__/xtb_aimnet2.cpython-37.pyc b/pyar/interface/__pycache__/xtb_aimnet2.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/__init__.cpython-37.pyc b/pyar/mlatom/__pycache__/__init__.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/constants.cpython-37.pyc b/pyar/mlatom/__pycache__/constants.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/conversions.cpython-37.pyc b/pyar/mlatom/__pycache__/conversions.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/data.cpython-37.pyc b/pyar/mlatom/__pycache__/data.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/environment_variables.cpython-37.pyc b/pyar/mlatom/__pycache__/environment_variables.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/initial_conditions.cpython-37.pyc b/pyar/mlatom/__pycache__/initial_conditions.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/plot.cpython-37.pyc b/pyar/mlatom/__pycache__/plot.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/simulations.cpython-37.pyc b/pyar/mlatom/__pycache__/simulations.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/stats.cpython-37.pyc b/pyar/mlatom/__pycache__/stats.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/stopper.cpython-37.pyc b/pyar/mlatom/__pycache__/stopper.cpython-37.pyc
diff --git a/pyar/mlatom/__pycache__/xyz.cpython-37.pyc b/pyar/mlatom/__pycache__/xyz.cpython-37.pyc
diff --git a/pyar/representations.py b/pyar/representations.py
@@ -328,7 +328,33 @@ def mbtr_descriptor(atoms_list, coordinates):
 
     return mbtr_output
 
+
+
+
+
+
+# def mbtr_descriptor(atoms_list, coordinates):
+#     # Create an Atoms object from the atoms_list and coordinates
+#     molecule = Atoms(atoms_list, positions=coordinates)
+
+#     # Get unique species from atoms_list
+#     unique_species = list(set(atoms_list))
+
+#     k2min, k2max, k2n = 0.7, 2.0, 100
 
+#     mbtr = MBTR(
+#         species=unique_species,
+#         geometry={"function": "distance"},
+#         grid={"min": k2min, "max": k2max, "n": k2n, "sigma": 0.000000001},
+#         weighting={"function": "exp", "scale": 0.5, "threshold": 3e-3},
+#         periodic=False,
+#         normalization="l2_each",
+#     )
+
+#     # Create MBTR output for the molecule
+#     mbtr_output = mbtr.create(molecule)
+
+#     return mbtr_output
 
 
 def soap_descriptor(atoms_list, coordinates):

diff --git a/pyar/scripts/__init__.py b/pyar/scripts/__init__.py
diff --git a/pyar/scripts/pyar-clustering b/pyar/scripts/pyar-clustering
diff --git a/pyar/scripts/pyar-descriptor b/pyar/scripts/pyar-descriptor
@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+
+import os
+import sys
+import numpy as np
+import warnings
+from ase.io import read, write
+from scipy.spatial import ConvexHull
+import MDAnalysis as mda
+import pandas as pd
+import argparse
+import glob
+
+# Suppress specific warnings from MDAnalysis
+warnings.filterwarnings("ignore", category=UserWarning, module="MDAnalysis.analysis.base")
+
+def calculate_properties(atoms):
+    # Calculate cluster size (number of atoms)
+    cluster_size = len(atoms)
+
+    # Calculate the convex hull to approximate the cluster volume and surface area
+    points = atoms.get_positions()
+    hull = ConvexHull(points)
+
+    # Volume and surface area from convex hull
+    volume = hull.volume
+    surface_area = hull.area
+
+    # Calculate the maximum distance between any two atoms (maximum length)
+    distances = np.linalg.norm(points[:, np.newaxis, :] - points[np.newaxis, :, :], axis=-1)
+    max_length = np.max(distances)
+
+    # Calculate gyration radius as an additional size measure
+    rgyr = np.sqrt(np.mean(np.sum((points - np.mean(points, axis=0))**2, axis=1)))
+
+    return cluster_size, volume, surface_area, max_length, rgyr
+
+def create_combined_descriptor(properties):
+    # Normalize the properties
+    normalized = np.array(properties) / np.sum(properties)
+
+    # Create a combined descriptor
+    combined = np.prod(normalized)
+
+    return combined
+
+def main(args):
+    xyz_files = []
+    for pattern in args.input_files:
+        xyz_files.extend(glob.glob(pattern))
+
+    if not xyz_files:
+        print("No XYZ files found.")
+        sys.exit(1)
+
+    data = []
+    unique_descriptors = {}
+    unique_atoms = []
+    duplicate_atoms = []
+
+    for filename in xyz_files:
+        atoms = read(filename)
+        properties = calculate_properties(atoms)
+        combined_descriptor = create_combined_descriptor(properties)
+
+        # Create .mb file
+        basename = os.path.splitext(os.path.basename(filename))[0]
+        mb_filename = f"{basename}.mb"
+        with open(mb_filename, 'w') as f:
+            f.write(f"{combined_descriptor}\n")
+
+        # Check if this descriptor is unique
+        if combined_descriptor not in unique_descriptors:
+            unique_descriptors[combined_descriptor] = filename
+            data.append([filename] + list(properties) + [combined_descriptor])
+            unique_atoms.append(atoms)
+        else:
+            duplicate_atoms.append(atoms)
+
+    # Create a DataFrame and save it as CSV
+    columns = ["Filename", "Cluster Size", "Volume (Å³)", "Surface Area (Å²)", "Maximum Length (Å)", "Radius of Gyration (Å)", "Combined Descriptor"]
+    df = pd.DataFrame(data, columns=columns)
+    df.to_csv("unique_cluster_properties.csv", index=False)
+
+    # Write trajectory files
+    write("unique_files.xyz", unique_atoms)
+    write("duplicate_files.xyz", duplicate_atoms)
+
+    print(f"Processed {len(xyz_files)} XYZ files.")
+    print(f"Found {len(unique_atoms)} unique structures and {len(duplicate_atoms)} duplicates.")
+    print("Results saved in unique_cluster_properties.csv, unique_files.xyz, and duplicate_files.xyz.")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Analyze molecular cluster XYZ files.")
+    parser.add_argument("input_files", metavar='files', type=str, nargs='+',
+                        help='input coordinate files (supports wildcards)')
+    args = parser.parse_args()
+    main(args)
diff --git a/pyar/scripts/pyar-optimiser b/pyar/scripts/pyar-optimiser
diff --git a/pyar/scripts/pyar-tabu b/pyar/scripts/pyar-tabu
diff --git a/setup.py b/setup.py
@@ -13,6 +13,7 @@
         'pyar/scripts/pyar-tabu',
         'pyar/scripts/pyar-clustering',
         'pyar/scripts/pyar-similarity',
+        'pyar/scripts/pyar-descriptor',
         'pyar/interface/mlopt.py',
         'pyar/AIMNet2/calculators/aimnet2_ase_opt.py'
     ],