A computer-implemented method for a generative adversarial approach for conformational space modeling of molecules is provided. The method can include obtaining molecule graph data for a molecule and inputting the molecule graph data into a machine learning platform. The machine learning platform can include architecture of a molecular graph generator, conformation discriminator, stochastic encoder, and latent variables discriminator. The method can include generating a plurality of conformations for the molecule with the machine learning platform. The plurality of conformations are specific to the molecule. Each conformation can have internal coordinates defining positions of atoms of the molecule. At least one conformation for the molecule can be selected based on at least one parameter related to molecular conformations. A report can be prepared that includes the selected at least one conformation for the molecule.

A method for selecting a material having a desired molecular property comprises generating a combinatorial library of molecule structures derived from a core molecular structure, splitting the library into a training set configured to train a graph neural network (GNN) machine learning (ML) model, a test set configured to test the validity of and assess accuracy of the GNN model, and a prediction set where predictions are made using the GNN model, optimizing geometries of the molecular structures, computing excited state energies of the optimized geometries, encoding molecular structure information into a matrix, determining three mutually orthogonal principal axes, transforming spatial coordinates into mutually orthogonal coordinates, constructing a molecular graph with n nodes, feeding the molecular graph into the GNN model as an input, and selecting a material having a suitable desired molecular property based on the output of the GNN model.

A method for selecting a material having a desired molecular property comprises generating a combinatorial library of molecule structures derived from a core molecular structure, splitting the library into a training set configured to train a graph neural network (GNN) machine learning (ML) model, a test set configured to test the validity of and assess accuracy of the GNN model, and a prediction set where predictions are made using the GNN model, optimizing geometries of the molecular structures, computing excited state energies of the optimized geometries, encoding molecular structure information into a matrix, determining three mutually orthogonal principal axes, transforming spatial coordinates into mutually orthogonal coordinates, constructing a molecular graph with n nodes, feeding the molecular graph into the GNN model as an input, and selecting a material having a suitable desired molecular property based on the output of the GNN model.

A method for finding an optimal quantum state minimizing the energy of a Hamiltonian operator with a quantum processor and a classical processor comprising a quantum circuit for producing trial quantum states for the Hamiltonian operator and parametric quantum gates with associated parameters, by using a VQE method, the method comprising: providing the Hamiltonian operator in an orbital basis and iteratively, until a predefined stopping criterion is satisfied: (i) applying the VQE method to find optimized values for the parameters that yield an intermediate optimal quantum state which minimizes the energy of the Hamiltonian operator, (ii) computing a one particle reduced density matrix (1-RDM) based on the intermediate optimal quantum state, (iii) determining an updated orbital basis in which the 1-RDM is diagonal, and an associated transformation matrix, and (iv) modifying the Hamiltonian operator with the transformation matrix; and then returning, as the optimal quantum state the intermediate optimal quantum state that minimizes the most the energy.

A method for finding an optimal quantum state minimizing the energy of a Hamiltonian operator with a quantum processor and a classical processor comprising a quantum circuit for producing trial quantum states for the Hamiltonian operator and parametric quantum gates with associated parameters, by using a VQE method, the method comprising: providing the Hamiltonian operator in an orbital basis and iteratively, until a predefined stopping criterion is satisfied: (i) applying the VQE method to find optimized values for the parameters that yield an intermediate optimal quantum state which minimizes the energy of the Hamiltonian operator, (ii) computing a one particle reduced density matrix (1-RDM) based on the intermediate optimal quantum state, (iii) determining an updated orbital basis in which the 1-RDM is diagonal, and an associated transformation matrix, and (iv) modifying the Hamiltonian operator with the transformation matrix; and then returning, as the optimal quantum state the intermediate optimal quantum state that minimizes the most the energy.

A stable structure search system includes one or more processors configured to acquire a plurality of degrees of structure similarity between each of a plurality of kinds of molecules and a first molecule included in a target molecule based on each interaction potential of the plurality of kinds of molecules, acquire a plurality of degrees of charge similarity between each of the plurality of kinds of molecules and the first molecule, acquire a plurality of total degrees of similarity based on sums of each of the plurality of degrees of structure similarity and each of the plurality of degrees of charge similarity, determine a second molecule whose total degree of similarly is largest among the plurality of kinds of molecules, acquire energy of a molecular structure of the target molecule based on an interaction potential of the second molecule, and determine whether the calculated energy satisfies a certain condition.

Traditionally, new alloy development and processing involved various high-end expansive experiments, huge development time and cost of required man-hours. One of the major issues, which limits the ability for materials scientists to design metallic materials from atoms using Molecular Dynamics (MD), is the lack of accurate interatomic molecular dynamics potentials (MDPs). Suitable MDPs of desired alloy systems enable new alloy compositions and related properties, but however, this is very difficult and time-consuming process. The present disclosure enables developing molecular dynamics potential for new/traditional metallic alloys for their simulated structural, thermodynamic, and mechanical property predictions. Present disclosure provides systems and methods for generating MDP for multi-element alloy systems wherein both Body Centered Cubic (BCC) element type and/or a Face Centered Cubic (FCC) element type are combined. Pure elements and multi-element alloys of combinations of BCC and FCC elements are modeled for predicting their various structural, thermodynamic, and mechanical properties.

Traditionally, new alloy development and processing involved various high-end expansive experiments, huge development time and cost of required man-hours. One of the major issues, which limits the ability for materials scientists to design metallic materials from atoms using Molecular Dynamics (MD), is the lack of accurate interatomic molecular dynamics potentials (MDPs). Suitable MDPs of desired alloy systems enable new alloy compositions and related properties, but however, this is very difficult and time-consuming process. The present disclosure enables developing molecular dynamics potential for new/traditional metallic alloys for their simulated structural, thermodynamic, and mechanical property predictions. Present disclosure provides systems and methods for generating MDP for multi-element alloy systems wherein both Body Centered Cubic (BCC) element type and/or a Face Centered Cubic (FCC) element type are combined. Pure elements and multi-element alloys of combinations of BCC and FCC elements are modeled for predicting their various structural, thermodynamic, and mechanical properties.

A computer-implemented method for predicting a conformation of a ligand docked into a protein is disclosed. According to some embodiments, the method may include determining one or more poses of the ligand in the protein, the poses being representative conformations of the ligand. The method may also include determining, using a neural network, energy scores of the poses. The method may further include determining a proper conformation for the docked ligand based on the energy scores.

A computer-implemented method for predicting a conformation of a ligand docked into a protein is disclosed. According to some embodiments, the method may include determining one or more poses of the ligand in the protein, the poses being representative conformations of the ligand. The method may also include determining, using a neural network, energy scores of the poses. The method may further include determining a proper conformation for the docked ligand based on the energy scores.