Provided are a method for searching for a molecular stable structure, a program for searching for a molecular stable structure, and a device for searching for a molecular stable structure, which are capable of acquiring a stable structure and various locally stable structures from a structural formula of a compound in a short time and with high accuracy. A three-dimensional structure is generated from the structural formula of the compound, and a locally stable structure is obtained from the three-dimensional structure. A one-dimensional or multidimensional energy distribution function for one or a plurality of internal coordinates and a probability distribution function of increasing a probability of low-energy internal coordinates are calculated from internal coordinates and an energy value of the locally stable structure. The method for searching for a molecular stable structure repeats the following processes: generating a three-dimensional structure based on the calculated probability distribution function; acquiring a locally stable structure; reflecting internal coordinates and an energy value of the obtained locally stable structure on the energy distribution function and the probability distribution function; and acquiring the locally stable structure, thereby obtaining a plurality of the locally stable structures and a structure with lowest energy. The program and the device for searching for a molecular stable structure execute the method.

The present invention relates to enzyme inhibitors. More specifically, the present invention relates to ligand-directed covalent modification of proteins; method of designing same; pharmaceutical formulation of same; and method of use.

The present invention relates to enzyme inhibitors. More specifically, the present invention relates to ligand-directed covalent modification of proteins; method of designing same; pharmaceutical formulation of same; and method of use.

In some implementations, the present solution can determine a first structural vector of a first chemical based on a chemical structure of the first chemical. The system can also determine first target vector of the first chemical based on at least one gene target for the first chemical. The system can use the structural vector and the target vector to generate a toxicity predictor score for the first chemical.

In some implementations, the present solution can determine a first structural vector of a first chemical based on a chemical structure of the first chemical. The system can also determine first target vector of the first chemical based on at least one gene target for the first chemical. The system can use the structural vector and the target vector to generate a toxicity predictor score for the first chemical.

A system for identifying and evaluating a pocket of a protein includes performing a Voronoi tessellation and developing a Voronoi diagram of a surface of the protein. All alpha-spheres on the surface of the protein are identified. The alpha-spheres are filtered based on radius and remaining alpha-spheres are clustered into alpha-clusters. At least one alpha-cluster is selected for quantitative evaluation. Alpha-sphere contact atoms are determined for a plurality of interaction points of the pocket. A Delaunay triangulation of the four contact atoms of each interaction point is performed. A plurality of alpha-spaces for each interaction point are determined. An alpha-atom and an alpha-atom contact surface area (ACSA) of each interaction point is determined. The pocket is ranked, a pocket-fragment complementarity is determined, and the pocket is matched between various conformations of the proteins.

A system for identifying and evaluating a pocket of a protein includes performing a Voronoi tessellation and developing a Voronoi diagram of a surface of the protein. All alpha-spheres on the surface of the protein are identified. The alpha-spheres are filtered based on radius and remaining alpha-spheres are clustered into alpha-clusters. At least one alpha-cluster is selected for quantitative evaluation. Alpha-sphere contact atoms are determined for a plurality of interaction points of the pocket. A Delaunay triangulation of the four contact atoms of each interaction point is performed. A plurality of alpha-spaces for each interaction point are determined. An alpha-atom and an alpha-atom contact surface area (ACSA) of each interaction point is determined. The pocket is ranked, a pocket-fragment complementarity is determined, and the pocket is matched between various conformations of the proteins.

An optimization apparatus includes a memory; and a processor coupled to the memory and the processor configured to: compute a local solution for a combinatorial optimization problem based on a first evaluation function representing the combinatorial optimization problem, select a state variable group targeted by partial problems from the plurality of state variables based on a first state variable whose value at the local solution is a predetermined value among the plurality of state variables included in the first evaluation function, a weight coefficient representing a magnitude of an interaction between the plurality of state variables held in a storage unit, and input selection region information, search a ground state for a second evaluation function representing the partial problems for the selected state variable group, and generate a whole solution by updating the local solution based on the partial solutions acquired by the ground state search.

An optimization apparatus includes a memory; and a processor coupled to the memory and the processor configured to: compute a local solution for a combinatorial optimization problem based on a first evaluation function representing the combinatorial optimization problem, select a state variable group targeted by partial problems from the plurality of state variables based on a first state variable whose value at the local solution is a predetermined value among the plurality of state variables included in the first evaluation function, a weight coefficient representing a magnitude of an interaction between the plurality of state variables held in a storage unit, and input selection region information, search a ground state for a second evaluation function representing the partial problems for the selected state variable group, and generate a whole solution by updating the local solution based on the partial solutions acquired by the ground state search.

A method and system for analyzing a target network relative to a background network of data using machine learning. The method includes extracting a first feature matrix from an adjacency matrix representative of the target network, extracting a second feature matrix from an adjacency matrix representative of the background network, generating a projection matrix based on the first and second feature matrices using a contrastive learning algorithm, generating a first contrastive matrix representation of the target network based on the projection matrix and the first feature matrix, generating a second contrastive matrix representation of the background network based on the projection matrix and the second feature matrix, and displaying a visualization of unique features of the target network relative to the background network based on the first contrastive matrix and the second contrastive matrix.