2 results about "Molecular Databases" patented technology

This invention relates to a method for constructing a machine learning potential energy model based on hierarchical active learning, comprising the following steps: constructing a database of background solvent molecules and lithium salt molecules; initializing a machine learning potential energy model committee; outer active learning automatically exploring the chemical species composition space of the electrolyte, generating electrolyte formulations and initial structures; determining whether a structure needs to be included in the labeling range based on uncertainty calculations; automatically constructing a liquid phase environment based on classical force field simulation methods; performing high-precision simulations based on first-principles calculations and labeling the energy and force values ​​of the structures; inner active learning driving the machine learning potential energy model to explore the configuration space and label the energy and force values ​​of structures with high uncertainty; obtaining a first-principles structure database of the real liquid phase environment through several iterations; and training to obtain the final high-performance machine learning potential energy model. This invention systematically and comprehensively samples the chemical species composition space of the electrolyte and the molecular simulation configuration space based on hierarchical active learning, thereby ensuring the predictive performance and simulation accuracy of the machine learning potential model on unknown and complex electrolyte systems.

The application discloses a drug virtual screening method based on hash learning, which comprises the following steps: firstly, obtaining a protein-molecule complex dataset; defining protein and molecule encoders respectively; defining a contrast learning objective function to learn the similarity information of the protein and the molecule; defining a multi-modal hash objective function to learn the binary vector of the protein and the molecule; constructing a final loss function by combining the contrast learning and the multi-modal hash objective function, and training a model; and representing molecules in a molecule database as binary vectors. When performing drug virtual screening, a protein target is represented as a binary vector. The Hamming distance between the binary vector of the protein target and the binary vectors in the molecule database is calculated, or an inverted index is constructed from the binary vector database to retrieve the most likely binding molecules. According to actual requirements, a certain proportion of molecules are selected as candidate drug molecules. The application improves the precision of drug virtual screening, reduces storage overhead, and improves retrieval speed.