An artificial intelligence-based (AI-based) drug molecule processing method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product are provided. The method includes: determining a plurality of candidate drug molecules for a target protein; performing activity prediction based on the plurality of candidate drug molecules and the target protein, to obtain activity information of each candidate drug molecule; performing homology modeling on the target protein, to obtain a reference protein having a structure homologous with that of the target protein; performing molecular docking based on the reference protein and the plurality of candidate drug molecules, to obtain molecular docking information of each candidate drug molecule; and screening the plurality of candidate drug molecules based on the activity information of each candidate drug molecule and the molecular docking information of each candidate drug molecule, to obtain target drug molecules for the target protein.

A method of calculating a dielectric constant and a dielectric loss of a polymer material including the following steps is provided: providing a polymer having an optimized molecular geometry; analyzing a dipole moment autocorrelation function of the polymer having the optimized molecular geometry; fitting the dipole moment autocorrelation function of the polymer having the optimized molecular geometry via a relaxation function to obtain a corresponding fitting function; calculating a static permittivity of the polymer having the optimized molecular geometry; and obtaining a complex permittivity spectrum via the fitting function and the static permittivity, so as to calculate a corresponding dielectric constant and dielectric loss of the polymer having the optimized molecular geometry.

A method of calculating a dielectric constant and a dielectric loss of a polymer material including the following steps is provided: providing a polymer having an optimized molecular geometry; analyzing a dipole moment autocorrelation function of the polymer having the optimized molecular geometry; fitting the dipole moment autocorrelation function of the polymer having the optimized molecular geometry via a relaxation function to obtain a corresponding fitting function; calculating a static permittivity of the polymer having the optimized molecular geometry; and obtaining a complex permittivity spectrum via the fitting function and the static permittivity, so as to calculate a corresponding dielectric constant and dielectric loss of the polymer having the optimized molecular geometry.

An information processing method is performed by a computer for evaluating flammability of a mixed refrigerant material containing a plurality of components. The method includes: calculating, for each of the plurality of components, a second value obtained by multiplying a mixture ratio thereof in the mixed refrigerant material by a first value obtained based on numbers of hydrogen atoms, halogen atoms, and double bonds included in a molecular structure thereof; calculating a total sum of the second value calculated for each of the plurality of components; and classifying the mixed refrigerant material into a predetermined flammability class based on the total sum.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

A method for predicting retrosynthesis of a compound molecule and a related apparatus. The method includes: obtaining a target molecule and determining the target molecule as a root node in a tree structure, then, expanding the first leaf node through a target retrosynthesis model to obtain a plurality of second leaf nodes, further, recursively processing the predicted molecule set corresponding to the second leaf nodes and determining a terminal node that satisfies a preset condition; and then, traversing path information corresponding to the terminal node to determine a retrosynthetic path of the target molecule. In this way, a retrosynthesis prediction process of a multi-step reaction is realized. Leaf nodes are gradually recursively expanded and screened, to ensure the reliability of reactants determined by the retrosynthesis prediction process of the multi-step reaction, thereby improving the accuracy of prediction of retrosynthesis of compound molecules.

A method for predicting retrosynthesis of a compound molecule and a related apparatus. The method includes: obtaining a target molecule and determining the target molecule as a root node in a tree structure, then, expanding the first leaf node through a target retrosynthesis model to obtain a plurality of second leaf nodes, further, recursively processing the predicted molecule set corresponding to the second leaf nodes and determining a terminal node that satisfies a preset condition; and then, traversing path information corresponding to the terminal node to determine a retrosynthetic path of the target molecule. In this way, a retrosynthesis prediction process of a multi-step reaction is realized. Leaf nodes are gradually recursively expanded and screened, to ensure the reliability of reactants determined by the retrosynthesis prediction process of the multi-step reaction, thereby improving the accuracy of prediction of retrosynthesis of compound molecules.

This disclosure relates generally to system and method for molecular property prediction. Typically, message-pooling mechanism employed in molecular property prediction using conventional message passing neural networks (MPNN) causes over smoothing of the node embeddings of the molecular graph. The disclosed system utilizes edge conditioned identity mapping convolution neural network for the message passing phase. In message passing phase, the system computes an incoming aggregated message vector for each node of the plurality of nodes of the molecular graph based on encoded message received from neighboring nodes such that encoded message vector is generated by fusing a node information and an connecting edge information of the set of neighboring nodes of the node. The incoming aggregated message vector is utilized for computing updated hidden state vector of each node. A discriminative graph-level vector representation is computed by pooling the updated hidden state vectors from all the nodes of the molecular graph.

A system and method that given one or more input molecules, produces a contextualized summary of characteristics of related target molecules, e.g., proteins. Using a knowledge graph which is populated with all known molecules, input molecules are analyzed according to various similarity indexes which relate the input molecules to target proteins or other biological entities. The knowledge graph may also comprise scientific literature, governmental data (FDA clinical phase data), private research endeavors (general assays, etc.), and other related biological data. The summary produced may comprise target proteins that satisfy certain biological properties, general assay results (ADMET characteristics), related diseases, off-target molecule interactions (non-targeted molecules involved in a specific pathway or cascade), market opportunities, patents, experiments, and new hypothesis.