267 results about "Molecular graph" patented technology

The invention discloses a drug combination risk prediction method and device based on multi-source feature fusion and comparative learning, equipment and a medium, and relates to the technical field of drug combination prediction. The drug combination risk prediction method comprises the following steps: acquiring a drug data set; and obtaining a feature map according to the drug data set. And according to the feature map, carrying out adaptive feature extraction on the molecular map structure to obtain molecular map features of the medicine. And defining molecular map features as structural features. And inputting the molecular graph features into a multi-layer cascaded graph convolutional network, extracting high-order topological features in a drug network, and obtaining relation features. According to the drug data set, similarity features are calculated, and interactive embedding features are extracted; according to the structural features and the similarity features, potential correlation and differences between the features are mined through a comparative learning mechanism, and structural comparative learning features and similarity comparative learning features are obtained; and performing feature fusion and feature alignment on the features to obtain fused features. And predicting the drug combination risk according to the fusion features.

The invention belongs to the field of bioinformatics, and relates to a molecular property prediction method based on multi-modal gating and comparative learning, which comprises the technologies of comparative learning, graph neural network, cross-modal alignment, gating attention and the like. Firstly, data standardization and graph construction are carried out, and molecular fingerprint embedding is extracted; secondly, a heterogeneous dual-channel graph coding architecture is adopted, one path captures atom short-range interaction through an attention mechanism, the other path integrates a molecular global structure and long-range dependence, and complementary molecular representation is generated; then, a cross-modal attention mechanism is introduced, bidirectional association of graph and fingerprint features is achieved, and modal weights are adaptively and dynamically distributed through a gating fusion module; and finally, a comparison pre-training strategy is adopted, a molecular graph and fingerprints are utilized to construct a sample pair, and discriminative molecular representation is learned on unlabeled data. According to the method, the accuracy of molecular property prediction is remarkably improved, and an efficient and reliable calculation tool is provided for virtual drug screening and lead compound optimization.

The invention relates to the technical field of computer-aided drug design, in particular to a drug molecule screening and optimizing method based on artificial intelligence prediction, which comprises the following steps: S1, obtaining a dynamic protein conformation set and molecular multi-dimensional characterization: obtaining a dynamic conformation set of a target protein and a physicochemical property spatial distribution diagram of a binding pocket of the dynamic conformation set, a two-dimensional molecular map topological structure and three-dimensional conformation coordinates of the drug molecules are obtained; s2, multi-modal fusion prediction is carried out; s3, generating interpretable optimization guidance; and S4, automatic iterative optimization: performing batch prediction and screening on the new candidate molecular structure, taking the screened optimal molecule as a new starting point, repeatedly executing the interpretability optimization guidance generation step and the step until an iteration termination condition is met, and outputting a final optimized molecule list. Through the multi-modal fusion deep learning model, the interaction strength of the drug molecules and the target protein can be quickly and accurately predicted, and the screening efficiency of the drug molecules is greatly improved.

The invention discloses a drug resistance prediction method and system based on comparative learning and multi-modal fusion, and the method comprises the steps: firstly generating a molecular map and a molecular fingerprint based on the SMILES of a target drug, and extracting the molecular features of the drug through a comparative learning model constructed through combining a map attention network and a map convolution network; and then, acquiring protein expression, gene expression and metabolic expression data from the target tissue cells, extracting modal features through a deep convolutional network, a Transform encoder and a multi-dimensional attention network, and realizing adaptive fusion of the multi-modal features through a heterogeneous interactive attention mechanism. And finally, jointly inputting the fused multi-modal features and drug molecular features into a multi-layer sensor to realize high-precision prediction of the drug resistance of cells to drugs. By introducing a contrast learning and multi-modal feature fusion mechanism, the characterization capability and prediction precision of the model are effectively improved, and efficient and reliable support can be provided for drug screening and clinical decision making.

The invention provides a drug target binding affinity prediction method based on multi-modal data fusion. The method comprises the following steps: firstly, extracting sequence feature information of drug SMILES and target FASTA, then constructing an affinity graph, modeling drug molecules and target protein molecules into an undirected graph, and extracting molecular-level features of atoms, bonds, residues and contact. And fusing the hierarchical graph structure information of the affinity graph and the molecular graph to obtain the graph structure feature representation of the drug-target spot. The sequence feature information and the graph structure feature representation are further fused by using intramolecular and intermolecular attention fusion mechanisms. And finally, performing affinity prediction by using the fused features, and outputting a drug-target binding affinity score. According to the method, sequence and structural information are effectively fused, the accuracy of drug target affinity prediction is improved, and the problems of insufficient information fusion and insufficient structural information utilization in an existing method are solved.

The invention provides a drug response prediction method based on a gene relation network and a drug substructure. The drug response prediction method comprises the following steps: performing feature extraction on three multi-modal features of gene expression, copy number variation and mutation of a cell line by adopting an enhanced graph attention network; acquiring a substructure of the medicine by using a gating message passing neural network, and extracting features by enhancing a graph attention network; constructing two complementary graph structures, namely an atom-bond graph and a bond-angle graph, and performing feature extraction and message passing on the two graphs by using a graph convolutional neural network so as to extract 3D features of the medicine; the characteristics of the drug and the cell line are integrated through concat operation, and drug response prediction is carried out through mlp. According to the drug response prediction method provided by the invention, cell line features are extracted by establishing and using three kinds of omics data with different emphasis, and drug feature extraction is performed by using a drug molecular map, a drug 3D structure, a drug molecular fingerprint and a drug substructure relationship.

The invention discloses a reaction site prediction method and device based on chemical and physical prior driving, and the method comprises the steps: extracting set features through the multi-modal input of a fusion molecular map, an SMILES sequence and a three-dimensional conformation; generating atomic embedding by using a message passing neural network, and calculating a mixed feature fusing a topological path and a three-dimensional distance; combining the key type weight to construct a graph position code of chemical environment correction; injecting the mixed distance and the charge difference into a Transform attention mechanism, and explicitly modeling an inter-atomic long-range electron effect; a model is jointly trained through double tasks of comparative learning and mask prediction, the comparative learning adopts a directional negative sample to enhance generalization, and mask prediction synchronously recovers an atom type and a charge transfer matrix; and finally, injecting quantum chemistry priori constraint attention weights such as a Fuzzy well function, outputting an atomic-scale reaction activity probability, generating a thermodynamic diagram, and realizing high-precision and interpretable active site labeling. According to the method, the drug design and reaction mechanism analysis efficiency can be remarkably improved.

The invention provides a molecular attribute prediction method introducing domain knowledge, which belongs to the technical field of meta-learning, integrates molecular graph information and molecular chemical information through a two-channel feature coding architecture, fuses small sample learning of molecular graph structure and chemical domain knowledge, and optimizes the molecular attribute through dynamic feature fusion and task perception optimization mechanism. The problem of insufficient model generalization ability caused by data scarcity in molecular attribute prediction is solved, so that multi-modal molecular attribute prediction is realized, and the prediction precision and interpretability are improved.

The invention relates to the field of computer-aided drug design (CADD) and molecular informatics, in particular to a multi-modal representation learning method based on cyclopeptide molecules, which is used for predicting cell membrane permeability of cyclopeptide. The method mainly comprises the following steps: (1) data collection: integrating cyclic peptide permeability data from a ChEMBL database, a CycPeptMPDB database and a CyclicPepeda database and patent literatures; (2) multi-modal learning: for different modal data, a deep learning model is adopted to extract feature representations of the data; the method comprises the following steps of: encoding an SMILES sequence by using ChemBERTa (ChemBERTa); using Vision Transform to extract molecular image features, and learning a molecular image structure and 3D coordinate information based on GNN; (3) multi-modal feature fusion: adopting a self-adaptive extensible fusion mechanism, integrating SMILES feature information into image, graph and 3D coordinate features through a cross-modal feature fusion mechanism, and splicing all modal features to obtain multi-modal molecular representation; and (4) permeability prediction: sending the multi-modal molecular representation into a full connection layer for regression prediction so as to evaluate the permeability of the cyclopeptide.

The invention discloses a multi-expert molecular attribute prediction method based on substructure information bottleneck, and aims to solve the problems that an existing method cannot fully excavate molecular substructure information and lacks an effective feature filtering mechanism. Substructure representation is coded through a graph neural network; constructing a substructure information bottleneck module, and filtering redundant features by taking maximization of mutual information of a substructure and a target attribute and minimization of mutual information of the substructure and a complete molecular graph as an optimization target; dynamically distributing the substructures to an expert model based on a skeleton and a functional group in combination with a gating mechanism, and calculating a distribution probability by utilizing a trainable clustering center; updating the model by adopting a double-layer strategy of optimizing discriminator parameters through internal circulation and optimizing main model parameters through external circulation; and finally, weighting and fusing expert output to realize attribute prediction. The method significantly improves the accuracy and robustness of molecular attribute prediction, and is suitable for the fields of drug research and development and material design.

The invention discloses a drug target affinity prediction system based on cross-modal feature fusion, and relates to the technical field of biological information. The invention aims to solve the problem of low prediction precision of the existing DTA prediction method. The method comprises the following steps: preprocessing a drug SMILES character string and a protein amino acid sequence to obtain a drug molecular map, a drug SMILES sequence embedding characteristic, a protein contact map and a protein amino acid sequence embedding characteristic; according to the drug molecular diagram and the protein contact diagram, drug diagram modal characteristics and protein diagram modal characteristics are obtained; obtaining drug sequence modal characteristics and protein sequence modal characteristics by using drug SMILES sequence embedding characteristics and protein amino acid sequence embedding characteristics; fusing the drug pattern modal features and the drug sequence modal features to obtain drug fusion features, and fusing the protein pattern modal features and the protein sequence modal features to obtain protein fusion features; and acquiring the drug target affinity by using the drug fusion feature and the protein fusion feature. The method is used for predicting the affinity of the drug target.

The invention belongs to the field of bioinformatics, and particularly relates to a drug and target effect prediction method based on a Floyd algorithm network, which integrates technical means such as a Floyd algorithm, deep learning, a Kolmogorov-Arnod network, an attention mechanism and the like. The method comprises the following steps: firstly, preprocessing a drug molecular map and a protein map, extracting molecular structure features by using a Morgan fingerprint algorithm, and introducing a second-generation protein sequence pre-training model of an evolution scale modeling framework to extract protein semantic features; and then, respectively inputting the embedded features of the drug and the protein into a parallel Kolmogorov-Arnod network constructed by a Floyd algorithm to carry out feature mapping, and introducing a joint attention mechanism to model a high-dimensional interaction relationship between drug atoms and protein residues. Experimental results show that the method disclosed by the invention has relatively high accuracy and generalization ability in a drug-target affinity prediction task.

The invention relates to the technical field of artificial intelligence application, and discloses an enzyme EC number prediction method, and the method comprises the steps: obtaining the sample sequence characteristics of a to-be-predicted sample containing a substrate SMILES sequence and a product SMILES sequence through a target BERT model; constructing a molecular object and feature coding based on atom mapping, atom truncation and sequence analysis, constructing a reaction graph of a to-be-predicted sample, inputting the reaction graph into a target graph isomorphic neural network, and constructing molecular graph features of the to-be-predicted sample based on a recursive neighborhood aggregation mechanism; and fusing the sample sequence features of the to-be-predicted sample with the molecular map features by using a bidirectional cross attention mechanism to obtain multi-modal features, inputting the multi-modal features into the multi-layer perceptron, and obtaining the prediction probability of the enzyme EC number of the to-be-predicted sample. According to the method, efficient and accurate end-to-end prediction of enzyme EC numbering is realized through the multi-dimensional chemical spatial characteristics of the collaborative modeling reaction.

The invention relates to the technical field of molecular property prediction, in particular to a molecular property prediction method based on double-graph collaborative representation and cross-view feature fusion, which comprises the following steps: automatically identifying key functional groups in a molecular graph through a graph attention mechanism (GAT), and constructing a Motif graph to represent a local chemical environment of the molecular graph; the Motif graph can effectively capture local structure characteristics in molecules. The Motif graph and the molecular graph are respectively processed through GAT, information of global features and local features is respectively extracted, and the two features are fused through cross attention to obtain fused molecular graph features, so that more comprehensive molecular feature representation is obtained, and the comprehensiveness of molecular representation and the performance of the model are improved. Molecular fingerprint information is jointly processed by using a bidirectional gating cycle unit (Bi-GRU) and a multi-head attention network, the expression ability of the model to complex molecular fingerprint data is enhanced, and the accuracy of molecular property prediction and the generalization ability of the model are improved.

The invention discloses an OLED material stability prediction method based on a heterogeneous graph neural network, and the method comprises the steps: constructing a molecular graph based on the molecular structure of an OLED material, carrying out the data enhancement of the molecular graph, fusing the features of the data-enhanced molecular graph with multi-modal data, and obtaining the feature data of the molecular structure of the OLED material; oLED material molecular structure feature data are transmitted to a heterogeneous graph neural network, deep feature information in a molecular graph is learned, and OLED material molecular structure fusion features are obtained; and constructing an OLED material thermal stability prediction model based on the depth operator network, and inputting the OLED material molecular structure feature data and the OLED material molecular structure fusion features into the OLED material thermal stability prediction model to obtain a prediction result of the OLED material stability. According to the method, the stability prediction performance of the OLED material can be remarkably improved, and a new path is provided for material design and optimization.

The embodiment of the invention discloses a training method, a prediction method, a device and equipment for a molecular attribute prediction model, and relates to the field of artificial intelligence assisted pharmacy. Comprising the steps that in a first training stage, in order to improve the interpretability of a sub-graph extraction model, the sub-graph extraction model and a sub-graph prediction model are trained based on a sample molecular graph, and the sub-graph extraction model obtained through training is used for extracting at least two interpretable key sub-graphs from the molecular graph; and in a second training stage, on the basis of the sub-graph extraction model obtained by training in the first training stage, training the sub-graph prediction model based on the sample sub-graph by taking improvement of the distribution external generalization ability of the sub-graph prediction model as a target, the sub-graph prediction model obtained through training is used for predicting molecular attributes of the molecular graph based on the at least two key sub-graphs of the molecular graph. By adopting the method provided by the invention, the interpretability of molecular attribute prediction and the generalization ability outside distribution can be improved.

The invention discloses a contrastive learning molecular property prediction method based on an anti-fact and a large language model, and belongs to the technical field of molecular representation learning combining a large language model and a graph neural network, and the method comprises the following steps: generating an original molecular graph through a molecular SMILES character string; generating a skeleton disturbance diagram and a functional group disturbance diagram; ensuring that the generated perturbation diagram is an anti-fact hard negative sample; generating a molecular natural language description through a large language model, and converting the molecular natural language description into a molecular semantic embedding vector by using a small language model; performing comparative learning among the original molecular graph, the positive sample and the anti-fact hard negative sample; original molecular graph embedding and molecular semantic embedding obtained after comparative learning are fused, and downstream molecular property prediction is carried out. According to the method, hard negative samples can be generated through an anti-fact mechanism, the diversity of molecular characterization modes can be ensured through a large language model, and the accuracy of comparative learning during molecular property prediction is remarkably improved.

A molecular structure prediction method based on a multi-granularity graph neural network comprises the steps of data set preprocessing, multi-granularity level data feature construction, multi-granularity graph neural network construction, multi-granularity graph neural network training, multi-granularity graph neural network verification and multi-granularity graph neural network testing. The key connection relation between atoms, the incidence relation of substructure keys and graph-level global feature representation are determined in the molecular graph, and the problem of local information loss in graph representation learning is effectively relieved; a message passing mechanism of graph neural sub-networks with different granularities is improved, a multi-granularity molecular graph data structure is trained, unique information of each hierarchical molecular structure is fully utilized, and the modeling capability of a model for a complex chemical structure is enhanced. The method has the advantages of being high in prediction accuracy, reducing errors, relieving local information loss existing in the prediction method, being good in prediction interpretability and the like, and can be applied to the technical fields of drug discovery, molecular property prediction and the like.

The invention relates to a semi-template drug molecule inverse synthesis prediction method based on graph-sequence pre-training. The method comprises the following steps: selecting a public chemical molecule data set N; selecting a molecular sample from the N, and then extracting a molecular graph and a word segmentation sequence from the molecular sample; obtaining a sequence embedding matrix and a graph embedding matrix of the i by utilizing the word segmentation sequence of the i and the molecular graph; constructing an overall model M and a loss function Ltotal used for training the M; and training M in two stages by using AdamW to obtain a trained model M. By adopting the method disclosed by the invention, reactant atoms for generating a product can be accurately reduced, a starting material of the product is defined, and the research and development success rate of medicines or other products is improved.

The invention discloses a molecular performance prediction method and system based on layered characterization, and belongs to the field of molecular property prediction. The method comprises the following steps: constructing a multi-layer graph structure, including an atomic layer, a group layer and a molecular layer, based on a molecular graph structure and an SMILES sequence; designing a hierarchical information interaction mechanism combining intra-layer polymerization and inter-layer information transfer, and performing multilayer structure semantic fusion to obtain characterization of an atomic layer, a group layer and a molecular layer; a hierarchical graph representation fusion module is constructed based on an attention mechanism, differential fusion is carried out on representation of an atomic layer, a group layer and a molecular layer, expression of key structure features is automatically enhanced, and unified fusion molecular representation is constructed; according to the method, a prediction task-oriented loss function is constructed, fusion molecular representation is input into a full-connection neural network prediction model, end-to-end molecular performance prediction is realized by training and learning a mapping relation between the fusion molecular representation and molecular properties, and classification and regression performance in a molecular property prediction task is remarkably improved.

The invention discloses a compound smell prediction method based on an isotropic graph neural network. The method comprises the following steps: (1) constructing molecular graph representation; (2) constructing an isovariant graph neural network model; (3) preparing training data; (4) training the model; (5) evaluating the model; and (6) predicting the odor of the compound. The invention further discloses a system of the compound smell prediction method based on the isotropic graph neural network. The method provided by the invention has relatively high prediction accuracy and relatively strong generalization ability.

The invention discloses a molecular map feature extraction method and device based on multi-scale information and a medium, and relates to the technical field of molecular activity prediction. The molecular map feature extraction method comprises the following steps: extracting atomic-scale features, bond-scale features and conformation features of target molecules; and fusing the atomic-level features, the bond-level features and the conformational features to obtain molecular map features of the target molecules. According to the method, the atomic-level features, the bond-level features and the conformation features of the molecules are extracted and fused to serve as input features of activity prediction, understanding of a model on the relationship between the atomic features, the bond features and the spatial features of the molecules and the activity is promoted, and therefore the molecular activity is predicted more comprehensively.

The invention relates to an enzyme turnover number prediction method and system fused with multi-modal characteristics of an enzymatic reaction, and belongs to the technical field of bioinformatics. Comprising the following steps: respectively constructing an optimized protein pre-training model and an optimized chemical reaction pre-training model; extracting sequence features of a to-be-detected amino acid sequence by utilizing the optimized protein pre-training model to obtain an enzyme sequence feature matrix; extracting sequence features of an enzymatic reaction SMILES sequence to be detected by utilizing the optimized chemical reaction pre-training model to obtain an enzymatic reaction SMILES feature matrix; using molecular fingerprints to represent substrate and product molecular sets, and extracting a set feature matrix of the two molecular sets through a graph attention network; the method comprises the following steps: representing substrate and product molecule sets by using a molecular graph, and extracting internal feature matrixes of molecules in the two molecule sets through a graph isomorphic network; and carrying out feature enhancement on the obtained feature matrix so as to obtain an enzyme turnover number prediction value. The method improves the stability and precision of the prediction result, and has the advantages of low cost and short period.

The invention provides a molecular-graph-oriented primitive-level representation learning method and system, and the method comprises the steps: carrying out the noise addition and reconstruction of an original molecular graph based on a graph diffusion model, calculating an edge reconstruction error, and dividing the original molecular graph into a plurality of primitive sub-graphs according to the edge reconstruction error; constructing an atomic view and a primitive view, and encoding the atomic view and the primitive view by using a graph neural network encoder to obtain an atomic embedding matrix and a primitive embedding matrix; and constructing a positive and negative sample pair based on the atomic view and the primitive view, and optimizing an atomic embedding matrix and a primitive embedding matrix by adopting a Babontwin double-view contrast loss function to realize cross-granularity expression alignment. According to the method, molecular primitives are extracted in a self-supervised mode through the diffusion model, systematic defects of a traditional method in the aspects of cross-granularity structure modeling, semantic guidance contrast learning and multi-level expression fusion are overcome through atom-primitive double-view alignment, and the semantic completeness and task generalization ability of molecular expression are remarkably improved.

In at least one example, a method for molecular graph structure based modeling to predict properties of polymers utilizing local cluster includes generating a data set that includes a respective structure and properties for each of a plurality of monomers corresponding to a designated polymer, converting the respective structures to graph connectivity structures, determining a plurality of local clusters based on the plurality of monomers, calculating a respective polymeric property of each of the plurality of local clusters based on density functional theory (DFT), inputting monomer data to a machine learning model trained to determine an unknown polymeric property of a designated polymer from an output value of a graph neural network and the respective polymeric properties for a plurality of identified local clusters from the designated polymer, and receiving a prediction of the unknown polymeric property of the designated polymer from the machine learning model.

The invention discloses a pre-training model and multi-source coding feature fusion-based water pollutant molecular property prediction method and system, and relates to the technical field of environmental science and artificial intelligence crossing. Comprising the steps of collecting pollutant data; the collected pollutant data is preprocessed; taking SMILES as a molecular input basis, and extracting molecular features; according to the molecular features, feature vectors are obtained from an encoder and then input to a vector interaction module for feature fusion; and embedding the comprehensive molecules obtained after feature fusion into an expert mixed structure module to obtain comprehensive representation of an expert mechanism, inputting the comprehensive representation of the expert mechanism into a preset prediction head, and completing prediction of molecular properties through the prediction head. According to the method, the molecular language model features, the molecular graph neural network features and the molecular descriptor features are integrated, and feature fusion is carried out by utilizing an attention mechanism and residual connection, so that high-precision prediction of the molecular properties of pollutants is realized.

The invention provides a method for constructing a drug interaction prediction model based on multi-view feature representation, and the method comprises the steps: obtaining the node embedding representation of each drug from a drug knowledge graph through a heterogeneous graph neural network, and obtaining a first feature vector of each drug pair; utilizing a graph attention neural network to obtain graph embedded representation of each drug from the drug molecular graph to obtain a second feature vector of each drug pair, and obtaining a third feature vector of each drug pair from the drug bipartite graph; the first feature vector, the second feature vector and the third feature vector of each drug pair serve as input, the real DDI of each drug pair serves as output, the prediction probability of the multi-layer perceptron is infinitely close to the real DDI of each drug pair by adjusting parameters of the multi-layer perceptron, and a drug interaction prediction model is obtained. According to the method, the distinction degree of the DDI features is improved by using multi-view feature representation, so that the model prediction robustness is enhanced, and meanwhile, the problem of overfitting when the DDI of a new drug is predicted is solved.

The invention belongs to the technical field of active site prediction, and particularly relates to an enzyme active site prediction method based on a graph neural network. In order to realize high-precision prediction of active sites, the enzyme active site prediction model HFGN adopts a double-branch architecture: enzyme branches integrate a three-dimensional structure, PLM embedding, homology score and EC function annotation, and realize multi-source feature fusion through an attention mechanism; the reaction branch is based on molecular maps of a substrate and a product, chemical reaction specificity is modeled through a map neural network, and finally enzyme-reaction context sensing embedding is realized through a cross-modal attention mechanism, so that the prediction precision and generalization ability of residue-level active sites are improved.

The invention discloses a high-precision molecular property prediction method and device based on multi-modal information. The method comprises the following steps: acquiring a molecular map, a molecular sequence and a molecular three-dimensional geometric configuration of a molecule; decomposing each molecular graph into a group of motifs, constructing a multi-stage pre-training framework to capture multi-scale information in the molecule, and performing molecular graph training on the molecule to obtain a molecular graph feature vector; designing an information transmission mechanism based on distance and angle, and carrying out learning training on the molecular three-dimensional geometric configuration to obtain a molecular geometric feature vector; preprocessing the molecular sequence feature vector of the molecule, and learning the molecular sequence information of the molecule to obtain a molecular sequence feature vector; and according to the molecular map feature vector, the molecular geometric feature vector and the molecular sequence feature vector, designing a molecular property prediction model based on a cross-modal cross attention mechanism to perform molecular property prediction. The method can enhance the robustness and accuracy of molecular property prediction.

The invention provides a task processing method based on intermolecular interaction, a training method based on intermolecular interaction and a device thereof. Based on a connecting edge formed between a first node in the first molecular graph and a second node in the second molecular graph, respectively performing embedding feature representation on the first node and the second node to obtain a first node embedding feature and a second node embedding feature; identifying a first action node feature and a second action node feature; based on the first action node feature and the second action node feature, determining target substructures in chemical structures indicated by the first molecular graph and the second molecular graph respectively; the task matched with the first molecule and the second molecule is a regression task, and performing regression prediction on the target substructures corresponding to the first molecule graph and the second molecule graph to obtain a processing result; the task matched with the first molecule and the second molecule is a classification task, classification is carried out based on the target substructures corresponding to the first molecule graph and the second molecule graph, and a classification result is obtained.