50 results about "Drug pair" patented technology

The invention discloses a circular RNA drug sensitivity correlation identification method based on integrated multi-instance learning. The circular RNA drug sensitivity correlation identification method comprises the following steps: collecting experimental verification circular RNA and drug sensitivity correlation data; establishing a feature representation model based on a heterogeneous network and vertexes; embedding a heterogeneous graph node into the model, and extracting deep feature representation of the node; designing a meta-path instance embedding projector, and generating a plurality of meta-path instances; a circular RNA and drug sensitivity association predictor is constructed and completed; constructing an integrated heterogeneous graph network deep learning model; and outputting the meta-path instance of the circular RNA and drug pair and the attention coefficient, and carrying out interpretable analysis. According to the method, integrated learning and a deep learning model are combined, so that the reliability of the model is improved; according to the invention, interpretable analysis is carried out by utilizing the meta-path and the attention coefficient, the potential action mechanism of the circular RNA associated with the drug sensitivity can be explained, and the guidance of medical research is facilitated.

The invention relates to a drug relocation method, in particular to a drug relocation method using neighborhood information and a weighted fusion network. The invention aims to solve the problems that the existing drug relocation method is a shallow prediction model, the characteristics of drugs and disease nodes cannot be deeply known, and the relocation result of the existing drug relocation method is biased to common infectious diseases. The method comprises the following steps: extracting a data sample of the action relationship of drugs on diseases; in the drug-to-disease effect relation graph, learning interaction characteristics between drugs and disease nearest neighbors by using a weighted graph convolutional network; aggregating the learned characteristics of the drugs and the diseases; hidden high-order nonlinear features are obtained through a multi-layer fusion network; inputting the action relationship of the drugs in the training set on the diseases into the model, training the model, and obtaining a final prediction model after multiple iterations; and inputting the drug pairs in the test set into the prediction model to obtain a prediction result. The invention belongs to the technical field of drug relocation.

The invention discloses an anti-cancer drug sensitivity prediction method and system based on bipartite graph and hypergraph learning, and belongs to the technical field of computer software. The method comprises the following steps: acquiring cell line and drug data and drug and cell line reaction original IC50 values by using an open source database, and standardizing the IC50 values; constructing a bipartite graph of the cell line and the drug, and obtaining embedded representation of the drug and the cell line by applying a graph convolutional network; super nodes are introduced to construct a cell line-drug isomerism hypergraph, and node features are learned through GCN; and finally, fusing the output of the GCN layer by applying an attention mechanism, and predicting the final association probability of the cell line-drug pair in combination with a full-connection layer. According to the method, combined exploration and collaborative optimization of the bipartite graph and the hypergraph are achieved, meanwhile, potential and complex relations between the medicine and the cell line are explored through the hypergraph, the quality of node feature representation is jointly improved, and therefore the association score between the medicine and the cell line is predicted more accurately.

The invention relates to a drug interaction prediction method and system based on multi-view comparative learning, and belongs to the technical field of natural language processing. According to the method, two channels of a drug molecular map and a biomedical knowledge map are constructed in parallel, structural and semantic features are extracted by using a pre-trained heterogeneous map neural network, and multi-view comparative learning guided by information gain is introduced for joint optimization, so that the generalization ability and robustness of the model to unknown drug pairs are enhanced. According to the method, system evaluation is carried out on the performance of the system in two types of prediction tasks (multi-type and multi-label) and three prediction scenes. Experimental results show that the method has excellent performance in all tasks and scenes. Further case analysis also verifies the effectiveness of the system in predicting the interaction type of the unseen drug pair.

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 discloses a drug incompatibility detection method based on fusion of a map and a large language model. Comprising the following steps: standardizing drug names in a prescription, mapping the drug names into uniform national standard codes, and generating a drug pair set; and extracting a drug interaction triple in combination with a large language model in the medical field, and constructing a heterogeneous drug knowledge graph. Based on a graph neural network and a comparative learning mechanism, embedded representation learning is performed on the knowledge graph, and the discrimination capability of drug node features is improved. Path retrieval and risk scoring are carried out on the drug pairs with the explicit interaction paths; and for a drug pair without an explicit path, screening alternative drugs by using chemical component similarity, inputting a pre-trained large language model through structured prompt, predicting a potential interaction relationship and credibility, and supplementing implicit risk information. According to the method, the problems of insufficient coverage and limited reasoning ability of the traditional knowledge graph are effectively solved, and the comprehensiveness and reliability of detection are improved.

The present invention relates to the field related to artificial intelligence and drug discovery. Specifically, a drug-drug interaction (DDI) prediction method based on RGDA-DDI is invented to solve the problem that the existing DDI prediction methods are not ideal. The method is divided into a data encoding module, a feature fusion module and a prediction module. The data encoding module is composed of multiple Residual-GAT submodules, each of which is composed of a graph attention layer, a Normalize layer and a SAGPooling layer, and is used to extract multi-scale features of the input drugs; the feature fusion module is composed of two dual-attention mechanism submodules, which are used for multi-scale drug feature fusion; finally, the fused features are input into the prediction module for prediction. This method overcomes the shortcomings of the existing DDI prediction methods, which lack modeling of multi-scale drug features and lack of mining of potential drug pairs (DDP) features. Experimental verification shows that the prediction performance of this method is better than the recently disclosed drug-drug interaction prediction method.

The application discloses a drug synergistic effect prediction method based on a biomedical knowledge graph and a Transformer, and relates to a drug synergistic effect prediction method. In order to solve the problem that a traditional drug combination discovery process mainly depends on clinical trials, which is not only time-consuming and laborious, but also high in cost and risky to patients, the application comprises the following steps: extracting drug data samples, generating a data set, dividing training and test sets, performing network training and testing; constructing a biomedical knowledge graph; converting a sequence list of a drug structure into a graph by using Rdkit; mining a subgraph of the knowledge graph by using a multi-hop subgraph mining network; learning feature representations of the knowledge network and the drug molecular graph by using a relation-aware Transformer, and performing fusion; performing synergistic effect prediction between drug pairs by using a multilayer perception machine; inputting drug pairs in a training set into the above model; inputting drug pairs in a test set into the prediction model to obtain a prediction result. The application belongs to the technical field of drug synergistic effect prediction.

The present invention discloses an Internet online diagnosis and treatment data processing system based on a big data model, which relates to the field of medical technology. The association rule analysis module uses weighted lifting to analyze the association between disease and drug treatment, which can accurately identify the relatively good matching relationship between disease and drug, and improve the pertinence and accuracy of drug recommendation. The online recommendation module uses candidate drug pairs, and combines the patient's real-time treatment situation, and dynamically analyzes the recovery effect of drugs in different time periods based on dynamic conditional probability. This mechanism not only ensures that the recommended drugs are highly matched with the patient's current condition, but also can adjust the drug selection according to the patient's feedback data. The system effectively avoids the problem of inaccurate recommendations caused by data sparsity or insufficient data in traditional systems by weighted processing of historical data and optimizing it in combination with data sparsity.

The embodiment of the present invention provides a method, device, equipment and storage medium for predicting drug interactions, which relates to the field of medical technology. Among them, the prediction method includes steps S1 to S9. S1 obtains the characteristics of multiple drugs and the reaction types between drugs. S2 constructs a drug feature matrix based on the characteristics of multiple drugs. S3 constructs a drug adjacency graph based on the reaction types between multiple drugs. S4 extracts drug feature information of different levels from the drug feature matrix through a deep neural network. S5 extracts neighbor topological structure information of different levels from the drug adjacency graph through a convolutional neural network. S6 fuses the feature vector and the structure vector to obtain the final embedded representation of each drug. S7 combines the final embedded representation of each drug to obtain multiple drug pair vectors. S8 uses the reaction type of the drug pair as a label and the drug pair vector as a training data set to train a classification model. S9 predicts the interaction type of unknown drug pairs through the classification model.

The invention provides an antiviral drug screening method and system based on inductive hypergraph learning, and a medium, and belongs to the technical field of bioinformatics, computational biology and artificial intelligence crossing, and the method comprises the following steps: S1, constructing a virus-drug adjacency matrix; s2, calculating a virus integration similar matrix and a drug integration similar matrix; s3, extracting statistic eigenvectors and graph theory eigenvectors of the viruses and the drugs and potential eigenvectors of the virus-drug pairs, and respectively merging the statistic eigenvectors and the graph theory eigenvectors according to rows to obtain a virus total eigenmatrix and a drug total eigenmatrix; s4, solving the target function by adopting a dual coordinate descent method to obtain an optimized projection parameter matrix; s5, calculating prediction scores from a virus perspective and a drug perspective, and averaging results to obtain a final virus-drug association prediction score matrix; and S6, screening the score of the row where the target virus is located, and sorting to obtain a final prediction result. The method not only improves the prediction performance, but also has good adaptability and popularization capability.

The invention provides a drug interaction relationship prediction method based on LLMs and ICL, belongs to the technical field of drug interaction relationship prediction, and solves the problems that a large language model is high in data set arrangement cost in the DDI-related characteristic prediction field, the generalization ability in a zero sample scene is limited, and the prediction efficiency is high. The method comprises the following steps: extracting a drug data sample, and making a data set; screening the drug data samples in the data set, and selecting the first K positive and negative sample drug pairs with the highest similarity; constructing a prompt of a drug relationship prediction model based on context learning and the selected positive and negative sample drug pairs; and mixing all the drug relationship prediction models by using MOE, evaluating scores of the drug relationship prediction models, and performing weighted fusion according to the scores to obtain a DDI final prediction result.

The present invention provides an antiviral drug screening method, system, and medium based on inductive hypergraph learning, belonging to the interdisciplinary field of bioinformatics, computational biology, and artificial intelligence. The method includes: S1. constructing a virus-drug adjacency matrix; S2. calculating a virus integration similarity matrix and a drug integration similarity matrix; S3. extracting statistical eigenvectors of viruses and drugs, graph theory eigenvectors, and potential eigenvectors of virus-drug pairs, and merging them row by row to obtain a total virus feature matrix and a total drug feature matrix; S4. solving the objective function using a dual coordinate descent method to obtain an optimized projection parameter matrix; S5. calculating prediction scores from the virus and drug perspectives, averaging the results to obtain a final virus-drug association prediction score matrix; S6. screening the scores of the target virus row and sorting them to obtain the final prediction result. The present invention not only improves prediction performance but also has good adaptability and generalizability.

The invention provides a traditional Chinese medicine prescription chemical cutting evaluation method and system based on a quantum heuristic Hamiltonian model, relates to the technical field of traditional Chinese medicine intelligence, can effectively capture complex nonlinear relations such as synergy / antagonism among medicines through interactive item energy Eint of Hamiltonian, and overcomes the limitation of linear superposition or rule matching of a traditional method. The whole prescription is regarded as an inseparable quantum state, the overall energy of the prescription is calculated, the thought of the overall view of traditional Chinese medicine is perfectly met, and the evaluation result is more comprehensive and more reasonable; fuzzy compatibility advantages and disadvantages are converted into specific numerical scores, a clear and objective quantitative basis is provided for formulated decision making of doctors or AI, and different schemes can be sorted and preferentially selected conveniently; by analyzing the value of the energy Eint of each interaction item in the Hamiltonian and the contribution to the total energy, collaborative drug pairs playing a leading role and potential conflict drug pairs in the prescription can be clearly revealed, and the credibility of a prescription recommendation result is improved.

The present application relates to a kind of for the evaluation reliability analysis method of drug interaction direction prediction model.It solves the problem that the evaluation result of drug interaction direction prediction in prior art is difficult to truly reflect the prediction reliability of model in actual application scene.It includes obtaining information data containing drug pair and interaction description;The role of drug in drug pair is distinguished to determine the affected drug and the acting drug;Direction label is generated based on interaction information, and the drug is encoded to construct input feature arranged in order of drug role;The prediction model is trained and evaluated under at least two different data division strategies;The evaluation results under different data division strategies are compared, and the evaluation reliability analysis result is output.The present application has the advantages that potential evaluation bias in the evaluation process can be identified for the interaction direction prediction task with drug role distinction, and the credibility and explainability of model evaluation result are improved.

The invention discloses a drug synergistic effect prediction method based on a biomedical knowledge graph and Transform, and relates to a drug synergistic effect prediction method. The invention aims to solve the problems that the traditional drug combination discovery process mainly depends on clinical tests, time and labor are wasted, the cost is high, and the patient also has risks. The method comprises the steps of extracting a drug data sample, generating a data set, dividing a training set and a test set, and performing network training and testing. Constructing a biomedical knowledge graph; converting the sequence representation of the drug structure into a graph by using Rdkit; mining sub-graphs of the knowledge graph by using the multi-hop sub-graph mining network; using a relation perception Transform to learn the feature representation of the knowledge network and the drug molecular map, and fusing the feature representation of the knowledge network and the feature representation of the drug molecular map; a multi-layer perceptron is used for predicting the synergistic effect between the drug pairs; inputting the drug pairs in the training set into the model; and inputting the drug pairs in the test set into the prediction model to obtain a prediction result. The invention belongs to the technical field of drug synergistic effect prediction.

The application discloses a kind of clinical drug abnormal use identification method based on artificial intelligence, comprising the following steps: obtaining target patient information, and data preprocessing is generated medication event sequence;According to medication event sequence, and extract one-hop neighborhood local subgraph as egonet;Risk weighted egonet structure features are calculated;According to hierarchical priority rule, medication event is layered, and the power law baseline parameter corresponding to each layer is obtained;Using OddBall graph anomaly detection, the power law deviation degree of each time window is calculated and forms deviation degree sequence;Variable point detection is carried out to deviation degree sequence to determine abnormal interval, and output abnormal use identification result;In abnormal interval, edge removal contribution evaluation is carried out to egonet edge set, and determines key drug pair and is associated with abnormal use identification result and outputs.The application improves the accuracy and reviewability of clinical drug abnormal use early warning.

The application discloses a drug interaction prediction method based on graph attention sampling, which firstly acquires drug pair data to be predicted, pre-processes the drug pair data to be predicted, obtains pre-processed drug pair data and drug molecular sequences, converts the pre-processed drug molecular sequences into molecular structure graphs, atomic vector matrices and molecular-atomic relationship lists through a molecular sequence conversion model, constructs an atomic adjacency matrix, a drug interaction network and a drug adjacency matrix, inputs the atomic vector matrix, the atomic adjacency matrix, the molecular-atomic relationship list, the drug interaction network and the drug adjacency matrix into a pre-trained drug interaction prediction model, and obtains a final drug interaction prediction result. The application can solve the technical problem that the existing drug interaction prediction method based on graph representation learning cannot consider both the drug molecular structure characteristics and the relationship information contained in the interaction network.

The application discloses a drug synergistic effect prediction method, system, device and medium based on heterogeneous graph tensor decomposition, and the prediction method comprises the following steps: obtaining a SMILES sequence of a drug, extracting a molecular structure feature of the drug, and obtaining a molecular structure feature representation of the drug; constructing a drug pair heterogeneous graph in each cell line, and obtaining a local interaction feature of the drug through a heterogeneous graph conversion network; performing Tucker decomposition on a three-channel heterogeneous graph relationship tensor, splicing the decomposition result with the local interaction feature of the drug, and extracting a global interaction feature vector of the drug; and predicting a synergistic score of a current drug-drug combination in a cell line according to the molecular structure feature representation of the drug and the global interaction feature vector of the drug. The application integrates the SMILES sequence of the drug and gene expression information of the drug pair in the cell line, and also converts the SMILES sequence into a drug molecular structure graph by using a graph convolution network, so as to extract the molecular structure feature of the drug. Such a design enables TensoGraph to more accurately reflect the complexity and diversity of the drug interaction network in the real world, thereby improving the prediction performance.

The invention relates to a drug interaction type prediction method fusing a multi-source feature cross-graph structure, and belongs to the technical field of deep learning. The method comprises the following steps: acquiring drug data to obtain a drug data set, and preprocessing the drug data set; performing Jaccard similarity calculation on the drug data to obtain chemical structure, biological target and enzyme action multi-dimensional data representation of the drug, and further obtaining initial feature representation of the drug; updating the initial feature representation of the medicine through a heterogeneous graph to obtain a medicine representation fused with a topological structure; the drug representation of the fusion topological structure fuses drug characteristics of different sources through an attention mechanism to obtain a final drug pair representation; the drug representations of the fused topological structures corresponding to the two drugs in the drug pair pass through a feature interleaving layer to obtain a final comprehensive representation; and the final drug pair representation and the final comprehensive representation are processed by a prediction module to obtain a drug interaction prediction probability vector. According to the invention, the accuracy and efficiency of drug interaction prediction are optimized.

The invention discloses an adverse drug reaction prediction method, system, equipment and medium, and relates to the technical field of drug response prediction.The method comprises the steps that tumor cell-drug data and a gene expression profile of a tumor cell line are obtained; the method comprises the following steps: constructing a heterogeneous bipartite graph by taking a tumor cell line and a drug in tumor cell-drug data as nodes and based on sensitive and drug-resistant edges defined by response values of tumor cell line-drug pairs; for nodes in the heterogeneous bipartite graph, based on a gene expression profile of a tumor cell line, cell gene expression characteristics are extracted through inductive learning, and drug characteristics are generated by fusing self characteristics of drugs and neighbor information of the drugs in the heterogeneous bipartite graph; and carrying out feature splicing on the drug features and the cell gene expression features to obtain each tumor cell-drug reaction pair, and carrying out prediction. According to the method, precision and generalization-technology secret details are balanced through direct push-inductive fusion learning, and prediction of new cell-new drug pairs is realized.

The invention belongs to the field of artificial intelligence and bioinformatics, relates to a drug interaction prediction method based on bidirectional event semantic guidance, and aims to improve the prediction accuracy. Comprising the following steps: extracting multi-modal drug characteristics of a to-be-predicted drug pair; constructing a bidirectional event semantic space; the bidirectional event semantic space refers to a semantic space obtained by constructing a corresponding negative drug interaction event description text for each positive drug interaction event description text to form positive and negative semantic pairs, encoding the positive and negative semantic pairs and then optimizing through a preset constraint condition. And carrying out semantic supervision alignment on the multi-modal drug features and the bidirectional event semantic space. And based on a result after semantic supervision alignment, combining a dynamic guidance coefficient adjustment strategy to zoom semantic guidance intensity, and outputting a drug interaction prediction result.

The application belongs to the technical field of drug interaction prediction, and provides a DDI prediction method and system based on a double-view robust causal substructure network, and the technical scheme is that a robust causal graph representation learning module identifies and eliminates mixed substructures in an input drug molecule graph and a drug pair two-part graph which have no causal contribution to DDI prediction or even produce interference through automatic generation of a tool variable, so as to generate a purer and more causal graph representation. Subsequently, a double-view substructure network module performs its unique double-view representation learning and prediction on the graph structure which has been robustly cut, so as to improve the accuracy, robustness and generalization ability of DDI prediction, especially when facing unknown drugs or complex interaction modes.

The application belongs to the field of artificial intelligence and bioinformatics, and relates to a drug interaction prediction method based on bidirectional event semantic guidance, aiming to improve the accuracy of prediction. It includes: extracting multi-modal drug features of the drug pair to be predicted. A bidirectional event semantic space is constructed. The bidirectional event semantic space refers to constructing a corresponding negative drug interaction event description text for each positive drug interaction event description text to form a positive-negative semantic pair. After encoding the positive-negative semantic pair, the semantic space obtained by optimizing the preset constraint condition is obtained. The multi-modal drug features are semantically supervised and aligned with the bidirectional event semantic space. Based on the result of semantic supervision and alignment, the semantic guidance intensity is scaled by combining a dynamic guidance coefficient adjustment strategy, and a drug interaction prediction result is output.

The present application relates to a protein drug reaction prediction method based on EM fusion learning, comprising: 1) constructing a data set containing protein nodes, drug nodes and intermediate nodes into a text attribute graph; 2) embedding the protein amino acid sequence and the drug molecule SMILES sequence to obtain corresponding sequence representations; 3) constructing a transformer-based protein-drug reaction prediction model; 4) constructing a GNN-based protein-drug reaction prediction model; 5) using a variational EM framework to alternately update the above two models to obtain an EM fusion protein-drug reaction prediction model; 6) inputting the to-be-tested protein amino acid sequence and the to-be-tested drug SMILES sequence into the above prediction model to output the reaction prediction result of the to-be-tested protein-drug pair. The present application learns the topological information in the protein-drug network to realize protein-drug reaction prediction.

This invention discloses the application of a safflower-blue safflower herb pair composition in the preparation of drugs for treating hepatocellular carcinoma and / or inhibiting liver fibrosis; wherein the safflower-blue safflower herb pair composition is composed of total flavonoids from safflower and total flavonoids from blue safflower, with a mass ratio of (1-3):1. Experiments have shown that the safflower-blue safflower herb pair composition can treat hepatocellular carcinoma and / or inhibit liver fibrosis, and its efficacy is significantly higher than that of total flavonoids from safflower or blue safflower alone. This invention has significant theoretical value and clinical significance.

The method for predicting drug pair interaction based on strong negative sample generated by multi-scale drug information involves the field of bio-information technology.In order to solve the problems that the existing technology only depends on the experimental data for drug interaction judgment, the model trained on weak negative samples selected by random negative sampling shows poor robustness and prediction performance, and most DDI prediction methods have poor prediction accuracy for some interaction categories under the cold start setting due to the skew distribution of data, the technical scheme provided by the present application is as follows: the method comprises the following steps: learning the representation of drug knowledge graph, drug structure and drug physical and chemical attribute information; obtaining a drug similarity matrix according to the drug multi-scale information representation, and constructing a drug similarity network; the step of fusing the drug similarity network; the step of generating strong negative samples for the target drug interaction data set.The method is suitable for application in the work of predicting the interaction between drugs.

The application discloses a drug interaction prediction method and system based on topology-aware attention and sparse mixed experts. Firstly, the adjacent topological bias of molecular substructure is injected into the self-attention mechanism through two-dimensional topology-aware coding to extract the drug microstructure features that reserve topological connectivity. Secondly, the macroscopic routing network and multiple microscopic interaction experts are connected through a sparse gating mechanism to form a sparse mixed expert network. The macroscopic features are used as guide signals to input the routing network, and the specific microscopic interaction experts that match the current drug pair are dynamically activated. Then, within the activated microscopic interaction experts, the induced fitting effect between drug molecules is dynamically captured by combining the parameter-shared bidirectional cross-attention mechanism. The application can accurately predict the type of drug interaction and the synergistic / antagonistic relationship, significantly improve the performance of the model on long-tail distribution data, and has high computational efficiency and biochemical interpretability.

The application belongs to the technical field of bioinformatics and artificial intelligence, and specifically discloses a bad drug interaction prediction method and system based on double-view motif learning, which comprises the following steps: constructing atom-level molecular graphs and motif-level molecular graphs of drug pairs, extracting atom-level features and aggregating them into motif-level molecular graphs; constructing a similarity-guided double-view interaction module to learn the interaction relationship between motifs within a drug and the interaction relationship between motifs across drugs to obtain motif representations after double-view interaction, and then constructing a global interaction vector and calculating attention feature vectors of two drugs; and inputting the attention feature vectors after splicing into a multilayer perceptron to output a prediction result of drug interaction. The application solves the problems of the existing DDI prediction method, such as lack of explicit modeling of substructures with chemical significance, lack of guidance of chemical prior knowledge for learning of cross-drug substructure interaction, and inherent information loss and ambiguity of uniqueness in motif-based modeling.

The application discloses a drug interaction prediction method and system based on a graph neural network and a multiple attention mechanism. The method comprises the following steps: converting SMILES sequences of a drug pair into graph data, and obtaining an embedding matrix of the drug pair by using a multilayer GIN operation; extracting a self-attention feature matrix of the drug pair from the embedding matrix of the drug by using a self-attention mechanism encoder, calculating a cosine similarity matrix of the drug pair, and obtaining a self-attention feature vector of the drug pair after a flattening operation; processing the embedding matrix of the drug pair by using an interactive attention mechanism encoder, obtaining an interactive attention coefficient feature matrix, performing average pooling operation on the interactive attention coefficient feature matrix of the two drugs respectively, then performing standardization, and then obtaining an interactive feature vector of the drug pair; and inputting the self-attention feature vector and the interactive feature vector of the drug pair into a multilayer perceptron to predict the interaction between the drug pair. The application can better predict the interaction between drugs.