46 results about "Extraction drug" patented technology

The invention discloses an intelligent decision-making method for a cerebral ischemia drug administration time window, and relates to the technical field of intelligent decision-making. The method comprises the following steps: S1, acquiring parameters, and setting a cerebral ischemia drug configuration scheme; s2, extracting a medicine characteristic parameter set and a medicine taking influence parameter set; s3, calculating a drug combination risk parameter set; s4, performing hierarchical classification processing on the drug combination risk parameter set, and performing drug correlation analysis; s5, performing weighted fusion on a correlation analysis result in combination with a drug influence attenuation rule, generating a drug administration time window evaluation parameter, and adding a label; and S6, according to the parameters, the labels and the configuration scheme, generating a cerebral ischemia drug administration time window intelligent decision scheme, and performing storage and backup. According to the method, by combining directional extraction of the drug characteristic parameter set and the drug taking influence parameter set with Pearson correlation algorithm screening, decision errors caused by data deviation are avoided.

The invention discloses a drug-target interaction prediction method and system, and belongs to the technical field of biological information. The method comprises the following steps: firstly, acquiring molecular structure data of a drug and sequence and structure data of a target spot; then, respectively extracting molecular map structure characteristics and SMILES sequence characteristics of the medicine, and amino acid sequence characteristics and three-dimensional space structure characteristics of a target spot; further, taking drugs and targets as nodes, taking the fused multi-modal features as node features, and combining known interaction and similarity information to construct an initial heterogeneous graph; inputting the heterogeneous graph into a dynamic graph neural network, dynamically learning an inter-node connection weight by using a graph attention mechanism, and iteratively updating node representation through multi-layer message transmission to obtain depth feature representation of drugs and targets; and finally, splicing the depth features, inputting the depth features into a multi-layer perceptron classifier, and predicting the drug-target interaction probability. According to the method, through multi-modal feature fusion and dynamic graph structure learning, the prediction accuracy and robustness are remarkably improved.

The invention provides a drug target prediction method based on cross-modal attention and uncertainty evaluation, and belongs to the technical field of drug target prediction. In order to solve the technical problems that the existing drug target prediction lacks quantitative evaluation on the reliability of a prediction result and a nonlinear interaction relationship between a drug and a target is difficult to establish, the method comprises the following steps: collecting data, and fusing graph structure features and sequence features of extracted drug molecules to obtain a final code of the drug molecules; extracting amino acid sequence characteristics of the target protein, and constructing protein sequence characteristic expression; inputting the drug molecular features and the protein sequence features into a cross-modal attention module, and aligning and fusing the drug features and the protein features by using a bidirectional cross attention mechanism to obtain drug-target combined feature representation; introducing an uncertainty quantification mechanism, and outputting uncertainty estimation of a drug-target interaction prediction label and a prediction result; the method is used for predicting drug target interaction.

The invention discloses a cross-modal interactive fusion structure diagram feature extraction method, and the method employs a multilayer diagram isomorphic network to extract local neighborhood features and global topological features of drug molecules, thereby improving the capability of a model for capturing the change of a fine structure. A convolutional neural network and a multi-head convolutional self-attention mechanism are integrated to comprehensively capture local features and long-range dependency relationships in a protein sequence; and interaction information between a drug and a target is fully modeled through a cross-modal interaction fusion module based on a gating mechanism, so that more accurate DTI prediction is realized.

The application relates to a drug-lncRNA relationship prediction method and system based on embedding constraints, and the method comprises the following steps: collecting lncRNA-drug association data and preprocessing, and constructing a data set; based on the data set, an lncRNA-drug association matrix is constructed, and an lncRNA-drug bipartite graph is extracted; based on the lncRNA-drug association matrix, an lncRNA similarity matrix and a drug similarity matrix are obtained, and dimension reduction processing is performed; the lncRNA-drug bipartite graph and the dimension reduction processed lncRNA similarity matrix and drug similarity matrix are input into an LDA-GNN model and an LDA-DHG model with an embedding constraint strategy, and the probability score of lncRNA and drug association is obtained; and based on the probability score, the relationship prediction of the drug-lncRNA is realized. Through the embedding constraint strategy, the prediction performance and the distinguishing ability of the model are significantly improved.

The present application belongs to the technical field of biological information, and particularly relates to a drug-target interaction prediction method based on multi-granularity representation; the method comprises the following steps: extracting an enhanced molecular representation of a drug molecule by using a hierarchical network; modeling first-order information and second-order information in an amino acid sequence respectively based on adjacent residues in the amino acid sequence, so as to extract multi-order sequence features; processing multiple sequence information by using a Pconsc4 tool to obtain spatial structure information representation of a protein; splicing the enhanced molecular representation, the multi-order sequence information and the spatial structure information representation of the protein to obtain fusion features; inputting the fusion information into an interaction prediction network to obtain a drug-target interaction prediction result; the present application can not only solve the weakness of existing methods that only focus on single-granularity information, improve prediction accuracy, but also show interpretability.

The application discloses a DDI prediction method based on a Siamese structure and graph contrast learning, comprising the following steps: collecting drug-drug interaction text data and physical and chemical property data files and targeting relationship data files of drugs; extracting the physical and chemical property characteristics and the targeting relationship characteristics of the drugs, fusing the characteristics to obtain initial characteristics based on the physical and chemical properties and the targeting relationship; calculating a drug-drug interaction adjacency matrix, combining the initial characteristics to construct a drug-drug interaction heterogeneous graph; inputting the heterogeneous graph into a Siamese structure-based graph contrast learning model to learn and obtain embedding characteristics of drug nodes; and using a link prediction method to calculate the score of edges between any two drug nodes. The application can alleviate the problem that the drug targeting relationship characteristics and the drug-drug interaction text data are difficult to be used alone when the data are sparse and have an impact on the performance of the model, improves the accuracy of drug-drug interaction prediction, and can be applied to identifying potential interactions between drugs.

The application discloses a drug interaction prediction method based on DS evidence theory. First, multi-modal data of drugs are acquired to construct a drug interaction dataset; then, multi-modal features of the drugs are extracted as inputs of a deep neural network, a multi-modal drug interaction prediction model is constructed, and the prediction model is trained; then, the trained prediction model is used to predict drug interactions. The prediction model uses Dirichlet distribution to calculate classification probability and uncertainty value, and obtains multi-modal prediction results and overall uncertainty value through Dempster-Shafer evidence theory fusion. Compared with existing prediction methods, the application uses multi-modal drug data, has a lower prediction error, can provide meaningful uncertainty information for guiding multi-modal prediction fusion and expressing prediction confidence, and has higher reliability and robustness.

The invention belongs to the technical field of intelligent medical treatment, and discloses a drug relocation method and system based on implicit interactive adjacency matrix remodeling, and the method comprises the following steps: S1, constructing a fusion drug-disease incidence matrix; s2, extracting drug domain features and disease domain features by adopting a parameter sharing double-path self-attention mechanism; s3, mapping the drug / disease features to the dimension space of the opposite side through the trainable projection matrix, and generating an implicit interaction prediction matrix; and S4, dynamically adjusting the contribution degree of the positive and negative samples through the weight lambda to solve the problem of data sparsity. According to the method, drug domain and disease domain feature decoupling learning is realized through a dynamic adjacency matrix by adopting a double-path self-attention mechanism, cross-dimensional implicit interaction prediction is completed by utilizing a trainable projection matrix, feature representation is iteratively optimized in combination with a recurrent neural network, the noise influence of artificial similarity data can be effectively reduced, and the accuracy of the method is improved. And the method has remarkable advantages in actual scenes such as Parkinson's disease drug relocation and the like.

The application discloses a brain hemorrhage perioperative medication scheme intelligent recommendation method and system, acquires physiological parameters and operation time sequence characteristics of a patient, constructs a patient risk image, carries out risk matching with a drug knowledge base to generate a candidate drug set, extracts drug attribute characteristics to determine a drug function grouping, carries out adaptability scoring based on the patient risk image to generate a grouping adaptability matrix, carries out drug interaction analysis to identify synergistic pairs and antagonistic conflict pairs, carries out combination optimization on the synergistic pairs to generate a synergistic scheme, carries out conflict exclusion screening on the antagonistic conflict pairs to generate safety constraints, constructs a medication scheme topology, carries out dose sensitivity anomaly detection and correction to generate a correction factor to generate a time-sharing drug administration scheme, carries out real-time monitoring to carry out perfusion evaluation to determine a safety level and trigger dose adjustment, forms an optimized medication scheme, and realizes intelligent recommendation of perioperative medication.

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 discloses a drug interaction prediction method based on similarity network fusion, and relates to the technical field of biomedicine, and the method comprises the steps: integrating drug data sets in a plurality of well-known drug databases, and extracting drug feature data; calculating similarity according to features extracted from the drug data set, and constructing a similarity matrix; the entropy value of each similarity matrix and the pairwise distance between the similarity matrixes are calculated, and the similarity matrix with the maximum information amount is preferentially selected; combining the selected similarity matrixes by adopting a similarity network fusion technology to obtain a fused similarity matrix; constructing an interaction matrix according to the obtained fusion similarity matrix; and training a convolutional neural network (CNN) model by using the fusion similarity matrix and the interaction matrix of the drug, and realizing drug interaction prediction on test data by using the trained CNN model. By combining the similar network fusion technology and the convolutional neural network model, the accuracy and reliability of drug interaction prediction are remarkably improved.

The invention discloses a medicine relocation system and method based on a quantum graph Fourier convolution network. The method comprises the following steps: integrating proteins, genes, microorganisms, metabolites, drugs, diseases and multi-source associated information of the proteins, the genes, the microorganisms, the metabolites, the drugs, the diseases to construct a heterogeneous biological information network and a local subgraph network; the method comprises the following steps: innovatively designing a quantum graph Fourier convolution network, extracting spectrum characteristics and topological information of protein, gene, microorganism, metabolite, medicine and disease nodes from a heterogeneous biological information network, updating medicine and disease node information, and obtaining discriminative characteristic representation; a multi-layer sensor is used for learning and depicting medicine-disease joint feature representation, and then the unknown curative effect of the medicine is predicted. According to the method, data mining and knowledge discovery are carried out based on the multi-source heterogeneous biological information network, the quantum Fourier graph convolutional network is innovatively used for modeling the multi-source heterogeneous biological network, high-order semantic dependence and a global structure mode between drugs and diseases can be effectively extracted, the performance of a drug relocation prediction system is improved, and the system is suitable for large-scale popularization and application. And the method has good expandability and practical application prospects.

The invention relates to a drug-target interaction prediction method, which comprises the following steps: preprocessing drug molecule data to construct a drug molecule graph, and preprocessing a target sequence to construct a target residue topological graph; inputting the two features into a prediction model, respectively extracting global features of the drug and the target by the model through two branches of a GAT network, acquiring residue-level features of the target through a GCN network, and matching functional group categories through a DiffPool layer clustering category number to obtain drug functional group features; the functional group features and the residue-level features interact through the cross attention module to generate interaction features, then the interaction features and the global features are spliced into joint features, and the joint features are input into a full connection layer to output a prediction result. According to the method, chemical prior knowledge and deep learning are deeply fused, the bottleneck of a traditional model is broken through, and a high-reliability technical solution is provided for computer-aided drug design.

The application discloses an antibody conjugated drug binding prediction method based on a virtual graph and multi-scale features, proposes a drug carrier, a linker, an antibody heavy chain and a light chain, and an antigen target protein initial feature construction method, proposes a 1DCNN for extracting drug sequence features, designs a drug feature extraction method based on a graph virtual node, introduces a virtual node and a virtual edge into a molecular structure graph, takes a Graph Transformer as a graph feature extractor, takes a virtual node feature as a drug representation, then inputs protein and drug features into a feature fusion module, adds an attention mechanism and a gated skip connection mechanism in feature fusion, captures potential interactions while fusing feature information of different hidden layers, and realizes higher precision affinity prediction. The application can solve the technical problems that existing methods are difficult to extract structural features of antibody conjugated drugs and features of different components are difficult to fuse.

The application discloses a drug-target interaction prediction method and device based on multi-view feature fusion and a medium, and comprises the following steps: (1) extracting drug features: first, generating a drug molecule graph, extracting molecular fragments to construct multiple subgraph structures, and then using a graph encoder to encode to obtain drug features; (2) extracting target features: first, extracting the protein pocket of the target, dividing the protein pocket into multiple subpockets to obtain multiple subgraph structures, and then using a graph encoder to encode to obtain the pocket features of the target; in addition, a self-attention module is used to extract the sequence features of the target, and a cross-attention is used to fuse the pocket features and the sequence features to obtain the target features; (3) using a bilinear attention to fuse the drug features and the target features, and calculating the interaction probability between the drug and the target. The application can effectively mine the biochemical attribute features in the drug molecules and the target protein structures, and improve the prediction accuracy of the drug-target interaction.

The application provides a drug-disease interaction prediction method fusing multi-neighborhood correlation information, first, drug and disease information in a drugomic database is preprocessed to construct a drug-disease correlation relationship network; second, node aggregation and linear fusion are introduced, and feature information of drugs and diseases in multiple neighborhood spaces is extracted in parallel; then, contrast learning is used to perform parallel fusion on single-domain features and multi-neighborhood features, and a hierarchical attention mechanism is used to aggregate feature representations to obtain general features of drugs and diseases; finally, the extracted feature information of drugs and diseases is sent into a classification model composed of a full connection neural network for training, a hybrid optimization strategy combining prediction loss and negative example generation loss is proposed to perform overall optimization on the model, the model is saved, and the relationship between drugs and diseases is predicted. The application has better performance when predicting the drug-disease correlation relationship, and reduces the dependence on prior knowledge.

This invention discloses a preparation method and application of a gel plaster, belonging to the field of traditional Chinese medicine plaster preparation technology. The preparation steps are as follows: S1, drug extraction: ultrapure water is measured at a material-to-liquid ratio of 1:10, and the decoction is separated three times. The three decoctions are combined, concentrated, and stored in a refrigerator for later use; S2, matrix preparation: phase A, phase B, and phase C are accurately prepared according to the prescription; the above contents are mixed evenly and coated onto non-woven fabric, and dried in an oven to obtain the matrix; the gel plaster is used in the treatment of insomnia. This invention optimizes the preparation process of the heart-nourishing and calming plaster, using the traditional decoction method to extract the drug. While ensuring the effective components of the drug, the drug is made into a gel plaster that is easier to wash, has a moderate consistency, is non-greasy, and has better biocompatibility. The transdermal absorption rate of this plaster determines the drug's ability to act on the body and its efficacy. By examining the transdermal rate of the heart-nourishing and calming gel plaster, the drug's permeability is ensured.

The application provides a method for evaluating drug accumulation toxicity based on ex vivo rabbit corneal long-term perfusion, and belongs to the technical field of drug accumulation toxicity evaluation. The method comprises the following steps: preparing a perfusion sample and building a perfusion device; performing continuous perfusion, collecting corneal physiological response data and drug concentration monitoring data in real time; performing denoising processing on the collected original data, and extracting drug accumulation toxicity characteristic parameters; inputting the toxicity characteristic parameters into a drug accumulation toxicity evaluation model based on a convolutional neural network to obtain a corneal toxicity grade under the current perfusion condition; establishing a multi-objective analysis model, solving the model, and obtaining a quantitative evaluation result of drug accumulation toxicity and a safe perfusion threshold; and determining the corneal toxicity risk grade of the drug and the safe use concentration range. The application ensures the reliability of the data through a denoising algorithm and a feature extraction method, realizes accurate toxicity determination by using a neural network, improves the scientificity and efficiency of the evaluation, and provides a precise toxicity evaluation method for animal ophthalmic drug research and development.

The invention relates to a preparation for treating acute plateau gastrointestinal dysfunction as well as a preparation method and application of the preparation, active ingredients in a pharmaceutical composition are extracted through a supercritical carbon dioxide fluid extraction technology on the basis of a formula for tonifying middle-Jiao and Qi, and a reagent or a reagent composition suitable for oral administration and / or patch is further prepared. The reagent or the reagent composition is suitable for gastrointestinal dysfunction caused by rapid plateau entry.

The utility model belongs to traditional chinese medicine extraction device technical field, concretely is a kind of traditional chinese medicine extraction drug residue separation device, including bottom plate, the upper end of bottom plate is equipped with the screen mechanism for the secondary screening separation of drug residue and liquid medicine, the upper end of bottom plate is equipped with the liquid collecting barrel for collecting extruded liquid medicine, the upper end of screen mechanism is equipped with the pressure residue mechanism for the coarse residue filtration and extrusion of traditional chinese medicine raw material, and the mixture after preliminary processing by pressure residue mechanism falls into the screen mechanism below.Motor one drive rotating cam, swing lever drives slider linear reciprocating motion, and then make fine, micro residue two grade screening frame whole vibration, mixture is first separated medium size drug residue by fine residue screening frame, and the remaining liquid residue is finely screened by micro residue screening frame again.Liquid medicine is finally screened by diversion groove and collected in liquid collecting barrel, and different size drug residue is intercepted by two grade screen frame respectively, so that the complete separation of liquid medicine and drug residue is realized.

The invention relates to a method for applying a medical big language model of an integrated knowledge graph to drug analysis and diagnosis support. The method comprises the steps of performing streaming analysis and entity recognition on a structured pharmaceutical database file, generating a drug record set containing standardized biomedical entity annotations, and constructing a graph structure knowledge base and a vector index base in parallel; receiving a natural language query, extracting drugs and disease entities and mapping the drugs and disease entities into standardized identifiers; synchronously retrieving the structured evidence set and the text evidence set; assembling an enhanced prompt text containing the task instruction, the verified evidence and the query according to the template; and inputting the large language model subjected to biomedical task fine tuning, and generating a binding response. By adopting the method, the problems of static stiffness, pure language model illusion and insufficient interaction of a structured knowledge base of a traditional system can be solved, reliable decision assistance is provided for replacement treatment and interaction review under the condition of drug shortage, and the drug use risk is reduced.

The application discloses a method for predicting ADMET properties of drug compound molecules based on deep learning fusion of molecular graphs and molecular point cloud, and comprises the following steps: obtaining SMILES code of a candidate drug molecule for which drug molecular property prediction is needed; processing the SMILES code of the candidate drug molecule; generating a corresponding two-dimensional molecular graph based on the number of atoms and the number of chemical bonds in the SMILES code of the candidate drug molecule, extracting atom node features and edge features of atomic bonds in the drug molecule from the SMILES code of the candidate drug molecule, adding the atom node features and the edge features of the atomic bonds in the drug molecule into the two-dimensional molecular graph, and obtaining a drug molecular graph; extracting corresponding point cloud features of the candidate drug molecule based on the SMILES code of the candidate drug molecule; and inputting the drug molecular graph and the corresponding point cloud features of the candidate drug molecule into a trained deep learning model to obtain an ADMET property prediction result of the candidate drug molecule.

The present application relates to a kind of drug-disease association prediction methods, comprising the following steps: step one, extracting drug-disease association neighborhood subgraph: with drug and disease in drug-disease association network as node, the relationship between drug and disease is edge to create two-part graph, and construct the adjacency matrix of association network;Extract the h-hop neighborhood of relevant drug node and disease node;The h-hop neighborhood of drug node and disease node is merged into the h-hop neighborhood subgraph of drug-disease association;Extract the neighborhood subgraph corresponding to each association as positive sample of model training, while randomly selecting the same number of drug-disease pairs without association to generate negative sample test data, and divide training set and test set;Step two, construct the initial node feature of neighborhood subgraph;Step three, learning of graph neural network.

This invention relates to the fields of bioinformatics and artificial intelligence, and proposes a method and system for predicting drug-target interactions based on multimodal feature fusion. The method includes: segmenting and encoding the acquired drug and target sequences to be identified; extracting sub-sequence features of the drug and target respectively; constructing a two-dimensional molecular graph of the drug and a three-dimensional structural graph of the target, and extracting graph structural features of the drug and target respectively; fusing the sub-sequence features and graph structural features of the drug and target through a cross-attention mechanism; and using a bidirectional collaborative attention mechanism for interactive fusion to obtain the predicted binding affinity of the drug and target. This disclosure, by combining multimodal complementary information of the drug and target, deeply explores the deep interactions between different modal features; simultaneously, by introducing a bidirectional collaborative attention mechanism in the interaction modeling of the drug and target, it effectively improves the accuracy of drug-target binding affinity prediction.

The invention relates to the field of drug and target interaction prediction, and discloses a similarity relation network drug and target interaction prediction method and system based on a pre-training language model, and the method comprises the steps: extracting an initial drug embedding feature and an initial protein embedding feature through the pre-training language model; constructing a drug similar network and a protein similar network; applying the graph neural network to a drug similar network and a protein similar network; extracting drug structure features by using a directed message passing neural network, and extracting protein structure features by using a convolutional neural network; performing cross fusion on the drug similarity relation characteristics and the protein similarity relation characteristics, and splicing cross fusion results with drug structure characteristics and protein structure characteristics; and inputting the drug-protein pair features into a classifier to carry out drug-target interaction prediction. According to the method, the generated embedded representation is combined with the similarity relation network, so that complementarity between semantic representation and relation representation is effectively mined.

The present application provides a kind of based on multi-view fusion graph convolution network parasitic disease drug association prediction method, to solve the problems such as data sparse, noise interference and incomplete feature information in drug development. The method is through "multi-view heterogeneous network construction-self-supervised learning-multilayer propagation and association prediction" process, accurately identify parasitic disease-drug association. First, collect data and construct benchmark dataset;Then, extract drug SMILES feature and disease MeSH descriptor, fuse drug similarity network, disease similarity network and drug-disease two-part network. Next, adopt self-supervised learning strategy to obtain node embedding representation, introduce neighbor information aggregation layer to enhance sparse relationship expression, and finally output association prediction score by weighted fusion multi-view features through attention mechanism. Compared with existing methods, the present application shows higher accuracy and stability in parasitic disease drug prediction task, and provides support for drug screening and new drug development.

The invention provides a drug-drug interaction prediction method PG-DDI based on pre-trained drug characteristics. According to the method, DDI prediction is converted into a multi-source feature fusion classification task: drug molecular map structural features are extracted by using GAT and GIN of freezing parameters, molecular fingerprint features of three fingerprints of MACCS and the like subjected to full connection layer processing are combined, and MolCLR pre-training features are superposed; self-adaptively capturing feature interior and cross-feature association through a double-attention module (self-attention and cross-attention); the model introduces a pre-training feature branch and combines with parameter freezing to realize knowledge migration. On the basis of the reference data set, the PG-DDI is evaluated according to indexes such as ACC, AUC and F1, the performance of the PG-DDI is superior to that of an existing advanced method, the accuracy and generalization of DDI prediction are improved, and the method is suitable for the medication safety evaluation scene of drug research and development.

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.

The invention discloses a drug-target binding affinity prediction method based on multi-granularity fusion, and the method comprises the steps: S1, extracting the feature representation of a drug SMILES character string, a Morga fingerprint and an Avalon fingerprint, and carrying out the fusion of the feature representation and the two fingerprints, and obtaining a drug feature representation; s2, extracting k-mer frequency features of the protein sequence, generating dimensionality reduction features by adopting a PCA dimensionality reduction method, inputting the dimensionality reduction features into a transform module for feature extraction, and outputting k-mer features; s3, generating an initial feature representation of the protein sequence by adopting a protein language model, performing fine tuning by adopting a transformer module, and fusing fine tuning features with k-mer features to obtain a protein feature representation; and S4, inputting the drug feature representation and the protein feature representation into an independent layered attention mechanism module to obtain aggregation features of the drug feature representation and the protein feature representation, splicing the aggregation features, and inputting a full connection layer to predict the drug-target binding affinity.