121 results about "Protein Feature" patented technology

The invention relates to the field of drug-target affinity prediction, in particular to a drug-target affinity prediction method based on a multi-scale mixed attention network. According to the method, global residue characteristics can be learned by protein pocket residues by utilizing a self-attention mechanism, so that the global characteristics of the protein are learned. In addition, a cross-modal feature fusion mechanism is utilized, protein and drug structural features are enhanced in sequence features, cross-modal feature fusion in entities is enhanced, meanwhile, a cross-entity interaction module is utilized to recognize key atoms of drug molecules or key residues of protein, and therefore the overall performance of the model is improved. Finally, multi-level protein feature extraction is further introduced to further extract protein features.

The invention relates to the technical field of pharmaceutical knowledge maps, in particular to a pharmaceutical knowledge map construction method and system based on artificial intelligence, and the method comprises the following steps: querying and collecting a molecular structure of a drug and a corresponding target protein sequence through a database, and carrying out the numerical coding of the molecular structure data of the drug, molecular fingerprints and protein structural domain features are extracted, and a drug and protein feature set is formed by combining drug chemical attributes and protein sequence features. According to the invention, through accurate analysis of the molecular structure of the drug and the target protein sequence thereof, the innovative scheme significantly enhances the understanding of the interaction of the drug and the protein, so that researchers can directly extract key features from data and monitor the dynamic change of the drug effect, thereby not only accelerating the development process of the drug, but also improving the development efficiency of the drug. By dynamically tracking the interaction between the side effect of the medicine and the pathological characteristics, the scheme provides powerful data support for personalized medical treatment.

The invention relates to the technical field of new-generation information, and discloses an lncRNA-protein interaction prediction method and system, so as to improve the prediction accuracy. The method comprises the following steps: acquiring an initial protein feature representation fused with surface, structure and sequence features; obtaining an initial lncRNA feature map fused with a sequence feature kernel, an expression profile feature kernel, a sequence similarity kernel and a Gaussian interaction spectrum kernel of protein; obtaining a final lncRNA feature map and a final protein feature map from the initial protein feature representation and the initial lncRNA feature map based on a cross attention mechanism; carrying out downsampling on the final lncRNA feature map and the final protein feature map by using global maximum pool operation, and generating a combined feature representation vector consisting of a one-dimensional lncRNA feature vector and a one-dimensional protein feature vector; and inputting the joint feature representation vector into a decoder consisting of full-connection classification layers to obtain a prediction score of the LPI.

The invention discloses a drug target prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: performing dynamic gating fusion on graph structure features and sequence features of a target drug to obtain drug features; performing dynamic feature enhancement on the digitized sequence of the target protein, and further obtaining protein features through context sensing optimization; obtaining a target affinity score of the target drug and the target protein by using a prediction model based on the drug characteristics and the protein characteristics; wherein the prediction model is obtained through feature representation training marked with actual affinity scores on the basis of a neural network. According to the method, the prediction precision of drug target interaction is improved through deep fusion of drug multi-modal features and protein sequence context perception optimization. The method can realize high-precision prediction of the drug target, and can be widely applied to the technical field of drug target prediction.

The invention provides an enzyme modification method based on artificial intelligence. The enzyme modification method comprises the following steps: training an AlphaFold2 model to obtain a glycosyltransferase tertiary structure prediction model; performing multi-sequence comparison on the protein and nucleic acid sequence database and the non-redundant protein feature sequence database based on the active point location recognition model to obtain a comparison result; initializing a matrix of which the length is equal to that of a comparison result, so as to construct a PSSM matrix and screen out potential mutation sites; according to the screened potential mutation sites, constructing an initial mutation library to form a virtual screening mutation library; performing structure reconstruction on the sequence in the virtual screening mutation library based on a glycosyl transferase tertiary structure prediction model so as to predict the glycosyl transferase tertiary structure and perform molecular docking and dynamic simulation on the glycosyl transferase tertiary structure; the method is used for analyzing binding pockets of proteins and ligands and determining dynamic interaction of amino acid residues and ligands in the binding pockets, and the contact number of each amino acid residue and the ligands is used for modifying the tertiary structure of the glycosyltransferase.

The invention provides a protein toxicity prediction method and system based on sequence information. The method comprises the following steps: acquiring a plurality of protein sequences from a protein database; performing feature calculation on all the protein sequences to obtain six types of protein feature vectors; splicing the six types of feature vectors according to columns to obtain a first feature vector; performing dimension reduction screening on the first feature vector to obtain a second feature vector of the target dimension; training a neural network model based on graph attention by using the second feature vector, and taking the trained neural network model as a protein toxicity prediction model; and inputting the new protein sequence into the protein toxicity prediction model to obtain a toxicity prediction result output by the protein toxicity prediction model. The method can adapt to different types of protein sequences, and the protein toxicity is accurately predicted through the learned universal sequence mode.

The invention provides a method for predicting a compound target based on a compound perturbation transcriptome and a protein sequence and application, and the method creatively combines the characteristics of the compound perturbation transcriptome and the characteristics of the protein target sequence as input characteristics and combines a deep learning model to realize prediction of the compound target. Specifically, perturbation transcriptome and active and inactive target spot information data of a compound are collected, transcriptome features are extracted through principal component analysis and linear discriminant analysis, meanwhile, a protein language model is used for representing target spot protein features, the transcriptome and a target spot of the compound are converted into learnable embedding, and the target spot information of the compound is obtained. And the classification model is used for training and learning potential association of the two, and is finally used for compound target prediction. According to the method, an external test set is used for proving high accuracy and practical applicability of the model. The method has the advantages of being low in cost, high in efficiency and wide in range, the compound target spot discovery efficiency can be remarkably improved, and the research and development process of drugs can be accelerated.

The invention relates to a protein implicit binding site prediction method based on deep learning. The method comprises four stages of data acquisition, feature engineering, model training and verification application. The method comprises the following steps: firstly, acquiring initial data from a protein database, performing data screening and sequence redundancy elimination, performing standardization processing on a PDB structure file, and generating a sample; then, constructing a composite feature space containing basic protein features and evolutionary conservative features; thirdly, feature dimension reduction is achieved through a hierarchical feature conversion and integrated feature selection method, and a model is constructed; finally, verification and application show that the method obtains 99.44% prediction accuracy on 954 non-redundant protein structures, ROC-AUC and PR-AUC both reach 0.9998, and the overlapping rate with a BioLiP database is 44.4%. The method can accurately identify potential drug binding sites, especially shows good generalization ability for drug targets difficult to prepare, and has important application prospects.

The invention discloses a protein design method, device and equipment, a medium and a program product, and is applied to the field of artificial intelligence. The method comprises the following steps: acquiring a protein framework, and extracting protein characteristics of the protein framework; obtaining a target protein sequence, and extracting target protein characteristics of the target protein sequence; fusing the protein features with the target protein features to obtain fusion features; the fusion feature is used for representing sequence information and structure information under interaction between the protein indicated by the protein framework and the target protein indicated by the target protein sequence; and performing protein sequence recovery on the protein framework based on the fusion feature, recovering a predicted protein sequence corresponding to the protein framework, and performing protein structure prediction on the predicted protein sequence to obtain a predicted protein structure corresponding to the predicted protein sequence.

The invention discloses a method for lightweight prediction of PPI based on Node2vec, and the method comprises the following steps: a protein initial representation module: learning protein initial representation from a protein interaction network G = (V, E) in an unsupervised manner by using Node2vec; the multi-scale relation structure representation module is used for setting two GNNs with different scales to capture shallow layer and deep layer structure information in the protein interaction network, and the GNNs comprise an SGCN variant for the shallow layer structure information and a Mama module for the deep layer structure information; carrying out weighted sum summation on the protein feature representations obtained by SGCN and Mama learning to obtain final protein representation; in the prediction module, the deep protein representation and the shallow protein representation are subjected to element multiplication, semantic information of the features is enhanced, and then prediction is carried out. An unsupervised learning method Node2vec is introduced to carry out unsupervised learning on initial expression of protein, then graph nerve + attention is adopted to carry out supervised fine learning, and local features and global features in the initial expression of the protein are planned as a whole.

The invention discloses a protein mutation stability prediction method based on generative adversarial network data generation, and belongs to the technical field of biological information, and the method comprises the following steps: constructing a protein mutation data set; extracting protein features from the Megascall data set and the protein mutation data set; performing five-fold cross validation on the generative adversarial network, and storing a generator G; generating a mutation sample through a generator G; constructing a downstream task network model; optimizing downstream task network model parameters through an adaptive gradient method; calculating evaluation index verification model performance through the verification set; and realizing prediction through a downstream task network model. A protein mutation sample is generated by applying the generative adversarial network, so that the problem of data scarcity in protein stability research is effectively solved; the generative adversarial mechanism is combined with the cyclic consistency loss, so that the high quality of the generated data is ensured, the data set is successfully expanded, and the adaptability of the model to different mutation types is improved.

The invention discloses a protein mutation stability change prediction method based on an integrated convolutional neural network model and regression hierarchical training, and belongs to the technical field of protein stability change prediction. Firstly, a training set and a test set are constructed, and four data sets are collected and arranged. The method comprises the following four steps: 1, performing enhancement processing on data based on antisymmetry, and balancing and training stable and unstable abrupt sample data in a set; 2, extracting protein characteristics; 3, training the model by adopting a regression stratified sampling strategy; and 4, constructing an integrated model based on a plurality of CNN sub-models for predicting the stability change of the protein mutation. Spatial neighbor evolution information is introduced for the first time; a regression stratified sampling strategy is proposed for the first time and is successfully applied to the training process of the model, so that the prediction capability of the model for the extreme delta delta G is effectively improved; the trained CNN sub-models are combined, information of all samples in a training set is fully utilized, and the generalization ability of the model is enhanced.

The invention relates to a drug-target interaction prediction method and system based on deep learning. The method comprises the following steps: determining an SMILES sequence of a drug molecule to be predicted and an amino acid sequence of protein; generating a drug molecular map, inputting the drug molecular map to a GPS layer, and extracting the feature representation of the drug by using GINE and multiple attention mechanisms; extracting the feature representation of the protein through an ESM-2 model; and performing cross attention mechanism feature fusion on the feature representation of the drug and the feature representation of the protein to obtain a fused feature, and predicting the binding probability of the drug and the protein based on the fused feature. The feature representation of the medicine is extracted by combining a GINE layer and a multi-head attention mechanism, and the feature representation of the protein is extracted by using the pre-trained ESM-2 model, so that the comprehensive extraction of the features can be realized, and the accuracy of the feature representation is improved; drug and protein features are effectively fused through a cross attention mechanism, and efficient and accurate prediction of drug-target interaction is realized.

The invention discloses an immunoblotting image recognition method and system based on deep learning, relates to the field of bioinformatics and computer vision, and solves the problem that it is difficult to extract various related features of protein from an image through an image recognition technology. The method solves the technical problem that a prediction value obtained by predicting a protein expression level obtained by a deep learning model through various protein feature data is difficult to correct. The method comprises the following steps: capturing a strip image on a film by using a high-resolution scanner; recognizing the preprocessed image through an image recognition technology, and extracting features related to the immunoblotting; predicting the feature data through a correspondingly trained deep learning model to obtain an area prediction value, a gray scale difference degree prediction value and a relative brightness prediction value; corresponding weights are given to the three prediction correction values for addition, and a comprehensive prediction correction value is obtained; and comparing the comprehensive expression evaluation value with a preset threshold value to judge the protein expression level.

The invention discloses an lncRNA-protein interaction prediction method based on bidirectional intention, and belongs to the technical field of bioinformatics, and the method comprises the following steps: data acquisition and preprocessing: constructing a data set; performing lncRNA feature extraction through a multilayer convolutional neural network; carrying out protein feature extraction based on an ACmix module; fusion of the lncRNA and protein bimodal features is carried out through a bidirectional intention network; performing lncRNA-protein interaction prediction on the fusion representation by using a three-layer and multi-layer perceptron network, and outputting at an output layer; and meanwhile, designing a loss function to carry out model optimization. The model is more comprehensive and accurate when the dependency relationship between the sequences is captured, so that the reliability and generalization ability of prediction are effectively 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 present invention relates to the field of biomedical technology and discloses an artificial intelligence-based anti-tumor drug resistance detection method and system, comprising: collecting genomic data of tumor cells and analyzing genetic changes in tumor cells; extracting tumor molecular markers from tumor cells and constructing a knowledge graph of anti-tumor drug resistance in tumor patients; extracting gene-protein features of tumor cells and identifying the pharmacochemical properties of anti-tumor drugs; fusing gene-protein features and pharmacochemical properties to perform dimensionality reduction processing to construct a drug resistance analysis model for tumor cells; analyzing drug-target interaction relationships in tumor patients and extracting gene-resistance association features of tumor cells to identify the model reliability of the drug resistance analysis model; defining the result interpretation of the drug resistance analysis model, and combining the model reliability and result interpretation to output the anti-tumor drug resistance detection results of tumor patients. The present invention can improve the accuracy of anti-tumor drug resistance detection.

The invention discloses a drug sequence descriptor-based drug and target interaction prediction method, and belongs to the technical field of drug target prediction. According to the method, the descriptors of the smiles sequences of the two drugs are adopted, and after the two descriptors are added, prediction of the model on the result is more accurate due to the fact that the two descriptors contain structural information and chemical information related to tasks; for protein sequences, the characteristics of a large language model ESM-2 and the characteristics of a BERT large language model are added, and the model weights of the ESM-2 model and the BERT model are derived from tens of thousands of protein sequences, so that the representation capability of output vectors is very high; the interaction between protein features and drug features from a source sequence is realized through the designed cross attention layer with the shared weight, the prediction precision of the model is further improved, and experiments show that the model designed by the invention has a better effect on multiple indexes on multiple data sets.

The application relates to the technical field of computer-aided drug design, and provides a molecule generation method, system, medium and equipment for drug discovery, which comprises the following steps: acquiring a SMILES string of a ligand and an amino acid sequence of a target protein, respectively extracting a ligand feature vector and a protein feature vector, splicing and fusing, and then predicting a binding affinity value through a multilayer perception machine; taking the protein feature vector as a condition, generating a new molecular potential representation through a reverse denoising process of a conditional diffusion model; wherein, at each step of the reverse denoising process, a graph-level readout operation is performed on pure noise, an affinity value is predicted through the multilayer perception machine, a gradient of an affinity guidance loss is returned to a noise prediction network, and the new molecule generation is guided to a high affinity area; and the new molecular potential representation is decoded into a SMILES string through a pre-trained molecular language decoder. Novel molecules with high binding potential can be quickly generated.

Embodiments of the present application disclose a drug screening method, device and computer readable storage medium; after obtaining protein information of a target protein and molecular information of a candidate drug molecule, the target protein is a target macromolecule which can be acted on by the drug molecule, then, feature extraction is performed on the protein information and the molecular information respectively to obtain protein features of the target protein and molecular features of the candidate drug molecule, according to the protein information and the molecular information, interaction information of the target protein and the candidate drug molecule under a molecular force field is determined, then, based on the protein features, the molecular features and the interaction information, a binding strength between the target protein and the candidate drug molecule is calculated, and according to the binding strength, a target drug molecule is screened from the candidate drug molecule; the scheme can improve the accuracy of drug screening.

The invention discloses a macromolecular protein cutting method and system based on multi-source protein feature scoring, and a storage medium, and belongs to the field of computational biology and intelligent drug research and development. In order to solve the technical problem that macromolecular protein is difficult to directly input into an existing calculation model, an amino acid position cutting comprehensive score is obtained by obtaining multi-source feature data such as a protein disorder region and structural domain annotation, candidate cutting sites are screened and a final cutting scheme is determined in combination with double constraints of a structural domain hard boundary and fragment length, and the method is suitable for large-scale industrial production. And generating a protein fragment adaptive to downstream calculation. According to the method, the integrity of the protein structural domain is guaranteed, the cut fragment can be directly used as model input such as AlphaFold, the accuracy and stability of structural prediction and molecular docking are improved, the method is suitable for scenes such as virtual screening and computer-aided drug design, and the problem that an existing cutting method is lack of systematic consideration is solved.

This invention discloses a drug target affinity prediction method that integrates PPI quality and uncertainty. The method constructs a drug molecule map and a multimodal protein structure representation, and extracts multi-source features by combining the local PPI sub-map of the target protein. By calculating the protein's low-frequency level, prediction uncertainty, and PPI quality, a PPI quality-aware gating factor is generated to adaptively adjust the PPI information injection intensity, and a residual enhancement strategy is used to preserve the original protein features. Subsequently, the drug representation and the enhanced protein representation are fused using adaptive gating, and the result is input into a prediction network to output the drug-target affinity. This method effectively integrates protein function and interaction information, improves the prediction stability of low-frequency proteins and the model's generalization ability, and provides an accurate and reliable computational tool for drug screening and candidate molecule selection.

The application provides an immunogenic epitope prediction method based on antigen presentation and immunogenicity feature fusion, comprising the following steps: extracting peptide segments and type I human leukocyte antigen protein features from an immunogenic epitope database by using a constructed feature extraction module; inputting the peptide segments and type I human leukocyte antigen protein features into a pre-trained antigen presentation prediction model to obtain an antigen presentation probability based on the antigen presentation prediction model; inputting the peptide segments, type I human leukocyte antigen protein features and antigen presentation probability information into an immunogenicity prediction model to realize fusion of antigen presentation and immunogenicity features, and obtaining an immunogenicity score representing a T cell activation probability of the peptide segments based on the immunogenicity prediction model, so as to realize prediction of the immunogenic epitope. The application improves the prediction accuracy of the immunogenic epitope.

The application discloses a kind of lncRNA-protein interaction prediction methods based on bidirectional intention, belong to bioinformatics technical field, including the following steps: data acquisition and pre-processing, construct dataset;Through multilayer convolutional neural network, lncRNA feature extraction is carried out;Based on ACmix module, protein feature extraction is carried out;Through bidirectional intention network, the fusion of lncRNA and protein double mode features is carried out;LncRNA-protein interaction prediction is carried out to the fusion representation using three-layer multilayer perception machine network, and output is carried out in output layer;While designing loss function carries out model optimization.The model of the application is more comprehensive and accurate when capturing intersequence dependence, thereby effectively improving the reliability and generalization ability of prediction.

The invention belongs to the field of artificial intelligence algorithm application-drug target interaction prediction, and relates to a DTI prediction method based on LLM and RBMO. Firstly, through data collection, integration and redundancy elimination, a batch of drug target sequences with a significant positive and negative sample imbalance problem are obtained as input data; then, a K-BERT model is adopted to extract deep features represented by drug molecules SMILES, and a ProstT5 model is applied to analyze high-dimensional information of a protein sequence; and then, introducing an RBMO and KNN combined feature selection method to intelligently screen protein features, and finally selecting 513 key features with the best biological discrimination ability. And finally, combining a multi-core feature fusion mechanism with an emerging Kolmogorov-Arnold network (KAN) so as to enhance the analysis and characterization capability of the model on complex biomolecular features.

The invention relates to the fields of gene editing and artificial intelligence, and discloses an Anti-CRISPR protein recognition method based on a graph neural network. According to the method, modeling is carried out on a similar relation between proteins by constructing a heterogeneous network, and protein features are learned by utilizing a graph neural network, so that the Anti-CRISPR protein recognition is realized. According to the method, multiple protein features including composition features, evolution features, repetition and distribution features, sequence correlation features, structure correlation features and embedded representation generated by an ESM-2 protein language model are integrated, and a graph attention mechanism (GAT) and an airspace-based graph neural network (GraphSAGE) are combined, so that the recognition performance is improved. The method shows excellent accuracy and robustness on multiple benchmark tests, especially shows higher recognition accuracy on an independent test data set, and can effectively distinguish positive and negative samples. The model has an important application value in the research of the Anti-CRISPR protein.

The invention discloses a drug target affinity prediction method, electronic equipment and a computer readable storage medium, the method comprises the following steps: feature extraction is carried out on input small molecule SMILES and protein sequences, and the small molecule adopts 10 molecular fingerprints of RDK, Topological, MACCS, AtomPair, ECFP4, FCFP4, FCFP6, Avalon, Layered and Pattern to construct mixed fingerprint features; compressing the high-dimensional molecular fingerprint features to vector dimensions consistent with protein features through linear mapping to realize feature balance, and splicing to form a fusion feature vector; and performing nonlinear interaction and expression enhancement on the fusion features by adopting a multi-expert hybrid module, and finally outputting an affinity prediction value between the small molecule and the protein through a linear regression layer. Through fusion of multi-source chemical fingerprints and deep protein pre-training representation, higher feature expression ability and stronger model generalization are realized; the complexity of the model is reduced through feature mapping and a lightweight multi-expert hybrid model, so that the model has better stability and expandability.

The invention relates to the technical field of biological information, and discloses a peanut protein interaction prediction method and system based on deep learning, and a medium. The method comprises the following steps: generating a word embedding vector for a peanut protein sequence through k-mers and Word2Vec algorithms, and splicing the word embedding vector with one-hot codes, physicochemical characteristics and PSSM information to obtain a comprehensive characteristic vector; screening key sites according to the PSSM conservative score to construct a feature matrix; a compressed feature vector is obtained through multi-layer neural network dimension reduction compression; after the two protein feature vectors are randomly spliced, the interaction probability is calculated through a full connection layer and a sigmoid function; and obtaining a peanut protein interaction prediction result according to threshold binarization classification. The technical problem that an existing deep learning method cannot effectively fuse multi-dimensional biological characteristic information and cannot accurately predict the peanut protein interaction relationship is solved.

The application discloses a multi-component joint detection method, device and application for synchronous analysis of bone metabolism markers. The multi-component joint detection method comprises the following steps: pretreating a serum sample, and simultaneously extracting small molecule sterols, short peptides and protein characteristic peptide segments; adopting a reverse phase chromatography system to perform chromatographic separation on the extracts, and realizing synchronous elution of lipid-soluble substances and polar substances through a variable gradient elution program; and adopting a segmented multi-reaction monitoring mode to perform mass spectrometry detection, and simultaneously detecting high-abundance indexes and low-abundance indexes in bone metabolism markers in a same sampling period. The application realizes synchronous quantitative detection of five bone metabolism markers, solves technical problems such as fragmentation, large concentration span, incompatible chromatographic behavior and isomer interference in the prior art, and improves detection efficiency by more than 400%, and reduces detection cost by 50%-70%.

The present disclosure relates to an alternative protein material prediction device. The device includes a protein feature extractor configured to composite features of protein as sequence features, structural features, and physicochemical features; a protein graph data generator configured to generate nodes based on the sequence features and physicochemical features of the protein and generate edges between the nodes based on the structural features of the protein, thereby generating protein graph network data, and an alternative material protein predictor configured to generate an alternative protein material prediction model for predicting an alternative protein material by learning the protein graph data that reflects the composite features of the protein.