59 results about "TARP Protein" patented technology

The invention discloses a drug target activation and inhibition relation prediction method based on a depth map neural network, and aims to improve the modeling precision and prediction performance of an activation or inhibition action mechanism between a drug and a target. According to the method, on the basis of a fine-grained graph interaction modeling mechanism, multi-scale structural characteristics of drug molecules and three-dimensional space structural information of protein residue levels are fused, and a heterogeneous interaction graph between drugs and proteins is constructed. The method comprises the following steps: firstly, acquiring a drug-target sample with an activation / inhibition tag through a public database, predicting a protein structure by utilizing AlphaFold2, and constructing a protein residue map and a drug molecular map; multi-scale structure semantic representation is obtained through sub-graph decomposition, atomic-scale feature extraction and graph neural network coding of drug graph features; protein graph node features are combined with context embedding generated by a pre-training language model, DSSP coding, secondary structure spectrum and atomic structure features are constructed, and edge features are designed based on the geometrical relationship between residues. Then, based on constraints such as spatial distance and biochemical similarity, a fine-grained mapping relation between drug atoms and protein residues is established, an interaction graph is constructed, and coding is carried out through a GraphSAGE network; and finally, fusing the interacted multi-source embedding, and completing the prediction of the activation / suppression relationship through a multi-layer perceptron. A cross entropy loss function, an Adam optimizer and hyper-parameter grid search are adopted in model training; in the evaluation stage, five-fold cross validation and an independent test set are adopted, and indexes such as the accuracy rate, the recall rate, the F1 score, the specificity and the Morse correlation coefficient are used for comprehensively evaluating the performance of the model. Experimental results show that compared with an existing method, the method has the advantages that the prediction accuracy and mechanism interpretability are remarkably improved, and the method has good generalization ability and application prospects and is suitable for multiple fields of drug action mechanism research, new drug discovery and the like.

The invention discloses a cancer driver gene prediction method and system based on a graph neural network, and the method comprises the steps: obtaining interaction data of M proteins; for each kind of protein interaction data, coding a relationship between proteins into a gene-gene interaction relationship, and finally obtaining M gene-gene interaction networks; configuring new nodes and new edges for the M genes and gene interaction networks respectively to obtain M heterogeneous networks; the new nodes are cancer-related multi-omics data, and the new edges are connection edges between the new nodes and original gene nodes; and inputting each heterogeneous network into a trained cancer driving gene prediction model to obtain a prediction result of whether each gene is a cancer driving gene or not.

The invention relates to the technical field of bioinformatics, and discloses a method and system for predicting interaction between an lncRNA gene sequence and protein, and the method comprises the following steps: obtaining sequence data of lncRNA and miRNA, and protein data; calculating the similarity of the lncRNA, the miRNA and the protein, and constructing a heterogeneous information network by taking the lncRNA, the miRNA and the protein as nodes and taking the similarity relationship among the lncRNA, the miRNA and the protein as edges; extracting a sub-graph from the heterogeneous information network according to the meta-path, and performing graph convolution operation on the sub-graph to generate feature representations of lncRNA, miRNA and protein; carrying out fusion treatment on the feature representations of the lncRNA, the miRNA and the protein to obtain a fused feature representation; and inputting the fusion feature representation into a trained prediction model for prediction to obtain a prediction result of the interaction between the lncRNA and the protein. According to the method, the adaptability on diversified data sets is enhanced, the interaction between the lncRNA and the protein can be predicted more accurately, and the accuracy of predicting the interaction between the lncRNA and the protein is effectively improved.

The invention discloses a drug target binding affinity prediction method based on collaborative attention, and belongs to the technical field of natural language processing, and the method comprises the steps: building a CLAT-DTA prediction model comprising an input data representation module, a feature extraction module, an information fusion module and a prediction module; converting drug molecules into fingerprint representation, and pre-training protein sequence data by using ESM; extracting drug data by using Encoder, and extracting protein data by using Bi-LSTM (Bidirectional Long Short-Term Memory); fusing the drug target data using a collaborative attention mechanism; three-layer full ligation is used to predict drug target binding affinity. According to the method, important information can be better polymerized, and the binding affinity between the drug and the protein can be predicted.

The present disclosure provides methods to identify peptides and small molecule moieties that are able to modulate protein-protein interactions (PPIs). Some moieties can disrupt specific PPIs within a complex, or disrupt variant-specific PPIs. Some moieties can alternatively bridge between two proteins in a protein-specific or a variant-specific manner. The methods described enable generation of compounds able to modulate PPI networks within cells with implications for drug development for pathological conditions.

According to the present invention, a technique which enables the production of an antimicrobial peptide Persulcatusin at reduced cost has been developed. A plant cell into which a polynucleotide sequence that encodes a gene for a protease to which a signal peptide localized in an intercellular organelle is added and a polynucleotide sequence that encodes a Persulcatusin fusion protein to which a signal peptide localized in an intracellular organelle different from the aforementioned intracellular organelle is added are introduced is produced, wherein, in the Persulcatusin fusion protein, a sequence that is cleavable with the protease is disposed between Persulcatusin and a protein that fuses to the Persulcatusin. Thus, Persulcatusin, which can serve as a therapeutic agent for bovine mastitis, can be produced at low cost.

A complementation system including two fragments of photoactive yellow protein (PYP), or truncated fragments thereof, and its use with a fluorogenic hydroxybenzylidene rhodanine (HBR) analog for detecting interactions between biological molecules of interest, in particular between proteins of interest. Especially, a complementation system including a first PYP fragment having an amino acid sequence having at least about 70% identity with the amino acid sequence of SEQ ID NO: 23, or a truncated fragment thereof including at least 89 consecutive amino acids from the C-terminal end of the amino acid sequence; and a second PYP fragment having an amino acid sequence having at least about 70% identity with the amino acid sequence of SEQ ID NO: 34, or a truncated fragment thereof including at least 8 consecutive amino acids of the amino acid sequence, preferably 8 consecutive amino acids from the N-terminal end of the amino acid sequence.

The application provides a boron-nitrogen-carbon nanosheet reinforced protein composite hydrogel, a preparation method and application thereof, and the protein composite hydrogel comprises the following raw material components: bovine serum albumin, boron-nitrogen-carbon nanosheets and a coupling agent, the coupling agent is configured to trigger the bovine serum albumin to be chemically cross-linked by itself to form a cross-linked network, and trigger the bovine serum albumin and the boron-nitrogen-carbon nanosheets to be chemically cross-linked to form a cross-linked network. The boron-nitrogen-carbon nanosheet reinforced protein composite hydrogel has good mechanical properties and biological activity, and can repair bone defects, especially large defects of load-bearing bones. The preparation method of the boron-nitrogen-carbon nanosheet reinforced protein composite hydrogel is simple and safe, only a small amount of coupling agent is introduced, the chemical bond cross-linking between proteins can be triggered, and the prepared hydrogel improves the defects of insufficient mechanical strength and insufficient biological activity of traditional hydrogels.

The invention belongs to the technical field of ion exchange chromatographic packing, and particularly relates to ligand-optimized ion exchange chromatographic packing as well as a preparation method and application thereof. The optimized ion exchange chromatography packing comprises a chromatography packing matrix and an ion exchange ligand. The ion exchange ligand comprises a functional group, a connecting arm and an auxiliary group. The auxiliary group is an alkyl chain segment or an alkoxy chain segment or an aryl chain segment with hydrophobic property. The ligand-optimized ion exchange chromatographic filler provided by the invention is used for adjusting the acting force of the ion exchange chromatographic filler, and selective adsorption and elution of different proteins on a chromatographic column are realized by utilizing various synergistic action mechanisms such as electrostatic interaction, hydrophobic interaction and the like between the optimized ligand and the proteins; therefore, the purpose of efficiently separating and purifying a complex protein mixed system is achieved, and the protein separation performance is remarkably improved.

The invention discloses a protein interaction prediction method and device and a storage medium, and relates to the technical field of biomedicine, and the method comprises the following steps: S1, identifying functional groups of a two-dimensional protein structure diagram, S2, capturing geometric structure information of proteins, and obtaining atomic characteristics of two proteins, S3, defining one-dimensional sequences of the two proteins as U and V respectively, s4, updating the three-dimensional coordinates of the atoms in the U and the V, and obtaining the feature representation of the U and the V; s5, performing feature fusion on the two proteins to obtain a fusion vector; s6, predicting and analyzing an interaction result between the two proteins; a double-view Gram matrix considering functional group information is used for capturing missing protein three-dimensional structure information, and an improved sliding attention mechanism is used for replacing a traditional data-driven attention mechanism, so that the problems that the sliding attention mechanism does not consider the influence of residues in the same sequence and is only suitable for a one-dimensional sequence are solved; and thus, the protein-protein interaction prediction precision is improved.

Structure-based drug design using a computer, includes: identifying a protein target of pharmacological interest; identifying at least three different ligands for binding to the protein; for each of the ligands, determining a relative strength of binding between the ligand and the protein to form a corresponding complex; ranking the different ligands identified as forming complexes with the protein based on the determined relative binding free energies; and identifying one or more of the ranked ligands as candidates for the drug based on the ranking. Determining the relative strength includes: simulating, using the computer, a set of pairs of different ligands forming at least one closed thermodynamic cycle comprising a plurality of legs linking at least two different ligand pairs to determine multiple relative binding free energy differences for the set of pairs of different ligands; and determining, using the computer, a non-zero hysteresis magnitude associated with each closed thermodynamic cycle by summing the relative binding free energy differences for each of the ligand pairs that form a closed thermodynamic cycle.

This disclosure provides a method, apparatus, medium, and electronic device for predicting RNA-protein interactions; relating to the field of artificial intelligence technology. The method includes: acquiring an RNA-protein pair to be predicted; extracting features from the RNA-protein pair to obtain sequence features; vectorizing the RNA-protein pair to obtain RNA sequence representation vectors and protein sequence representation vectors; based on the sequence features, RNA sequence representation vectors, and protein sequence representation vectors of the RNA-protein pair, using an interaction prediction model to obtain predicted interaction values ​​for the RNA-protein pair; and determining the interaction between the RNA and protein based on the predicted interaction values.

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 present invention discloses a method for predicting protein-protein interactions based on cross-graph representation learning, belonging to the field of protein-protein interactions, comprising the following steps: S1, collecting a prediction data set of protein-protein interactions, then performing feature processing on proteins to construct a protein graph; S2, using a graph encoder based on GCN to learn the spatial structure information of the protein graph; S3, using an encoder based on a self-attention module to learn the information between receptor proteins and ligand proteins; S4, using a dual interaction graph module to learn the information of residues between receptor proteins and ligand proteins; S5, generating a classifier for predicting protein-protein interactions. The present invention is used to solve the problem that the performance of existing methods for predicting protein-protein interactions often degrades in different fields.

The application relates to the fields of artificial intelligence and digital medical technologies, and provides a protein affinity change prediction method and related equipment, a first initial graph network of a protein before mutation is constructed, a second initial graph network of a protein after mutation is constructed; the first initial graph network is updated in the graph at least once, and the first initial graph network and the second initial graph network are updated between graphs at least once until a first target graph network is obtained; the second initial graph network is updated in the graph at least once, and the second initial graph network and the first initial graph network are updated between graphs at least once until a second target graph network is obtained; according to the first target graph network and the second target graph network, the affinity change between the protein before mutation and the protein after mutation is predicted, so that the prediction accuracy of the protein affinity change is improved.

The invention discloses a drug-target affinity prediction method based on text guidance and a hybrid expert network, and belongs to the technical field of biological information. The method aims at solving the problems that an existing drug-target affinity prediction method is only limited to single-modal feature extraction, and complex nonlinear interaction relations between drugs and proteins are difficult to capture. Based on drug molecular structure data, protein sequence data, text description information and drug-target affinity data, unified input features are formed through standardization and multi-modal feature construction, a structure-text cross-modal alignment mechanism is introduced in comparative learning to carry out characterization learning on the multi-modal features of drugs and proteins, and the multi-modal features of the drugs and the proteins are obtained. Semantic alignment and feature decorrelation between different modal representations of the same entity are realized through joint optimization of InfoNCE loss and Barlow Twins loss; four heterogeneous expert networks are determined in combination with a gating network and a multi-head cross attention mechanism to capture drug-target interaction, and adaptive weighted fusion is performed to realize prediction.

The invention discloses a preparation method of magnetic cottonseed protein nanospheres with high lipase loading, which relates to the technical fields of enzyme engineering and lipase loading in the biological industry, and includes: using the antisolvent method to coat nano-Fe3O4 particles with plant polyphenols and cottonseed protein to obtain magnetic cottonseed protein nanospheres; adding the magnetic nanoprotein spheres into a lipase solution, and using the covalent and secondary interactions between the plant polyphenols and the cottonseed protein to load the lipase on the magnetic cottonseed protein nanospheres; separating, washing, and drying to obtain magnetic cottonseed protein nanospheres with high lipase loading. The invention uses the antisolvent method to coat the nano-particle Fe3O4 to prepare magnetic cottonseed protein nanospheres, fixes the lipase on the surface of the nanospheres through the covalent and secondary interactions between the plant polyphenols and the protein, optimizes the parameters, and obtains magnetic cottonseed protein nanospheres with high lipase loading. The obtained magnetic cottonseed protein nanospheres of the invention can realize the efficient catalysis and recycling of lipase.

To provide a method for treating specimens including clinical samples preserved in a liquid-based cytodiagnosis preservative containing formaldehyde.SOLUTION: The method begins with a step of preparing a reaction mixture by mixing a specimen with a protease enzyme and 2-imidazolidone or other formaldehyde scavenger. After that, the reaction mixture is incubated at an elevated temperature for a period of time sufficient enough to reverse the chemical modification by formaldehyde to the nucleic acid which may be contained in the specimen. By this step, at least part of the chemical modification caused by reaction between formaldehyde and nucleic acid or protein is reversed. For example, chemical crosslinks may be broken. Next, there is a step for isolating the nucleic acid from the reaction mixture after the incubation step. In the final step, in vitro amplification reaction is carried out using the nucleic acid from the isolation step as a template.SELECTED DRAWING: None

The application discloses a CUT&Tag method applied to plant pollen. The CUT&Tag method of plant pollen protected by the application contains Percoll in a nuclear extraction solution, so as to remove starch in pollen cells. After the starch is removed, the method further comprises a step of removing polysaccharides and polyphenols in the pollen cells by using a buffer containing 1,6-hexanediol and glycerol. The concentration of the Percoll in the nuclear extraction solution can be 60%. Experiments prove that the CUT&Tag method of plant pollen established in the application can effectively remove polysaccharides, polyphenols, high starch and other impurities rich in the pollen, and can effectively identify the interaction between DNA and proteins in the plant pollen. The method of the application can also be popularized to the research on the interaction between DNA and proteins in other tissues of corn or other plants.

Disclosed herein is the use of DNA aptamer assemblies of varying DNA length, structure, and sequence to both bind to collagen and other proteins, to then act as a biocompatible, degradable, reversible, or permanent 3D crosslinkers between proteins, and to service as a biologically functional material when using the appropriate aptamer sequence. Therefore, disclosed herein are compositions comprising collagen fibers crosslinked with DNA aptamers. Also disclosed are devices and implants made from or coated with collagen fibers crosslinked with DNA aptamers. Also disclosed are methods of making collagen fibers. Also disclosed are kits for producing collagen fibers. Also disclosed herein are compositions DNA aptamers in a collagen fiber matrix that stabilizes the DNA aptamer.

The present disclosure relates to compounds, complexes, compositions, kits and methods for determining interacting and / or binding sites between e.g., proteins, proteins and nucleic acids, proteins and small molecules, or intrachain protein domains. The disclosure provides rapid and direct positive identification of the contact interface region between such molecules, and can be applied to individual interacting pairs, as well as large-scale or global interactions.

Systems and methods are disclosed for building a regression-based machine learning algorithm to predict native and near-native binding confirmations between two or more proteins. They include receiving training data, the training data representing a plurality of protein to protein docking poses based on one or more hotspots and a set of descriptors characterizing interaction interface features of one or more of the plurality of protein to protein docking poses. The systems and methods further specify a dedicated training data set based on a variety of single domain interactions. The training data set comprises an information space required to create dedicated regression and classification models in order to identify near native binding configurations. A specific and diverse set of interaction interface descriptors is calculated to provide the foundation for both, the regression and classification models.

Characterization of the binding dynamics at the interface between any two proteins that specifically interact plays a role in myriad biomedical applications. The methods disclosed herein provide for the high-throughput characterization of the specific interaction at the interface between two protein binding partners and the identification of functionally significant mutations of one or both protein binding partners. For example, the methods disclosed herein may be useful for epitope and paratope mapping of an antibody-antigen pair, which is useful for the discovery and development of novel therapies, vaccines, diagnostics, among other biomedical applications.

This application proposes a method, device, electronic device, and storage medium for constructing a mirror protein interaction map. The method for constructing a mirror protein interaction map includes: constructing a first graph neural network based on the original protein, and inputting the amino acid sequence of the original protein into the first graph neural network to predict the properties of the original protein and the interactions between the original protein and other original proteins; constructing a second graph neural network based on the interactions between the original proteins; inputting any amino acid sequence into the second graph neural network to predict the properties, three-dimensional structure, and interactions between the mirror protein and other proteins corresponding to the amino acid sequence; and constructing a mirror protein interaction map using the protein properties and three-dimensional structure as node information and the interactions between any two proteins as edges. This application can predict the structure and properties of mirror proteins and construct a mirror protein interaction map.

The application discloses a conformation prediction method. The method comprises the following steps: acquiring a conformation prediction model, and acquiring structure data of a complex to be predicted; wherein the structure data of the complex to be predicted comprises structure data of a ligand and structure data of a target protein; inputting the structure data of the ligand and the structure data of the target protein into the conformation prediction model to acquire ligand features and target protein features; performing position embedding, cross attention and connection operation on the ligand features and the target protein features to obtain a connection result matched with the ligand features and the target protein features; and predicting a target binding conformation of the structure data of the ligand and the structure data of the target protein according to the connection result. The technical scheme of the embodiment of the application provides a new conformation prediction method, learns important features such as shapes between ligands and target proteins, improves the prediction performance of the binding conformation, and helps to find the optimal binding conformation.

The invention discloses an HIV (human immunodeficiency virus) gene regulatory network construction method based on a Boolean network model, which comprises the following steps of: 1, screening HIV-related genes and proteins and regulatory action relationships between genes, between genes and proteins and between proteins from Pubmed, constructing a directed network graph according to the relationships, and optimizing the network; a Boolean polynomial is then defined for each node, and the network is converted into a Boolean model. The invention provides an effective method for researching dynamic information of a network, which is beneficial to revealing a regulation mechanism of a biological system, so that a theoretical basis is provided for disease diagnosis, treatment and drug development. In the aspect of researching a new HIV drug target, the invention also helps to reveal a regulation relation in an HIV infection stage and a replication process, identifies key genes and proteins participating in HIV infection and replication, and helps to discover a new treatment target and optimize an antiviral treatment strategy.

The present invention relates to novel bifunctional molecules capable of undergoing bioorthogonal reactions and inducing proximity between two proteins, methods of inducing proximity between two proteins employing said novel molecules and bioorthogonal reactions and genetic code expansion, methods of evaluating protein-protein proximity interactions employing the novel bifunctional molecules, medical uses of the novel molecules, and methods of treatment of a disease involving post-translational modifications of a protein employing the novel bifunctional molecules.

The present invention relates to the field of protein prediction technology, and in particular to a protein interaction prediction method based on a dual synergy mechanism. The present invention introduces protein synergy into a twin architecture by utilizing the interactive attention between protein structure pairs, thereby realizing the sharing of interaction knowledge between proteins. The present invention proposes a protein synergy mechanism based on interactive attention, so that the determination of key residues in a protein depends not only on its own characteristics, but also on its cooperative proteins, thereby realizing knowledge sharing between two proteins and further improving the interaction prediction accuracy of the model. The present invention introduces protein function prediction tasks and subcellular location prediction tasks into the training process of the protein interaction prediction model, so that the knowledge shared between a pair of proteins can be complemented in different tasks, further improving the interaction prediction accuracy of the model.

A dual expression vector and a method are provided. The dual expression vector has a first multiple cloning site and a second multiple cloning site. The genes of the different proteins could be inserted into the first multiple cloning site and the second multiple cloning site of the dual expression vector for testing the interaction between the different proteins.

Disclosed is a method performed by a computing device. The method may include a method for training an artificial intelligence model by using interaction data between a protein and a ligand. The method may include: converting a binding structure between a ligand and a protein into at least one binding word in text form which is processable in an artificial intelligence-based Large Language Model (LLM); generating training data using the at least one binding word; and training the LLM using the training data.