25 results about "Protein pair" patented technology

The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilizing compound-protein machine learning representations to generate target results. For example, the disclosed systems can utilize a compound-protein interaction machine learning model to generate a compound-protein machine learning representation for compound protein pairs. The disclosed systems can utilize the compound-protein machine learning representation to train and utilize other target machine learning models in generating predicted bioactivity results. For example, the disclosed systems train a target machine learning model from compound-protein machine learning representations to generate ADMET predictions and / or biological perturbation program predictions. Furthermore, the disclosed systems can utilize one or more explainability models in conjunction with target machine learning models trained based on compound-protein machine learning representations to identify proteins that contribute to predicted bioactivity results.

The invention aims to provide a method, equipment, medium and program product for determining acidity coefficient, the method comprises the following steps: constructing a simulation box corresponding to protein, the simulation box comprising the protein, a corresponding solvent and a buffer solution; performing molecular dynamics simulation on the simulation box by utilizing a trained machine learning force field to obtain corresponding track file information; and determining an acidity coefficient corresponding to each drippable site in the protein based on the track file information. A dynamic process of protein in a solution is accurately and efficiently simulated by utilizing a machine learning force field, and an accurate acidity coefficient is calculated based on a state of a protein solution system in simulation.

A method for generating binding peptides presented by any given Major Histocompatibility Complex (MHC) protein is presented. The method includes, given a peptide and an MHC protein pair, enabling a Reinforcement Learning (RL) agent to interact with and exploit a peptide mutation environment by repeatedly mutating the peptide and observing an observation score of the peptide, learning to form a mutation policy, via a mutation policy network, to iteratively mutate amino acids of the peptide to obtain desired presentation scores, and generating, based on the desired presentation scores, qualified peptides and binding motifs of MHC Class I proteins.

The invention discloses a drug-target interaction prediction method combining link-perceived cross attention and link-level contrast learning, and introduces a link-perceived cross attention mechanism which allows global features of a sequence (such as protein) to serve as a query to pay attention to internal details of a paired sequence (such as a drug), so as to predict drug-target interaction. Context-aware local features are dynamically generated for each drug-protein pair. Besides, in order to cope with the challenge that information of a knowledge graph is difficult to apply to a cold start scene, a link-based contrast learning strategy (Link-based contrast learning) is designed, and local features generated by a sequence mode through cross attention are aligned with local features obtained through different relation links in a relation mode, so that the probability that the information of the knowledge graph is applied to the cold start scene is lowered, and the probability that the information of the knowledge graph is applied to the cold start scene is lowered. Richer and finer-grained supervision signals are provided for the model, and the sequence model is prompted to learn a'relation mode 'contained in the knowledge graph instead of memorizing a'relation instance' of a specific entity.

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.

This application discloses a protein liquid-liquid phase separation prediction method based on cross-level information transfer. The method obtains the amino acid sequence of the target protein and generates residue-level fusion feature sequences using a branched coding network and a gated fusion network. These residue-level fusion feature sequences are then input into a residue prediction head to generate residue-level driving probabilities. The K highest probability values ​​from these driving probabilities are extracted, and corresponding high-response statistics are constructed. Protein-level aggregation of the residue-level fusion feature sequences is performed to generate a protein-level global representation. This global representation and the high-response statistics are then input into a protein prediction head to output a liquid-liquid phase separation tendency score for the target protein. This method achieves cross-level collaborative inference of residue-level driving region localization and protein-level phase separation tendency prediction, solving problems such as the disconnect between protein-level prediction and residue-level localization, and the dilution of the contribution of highly active driving sites by non-driving residues, thus improving the accuracy of the prediction results.

The embodiment of the invention discloses a protein generation method and device, electronic equipment and a storage medium, and the method comprises the steps: firstly obtaining protein demand information which comprises attribute information and functional domain information corresponding to protein; and then, performing feature extraction on the attribute information to obtain protein feature data corresponding to the attribute information, and performing feature extraction on the functional domain information to obtain functional domain feature data matched with a functional domain corresponding to the functional domain information, so as to obtain the protein feature data according to the protein feature data and the functional domain feature data. And generating a target protein containing the functional domain corresponding to the functional domain information. According to the technical scheme, the protein with the specific functional domain can be generated, the matching degree between the generated protein and the protein demand information is improved, and the success rate of protein generation is improved.

The invention discloses a protein targeted degradation system based on a biological orthogonal protein pair and application of the protein targeted degradation system, and belongs to the field of biological medicine. Wherein the protein targeting degradation system comprises a ligand A targeting a tumor specific receptor, a ligand B targeting a tumor target protein and a biological orthogonal protein pair, and the ligand A and the ligand B respectively form a fusion protein with one protein in the biological orthogonal protein pair. The targeted degradation system provided by the invention can realize precise, efficient and safe degradation of tumor-related proteins (such as EGFR, PD-L1, HER2, c-MET and the like) through dual precise recognition of the targeting ligand and the bio-orthogonal protein pair, thereby realizing anti-tumor treatment.

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.

The present invention relates to a compound of formula (I) (G-X-NH) o-Y wherein: G is a glycan comprising n monosaccharide units linked by a glycosidic bond; n is an integer of monosaccharide units connected through a glucosidic bond, preferably n is 2 to 200, more preferably 2 to 100, and most preferably 2 to 20 monosaccharide units; o is an integer of 0 to 10, if Y is a peptide or protein, Y corresponds to an integer of 1 to 10, preferably an integer of 1 to 5, per 10 kDa of peptide or protein; x is based on an aldose, linked via a glycosidic bond to G and wherein the aldehyde group of the aldose has reacted with the primary amino group of the group Y to obtain a product of formula (I) wherein the aldehyde group of the aldose has been reduced in form in formula (I) to the corresponding secondary amino group preferably by reductive amination to obtain the secondary amino group of formula (I); and Y is selected from amino acids, peptides and proteins.

This invention relates to the field of bioinformatics, and particularly to a method and system for predicting protein interaction using a two-branch protein sequence feature fusion approach. The method includes: acquiring a first protein sequence and a second protein sequence and vectorizing them respectively to generate corresponding primary features; performing dynamic channel attention enhancement processing on the first protein's primary features to generate enhanced features for the first protein; performing semantic embedding encoding processing on the second protein's primary features to generate semantic features for the second protein; fusing the enhanced features and semantic features to obtain a two-branch interaction feature set; constructing nodes of a graph isomorphic network using the elements of the set; generating protein pair structure embedding representations based on feature weighting aggregation of neighboring nodes; inputting these representations into a fully connected classifier; and outputting protein interaction prediction results. This invention effectively solves the problem that existing technologies cannot fully capture the lack of collaborative representation of multi-scale biological semantics in protein interaction prediction.

The invention relates to the technical field of computer-aided drug design, in particular to feature matching sampling and screening equipment based on a protein pocket, and aims to solve the technical problems that in the prior art, when protein pair data with extremely unbalanced positive and negative samples is processed, the sampling time is short; the generalization ability of the model is poor, and the correlation characteristics between the protein pairs cannot be effectively captured. The core of the invention comprises: a feature extraction module for obtaining feature representation of a protein pocket; the feature fusion module is used for explicitly modeling a bidirectional dependency relationship between protein pairs by adopting a cross attention network; the data rebalance system integrates the generative adversarial network to perform positive sample data enhancement, and adopts a popularity-based dynamic negative sampling strategy to screen high-quality negative samples; and a classification output module. According to the method, the accuracy and robustness of predicting the similarity of the protein pockets on highly heterologous and unbalanced data are remarkably improved, the AUC value can reach 0.848, and the method is superior to a traditional method.

Disclosed in the present invention is a method for detecting a protein having changes in an energy state, and affinity of a ligand to a protein. Specifically, after the energy state of a protein changes, the tolerance to enzyme cleavage destruction changes, the structure of the protein in a low-energy state is also destroyed under a non-denaturation condition by using a large amount of enzymes, and a small peptide fragment which has a molecular weight of less than 5 KDa and can be directly used for bottom-top mass spectrometry analysis is directly generated. The method has extremely high sensitivity, and quantitative proteomics is used to find enzyme cleavage differential peptide fragments, and proteins to which the differential peptide fragments belong and the positions in the proteins are analyzed, so that a protein having changes in an energy state, and a change region can be determined in the whole proteome range. If the energy state of the protein changes due to addition of a ligand, the method can determine a binding protein and a binding region of the ligand; and the output of a quantitative result on the peptide fragment level further enables the method to determine the local affinity of binding of the ligand to the protein.

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 disclosure relates to modified proteins, methods, compositions and kits for mapping the methylation status of nucleic acids comprising 5-methylcytosine and 5-hydroxymethylcytosine. In some embodiments, the modified proteins have been altered to increase protein stability. In some embodiments, a protein selectively acts on certain modified cytosines of a target nucleic acid and includes one or more substitution mutations that enhance the protein's selectivity for certain modified cytosines, optionally enhance the stability of the protein, or optionally enhance both selectivity and stability. Also provided are compositions and kits comprising one or more of the proteins, as well as methods of using one or more of the proteins.

A method for training a vector model, including: obtaining more than one RNA sequence and more than one protein sequence; obtaining more than one first RNA vector by vectorizing the more than one RNA sequence; obtaining more than one first protein vector by vectorizing the more than one protein sequence; determining an interaction between the RNA sequence and the protein sequence according to the first RNA vector and the first protein vector; obtaining a similarity of more than one RNA-RNA pair by calculating a distance between any two RNA sequences; obtaining a similarity of more than one protein-protein pair by calculating a distance between any two protein sequences; training the vector model according to an interaction between the RNA sequence and the protein sequence, the similarity of the RNA-RNA pair and the similarity of the protein-protein pair.

The present application relates to artificial intelligence, and provides a drug candidate library construction method, device, equipment and storage medium. The method performs site mutation on the initial protein to obtain a new protein, performs graph characterization on the new protein and the initial protein to obtain a new characterization vector and an initial characterization vector, calculates a spatial structure loss value of the new protein and the initial protein, inputs the new characterization vector and the spatial structure loss value into a protein property prediction model to obtain a predicted property, and screens a target protein from a plurality of new proteins. Amino acid sequences are generated based on antigen-antibody complexes and disease antigens, and the target protein and the amino acid sequences are combined to improve the rationality of generating the drug candidate library. In addition, the present application also relates to blockchain technology, and the drug candidate library can be stored in the blockchain.

A method, apparatus, medium, and electronic device for predicting RNA-protein interactions are disclosed, relating to the field of artificial intelligence technology. The method includes: acquiring an RNA-protein pair to be predicted (S210); extracting features from the RNA-protein pair to obtain sequence features (S220); vectorizing the RNA-protein pair to obtain RNA sequence representation vectors and protein sequence representation vectors (S230); based on the sequence features, RNA sequence representation vectors, and protein sequence representation vectors of the RNA-protein pair, using multiple interaction prediction models to obtain multiple interaction prediction values ​​for the RNA-protein pair (S240); and determining the interaction between the RNA and protein based on the multiple interaction prediction values ​​(S250).

Disclosed is a method for predicting protein-protein interactions between plant proteins and pathogen proteins. The method comprises: by one or more computing devices: a) transforming (102) one or more protein sequences (208) of a plant into a respective plant protein feature vectors (302; 306) and transforming (104) one or more protein sequences (210) of a pathogen into a respective pathogen protein feature vectors (304; 308); b) forming (106) a plurality of different feature vector pairs (313) respectively comprising one (312) of the pathogen protein feature vectors and one (310) of the plant protein feature vectors; c) providing (108) the vector pairs to a trained machine learning model (212), and in response receiving (110), for the pairs of feature vectors, an indication (322) if at least one output protein pair represented by one of the feature vector pairs is predicted by the trained machine-learning model to interact.

The invention provides a protein structure generation method based on a diffusion model, relates to the technical field of artificial intelligence, and belongs to the technical field of biomedicine and AI crossing. According to the method, a new protein skeleton structure is constructed step by step by simulating a'generation-denoising 'process of protein, and the method comprises the following steps: expressing protein residues in a dual mode; wherein the dual modes comprise that the protein based on the point cloud is adopted only in the forward diffusion process and the protein based on the FSframe is adopted in the reverse diffusion process; performing feature fusion on the information of the protein residues; updating residue pair information after feature fusion through triangular multiplication; and improving the diffusion model to generate a protein structure. According to the invention, the contribution of amino acid to other sequence information can be selectively enhanced or weakened according to the relationship between amino acid and other amino acid, and key residue information between the amino acid and a protein structure can be more accurately captured.

The invention discloses a hydrogel base PVAamp and a preparation method thereof. The invention relates to a preparation method and application of an SA-AAO nano-channel sensing film. According to the invention, PVAamp is adopted; the SA hydrogel provides high hydrophilicity, can form a compact and highly ordered hydration layer on the surface of the hydrogel, and can effectively prevent most of hydrophobic proteins from penetrating through the hydrogel layer in combination with the steric hindrance effect dual protection of the nanoscale network aperture, thereby greatly reducing the probability of direct contact, non-specific adsorption or blockage of the proteins to the surface of AAO (Anodic Aluminum Oxide); the influence of protein on the detection target transmembrane current, namely PVAamp, is reduced; the signal attenuation ratio of the SA-AAO heterogeneous film is greatly reduced from 96.36% to 0.06%. According to the blade coating method, the thickness of the hydrogel can be flexibly and stably regulated and controlled, the hydrogel layer is easy to replace due to the hierarchical structure in the heterogeneous film, the AAO film can be repeatedly used, and the cost is reduced. The preparation method is simple to operate, stable in interface and excellent in protein interference resistance.

This invention relates to the field of bioinformatics, and more particularly to a method and system for predicting protein interactions based on multimodal geometric feature fusion. The method includes: extracting features from the amino acid sequence, three-dimensional structure, and three-dimensional coordinates of a target protein to generate protein sequence features, protein structural features, and protein spatial features; performing standardization and adaptive weighted fusion on these features to generate unified multimodal protein features; updating node features in a protein graph constructed based on the multimodal protein features by combining graph position encoding and a global attention mechanism; sequentially encoding the center node, subgraph, and context of the node features to generate a comprehensive node embedding; and predicting the interaction type and probability between protein pairs based on the comprehensive node embedding. This invention effectively solves the problems of feature representation bias and insufficient complex interaction modeling capabilities caused by traditional PPI prediction methods that ignore protein geometric structure information and multi-level local associations.

The application aims to provide a method and device for constructing a protein sequence prediction model, which comprises: determining corresponding surface point cloud information and sample protein sequence information of a sample protein based on sample protein information, wherein the sample protein information comprises protein sequence information and protein structure information, and sequence information belonging to the surface of the sample protein in the sample protein sequence information is masked; and training a corresponding protein sequence prediction model based on the surface point cloud information and the sample protein sequence information of the sample protein, wherein the protein sequence prediction model comprises a structure encoder, a sequence encoder and a corresponding decoder. In the construction of the protein sequence prediction model, the application introduces information of a protein surface for sequence prediction, which can effectively improve the prediction accuracy of the model and improve the surface accuracy of the predicted protein sequence.

This invention relates to the field of protein processing technology, and more particularly to a protein processing method, apparatus, storage medium, and computer program product. The method includes: acquiring a protein to be processed; generating at least one self-generated protein corresponding to the protein to be processed, wherein the protein to be processed and the self-generated protein are homologous proteins; storing at least one self-generated protein in a protein database, and performing structure prediction on the protein to be processed based on the protein to be processed and / or the self-generated protein in the protein database. This invention addresses the deficiency in existing technologies where the number of homologous proteins is small, leading to inaccurate structural prediction results for structural proteins, and improves the performance of protein structure prediction.

The disclosure provides a vector model training method, a negative sample generation method, a storage medium and an electronic device; it relates to the technical field of artificial intelligence. The method comprises: obtaining a plurality of RNA sequences and a plurality of protein sequences; vectorizing the plurality of RNA sequences to obtain a plurality of RNA first vectors; vectorizing the plurality of protein sequences to obtain a plurality of protein first vectors; determining the interaction between the RNA sequences and the protein sequences according to the RNA first vectors and the protein first vectors; calculating the distance between any two RNA sequences to obtain the similarity of a plurality of RNA-RNA pairs; calculating the distance between any two protein sequences to obtain the similarity of a plurality of protein-protein pairs; training a vector model according to the interaction between the RNA sequences and the protein sequences, the similarity of the RNA-RNA pairs and the similarity of the protein-protein pairs, and generating a target negative sample using the trained vector model.