44 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 provides a design method of a protein variant structure based on molecular dynamics, and belongs to the technical field of molecular dynamics simulation. A protein-standard nucleic acid compound ground molecule system and a protein-nonstandard sequence compound ground molecule system are respectively constructed, and based on a molecular dynamics simulation technology, protein conformation stability, low-energy conformation states, main change processes, collaborative movement and key residues of the protein-standard sequence system and the protein-nonstandard sequence system are compared, so that protein conformation stability and low-energy conformation states of the protein-standard nucleic acid compound ground molecule system and the protein-nonstandard sequence compound ground molecule system are obtained. The molecular mechanism of protein-nucleic acid interaction is analyzed, the recognition behavior of the protein on the standard nucleic acid sequence and the activation process of the standard nucleic acid sequence on the corresponding function of the protein are understood from the molecular level, and finally the protein variant with more related functions is designed.

The invention discloses a method for rapidly determining the content of breast milk oligosaccharide in dairy products, which comprises the following steps: sampling and pretreating different types of dairy products according to sample states, carrying out ultrasonic extraction, refrigerated centrifugal degreasing and centrifugal ultrafiltration protein purification on the obtained sample, and reducing the purified sample solution by using sodium borohydride to obtain a sample solution to be detected; reducing the breast milk oligosaccharide standard substance by sodium borohydride to obtain a standard solution to be detected; determining the standard substance solution and the to-be-detected sample solution by adopting ultra-high performance liquid chromatography-tandem mass spectrometry, establishing a standard curve, and carrying out quantitative analysis on the to-be-detected sample solution; the chromatographic conditions are as follows: an ACQUITY UPLC BEH Amide hydrophilic interaction chromatographic column is adopted; the mobile phase A is 20 mmol / L ammonium formate; the mobile phase B is acetonitrile; and gradient elution.

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.

The invention relates to a drug target determination method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a protein heat map corresponding to candidate proteins; based on a feature extraction model, extracting features of the protein heat map to obtain heat map features corresponding to the candidate proteins; based on the heat map features corresponding to the candidate proteins, clustering the candidate proteins to obtain a plurality of candidate protein sets; based on the temperature data and the protein concentration data of each candidate protein in a candidate protein set, determining the protein concentration difference significance corresponding to the candidate protein set, and based on the protein concentration difference significance and the protein concentration data of the candidate proteins, determining the protein concentration difference significance corresponding to the candidate protein set; and determining standard reference data of the candidate proteins, and determining a drug target based on the standard reference data of each candidate protein in the plurality of candidate protein sets. According to the embodiment of the invention, the drug target can be accurately determined.

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 application provides a double cell recognition method, comprising the following steps: step one) obtaining a data set to be subjected to double cell recognition, and then clustering and grouping the data set to be subjected to double cell recognition to obtain a plurality of cell populations; step two) determining mutually exclusive protein pairs according to the cell types of the data set to be subjected to double cell recognition, and then determining the expression negative cell population and the expression positive cell population corresponding to each protein in the mutually exclusive protein pairs by using the COSG method of cyclic iteration in the cell populations obtained in step one); step three) calculating the threshold value of the positive and negative expression of each protein in the mutually exclusive protein pairs according to the data in the expression negative cell population and the expression positive cell population; and step four) recognizing double cell data in the data set to be subjected to double cell recognition according to the threshold value. The double cell recognition method based on the COSG method of cyclic iteration is more stable and more effective in the recognition of positive and negative cell population modules.

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 application relates to the field of computer technology and provides a method, apparatus, electronic device, and computer program product for constructing a protein language. The method includes: segmenting a target protein based on secondary structure information to obtain two or more target protein fragments; determining the protein language terms corresponding to each target protein fragment; and determining the protein language statement corresponding to the target protein based on the protein language terms corresponding to each target protein fragment. This application facilitates the capture of semantic information at the molecular level by the protein language model, thereby obtaining better protein representation.

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.

A nutritional composition for administering to a human includes an amount of bioavailable protein that is safe for human consumption and that is effective for supporting the synthesis of proteins, and the repair and maintenance of cells and tissues throughout the body. An amount of a medium-chain triglyceride that is safe for human consumption and that is effective for maintaining gut health, an amount of an emulsifier that is safe for human consumption and that is effective for maintaining cellular health, and an amount of soluble fiber that is safe for human consumption and that is effective for maintaining or enhancing a health of the gut or cardiovascular system are also included. An amount of one or more vitamins and minerals that are effective for blood cell production are also included. The nutritional composition is formed as a chewable dosage form comprising a gelatin matrix.

Embodiments of the present application provide a protein stability prediction method and device, computer equipment and a storage medium. The method comprises: obtaining a first to-be-tested sequence corresponding to an original protein and a second to-be-tested sequence corresponding to a mutant protein; determining a plurality of first target residue features from the first to-be-tested sequence according to the attention mechanism of the protein language model and extracting the global features thereof to obtain first virtual structure microenvironment features; similarly, obtaining second virtual structure microenvironment features corresponding to a plurality of second target residue features; determining a first difference based on the first virtual structure microenvironment features and the second virtual structure microenvironment features, and determining a second difference based on a first global sequence feature corresponding to the first to-be-tested sequence and a second global sequence feature corresponding to the second to-be-tested sequence; and predicting based on the first difference and the second difference to obtain a protein stability prediction result. In this way, the accuracy of predicting the stability of the protein can be improved.

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 application provides a protein interaction prediction method and device, electronic equipment and storage medium, comprising: obtaining a first amino acid sequence corresponding to a first protein and a second amino acid sequence corresponding to a second protein; performing protein prediction based on the first amino acid sequence and the second amino acid sequence through a pre-trained target prediction network to obtain a protein prediction result; wherein the target prediction network comprises an amino acid embedding subnetwork, a vector encoding subnetwork and a prediction subnetwork, and the protein prediction result is used to represent the probability of interaction between the first protein and the second protein. The application can efficiently and accurately predict whether the proteins will interact, and can also realize cross-species protein interaction prediction.

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.

The application discloses a method for determining protein structure alignment and a related device. The method comprises the following steps: determining an initial quantum state to be prepared based on the structure of a target protein, wherein the target protein comprises a protein whose alignment mode is to be determined; constructing a target quantum circuit by using the initial quantum state and a Hamiltonian corresponding to the target protein; running and measuring the current target quantum circuit to obtain a final quantum state containing the alignment mode of the target protein; and determining the optimal alignment mode of the target protein according to the final quantum state. According to the embodiment of the application, the optimal alignment mode of the protein can be efficiently determined by using the eigen-parallelism of quantum computing.

The application provides a protein-protein docking method and system based on multi-region division, and relates to the technical field of biology. The method comprises the following steps: keeping the posture of one protein with a relatively large number of atoms in two docked proteins unchanged as a receptor protein, dividing the surface atoms of the receptor protein into a plurality of subspaces, independently and in parallel searching the posture of a ligand protein in the plurality of subspaces, determining the candidate ligand protein conformation generated by each subspace, greatly shortening the search time length of the protein-protein docking posture, improving the docking efficiency of the receptor protein and the ligand protein, and combining the candidate ligand protein conformations generated by each subspace, and then determining the posture of the ligand protein that is best docked with the receptor protein from the combined candidate ligand protein conformations, thereby improving the accuracy of the receptor protein and the ligand protein.

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.

A method implemented by one or more computer devices includes accessing a molecular descriptor matrix representing a set of amino acid sequences corresponding to a protein and refining a set of hyperparameters associated with a machine learning model trained to generate predictions of molecular binding properties of the protein. Refining the set of hyperparameters includes iteratively performing a process until a desired accuracy is reached, which includes reducing the molecular descriptor matrix by selecting one representative feature vector for each of a plurality of feature vector clusters, determining a most predictive feature vector of the selected representative feature vectors based on correlation, calculating a cross-validation loss based on the most predictive feature vector and a predetermined batch of binding data, and updating the set of hyperparameters based on the cross-validation loss. The method further includes generating predictions of molecular binding properties of the protein.

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 invention provides a protein data processing method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: filling first grid data of a first protein and a second protein from a plurality of dimensions according to different postures of the first protein and the second protein to obtain second grid data of each posture corresponding to the plurality of dimensions; based on second grid data of multiple dimensions corresponding to each attitude and each translation conformation corresponding to the attitude, determining a first docking index corresponding to each translation conformation, the translation conformation being used for representing a translation operation corresponding to the first protein or the second protein; based on the first docking index corresponding to each translation conformation, determining a target docking translation conformation; and performing docking processing on the first protein and the second protein based on the target docking translation conformation to obtain a protein docking result. According to the invention, the accuracy of protein docking can be improved.

The embodiment of the invention discloses a health data prediction method, device and equipment based on protein expression data and a storage medium, and the method comprises the steps: in response to a health prediction trigger instruction input by a user, extracting initial data for health prediction from the health prediction trigger instruction by using a large language model; obtaining protein expression data corresponding to at least one key protein based on the initial data; inputting the protein expression data into the trained MLP neural network model to obtain a prediction result of health prediction; and based on the prediction result, generating and displaying a prediction analysis report. The matching probability between the protein expression data and the health data can be accurately analyzed through the self-learning ability of the MLP neural network model, and the corresponding prediction analysis report is given for the prediction result, so that reliable data support is provided for accurate health diagnosis of doctors, data display can be provided for individual users, and the user experience is improved. And support is provided for early intervention and health prevention of the user.

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.