100 results about "Protein structure prediction" patented technology

A protein structure prediction method based on a cryoelectron microscope and a diffusion model comprises the following steps: extracting feature points from an electron density map of the cryoelectron microscope, converting the feature points into point cloud structures, and predicting corresponding amino acid types through a DAQ model according to the point cloud structures; one-dimensional and two-dimensional tensor features are obtained for an input amino acid sequence through an AlphaFold2 neural network and are used for training and constructing an obtained denoising neural network based on conditional diffusion, so that the denoising neural network supports input of point cloud structure information of a cryoelectron microscope and fusion of electron microscope information and sequence information; and the trained denoising neural network is matched with a sampling process based on conditional diffusion to realize protein skeleton structure prediction. According to the method, a more accurate prediction structure is given according to the information of the cryoelectron microscope, meanwhile, a change conformation space is reflected through the diffusion model, the prediction structure precision can be improved on the basis of a low-quality prediction structure prediction sample, meanwhile, the overall structure prediction precision based on the electron density map of the cryoelectron microscope is improved, and the change of the prediction structure conformation is reflected.

The invention relates to a diacylglycerol acyltransferase mutant and application thereof in synthesis of triacylglycerol from saccharomyces cerevisiae, and belongs to the technical field of enzyme engineering. Diacylglycerol acyltransferase is a rate-limiting step of a synthetic route of saccharomyces cerevisiae triacylglycerol (TAG), and at present, a research on a DGA1 mutant for efficiently synthesizing TAG is lacked, and a research on the aspect of a DGA1 catalytic mechanism is also lacked. The DGA1 mutant capable of effectively improving TAG synthesis is obtained by screening in combination with a directed evolution technology, and a result shows that 282-site mutation of diacylglycerol acyltransferase can significantly increase the accumulation amount of TAG. Meanwhile, the catalytic mechanism of the DGA1 is preliminarily explored by combining protein structure prediction, molecular docking and molecular dynamics simulation, and a foundation is laid for deeply analyzing the catalytic mechanism of the DGA1. The recombinant saccharomyces cerevisiae is also constructed based on the mutant, so that the TAG synthesis is improved, and meanwhile, the relative proportion of C18: 1 in total fatty acids is remarkably increased.

Disclosed herein are methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for antibody structure prediction. In one example method, a target antibody sequence for a target antibody comprising an amino acid sequence is received. The target antibody sequence is processed by an antibody language model (ALM) to obtain residue coding and attention weight coding without multiple sequence alignment (MSA), where the ALM is a protein language model trained according to the antibody sequence, and the ALM comprises a plurality of self-attention layers. The residue coding and attention weight coding are converted into a single representation and paired representations and input into a structure prediction model. And determining a prediction structure of the target antibody by using the structure prediction model.

The invention discloses a quantum computing method for protein structure prediction. The method comprises the following steps: acquiring a protein amino acid sequence; performing coordinate generation and polar coordinate conversion on each residue, and calculating an interaction strength parameter to complete sequence pretreatment; constructing a continuous coordinate quantization encoder quantum circuit and realizing quantization encoding of protein continuous space coordinates; constructing an interaction strength quantization encoder quantum circuit and realizing quantization encoding of interaction strength between residues; iteratively updating the obtained data information to realize optimization of all residue coordinate information; and performing standardization processing according to the obtained data information to obtain a prediction result of the protein structure. The invention also discloses a system for realizing the quantum computing method for predicting the protein structure. According to the method, through quantization coding of continuous space coordinates of the protein, quantization coding of interaction strength between residues and the iterative updating process, prediction of the protein structure is achieved, reliability is higher, accuracy is better, and occupied computing resources are fewer.

The invention belongs to the technical field of protein structure prediction, and relates to a protein structure prediction method, system and device based on a light quantum computer, and the method comprises the steps: 1) obtaining a multi-sequence alignment MSA matrix of a target sequence based on the target sequence alignment of a to-be-predicted protein; 2) encoding the obtained multi-sequence alignment MSA matrix into a {0, 1} matrix; 3) converting the amino acid interaction of the protein into an undirected graph model of {0, 1} state nodes, and training by adopting a Boltzmann machine training mechanism and using a light quantum computer to obtain a weight coefficient of a connecting edge between the nodes in the undirected graph model; and 4) obtaining an interaction coefficient between different amino acids of the protein based on the weight coefficient. According to the method, the calculation efficiency and the solving result of protein structure prediction are improved, and the problems that complex scheduling problems are difficult to calculate and accurate solutions cannot be obtained in the prior art are solved.

The invention discloses a functional protein mining and screening method and device, which combines multi-dimensional bioinformatics analysis such as protein structure prediction, protein function annotation, protein cluster mining and the like with an artificial intelligence method based on a protein big language to construct a process for mining and screening a functional protein. Protein structure analysis is introduced, and proteins with similar functions are explored by utilizing association of protein structures and functions and constructing a structure similarity map. The protein large language model can contain characteristic parameters related to protein functions, such as a protein structure, post-translational modification and biophysical characteristics, and reveals the inherent functional relevance of the protein in a vector matrix form. By introducing the two analysis means and combining with the traditional sequence-based protein function annotation method, the sequence similarity and affinity are lower, but proteins with corresponding functions are excavated and screened out, so that biomacromolecules can be utilized more efficiently and accurately.

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 provides a protein side chain conformation prediction method and system and electronic equipment, and relates to the technical field of bioengineering.The method comprises the steps that feature information of each original amino acid is extracted based on a target position and a protein structure file; the feature information comprises self features of the original amino acids and associated features between the original amino acids; masking the characteristics of the amino acid needing to be designed; updating all the feature information through a protein structure prediction model; based on the updating result, predicting the category of amino acid needing to be designed, and obtaining a structure prediction result of the target protein; by combining the characteristics of adjacent amino acids, the accuracy of protein structure prediction is improved.

The invention discloses a protein structure prediction method based on a mutual attraction relation between residue side chain low-entropy hydration layers, and belongs to the technical field of structural biology. The problem that an existing prediction method of the protein folding structure is poor in prediction effect is solved. According to the protein structure prediction method based on the mutual attraction relation between the residue side chain low-entropy hydration layers, protein structure prediction is achieved through water entropy force; the prediction is to predict a secondary structure and a tertiary structure of the protein based on the primary structure of the protein; the water entropy force is an interaction attraction force between amino residue side chain low-entropy hydration layers; the interaction attraction force means that entropy increase of low-entropy water molecules of the low-entropy hydration layer drives lateral attachment between amino acid residue side chains; the lateral attachment means that the two residue side chains are in a nearly parallel state. The method is used for protein structure prediction.

The invention belongs to the field of bioinformatics, relates to an enzyme function prediction method based on structure perception and semantic features, and integrates technologies such as a protein large language model, a protein structure prediction model, a graph convolutional neural network and a cross-modal attention mechanism. The method comprises the following five steps of initial multi-view feature extraction, key structure perception, key semantic information extraction, multi-view information fusion and function classification. The method comprises the following steps: firstly, inputting an amino acid sequence of enzyme into ESM2 and ProtT5 protein large language models and an ESMFold protein structure prediction model for preprocessing so as to extract Esm semantic information, Prt semantic information and structure information; then, inputting the Esm semantic information and the structure information into a key structure sensing module provided by the method so as to obtain key structure features; a large number of experimental results show that the method can efficiently and accurately predict the enzyme function, and the performance of an existing method is remarkably improved.

The present invention proposes a method and system for predicting the binding of polypeptides to TCRs based on deep learning. The method comprises: digitizing the sequences of polypeptides and TCRs according to a digital dictionary of amino acids to extract the correlation features of the polypeptides and TCR sequences; obtaining the three-dimensional structure of the polypeptide and TCR sequences according to the HelixFoldSingle protein structure prediction model, and extracting the three-dimensional structural features of the polypeptide and TCR sequences; linearly weighting the correlation features of the polypeptide and TCR sequences and the three-dimensional structural features of the polypeptide and TCR sequences to obtain a prediction result of the binding of polypeptides to TCRs. The scheme proposed by the present invention takes into account the correlation features of the interaction between polypeptides and TCRs and also takes into account the spatial structural features of the sequences. By combining the correlation features between sequences and the sequence structural features through a multimodal deep learning model, the accuracy of predicting the binding of polypeptides to TCR sequences is further improved.

The invention provides a polypeptide and TCR combination prediction method and system based on deep learning. The method comprises the following steps: performing digital processing on sequences of polypeptide and TCR according to a digital dictionary of amino acid, and extracting correlation characteristics of the sequences of the polypeptide and the TCR; obtaining a three-dimensional structure of the polypeptide and the TCR sequence according to a HelixFoldSingle protein structure prediction model, and extracting three-dimensional structure characteristics of the polypeptide and the TCR sequence; and performing linear weighting on the correlation characteristics of the polypeptide and the TCR sequence and the three-dimensional structure characteristics of the polypeptide and the TCR sequence to obtain a prediction result of combination of the polypeptide and the TCR. According to the scheme provided by the invention, correlation characteristics of interaction between the polypeptide and the TCR are considered, and spatial structure characteristics of the sequence are also considered. The correlation characteristics and sequence structure characteristics between the sequences are combined through a multi-modal deep learning model, so that the accuracy of predicting the combination of the polypeptide and the TCR sequence is further improved.

The invention discloses application of novel reverse transcriptase and related fusion protein of the novel reverse transcriptase in plant-guided editing. Candidate RT protein is obtained through systematic mining from a public database, novel reverse transcriptase cl1 with activity is screened out in combination with a fluorescence report system, and a guided editing system suitable for plants is constructed. The system tests in wheat protoplast, and verifies the editing activity of cl1 to a plurality of endogenous targets. Further combining with protein structure prediction and rational design point mutation optimization, the cl1 mutant with higher editing efficiency is obtained, and the method can be applied to accurate and effective editing of plant genomes and plant breeding and improvement.

The invention discloses an IV-type secretory effect protein recognition method and system based on multi-modal information, and belongs to the technical field of bioinformatics and secretory protein recognition. The method comprises the following steps: firstly, extracting amino acid residue characteristics of protein by using a protein language model, and constructing a spatial adjacency graph of the protein by using a three-dimensional structure predicted by a protein structure prediction model; respectively extracting sequence features and structural features of the protein through a deep sequence module and a hierarchical graph module; meanwhile, a contrast learning module is introduced to realize cross-modal alignment of the same protein in a potential space; and performing bidirectional interaction on the sequence features and the structural features by using a cross attention module to obtain joint features, and finally outputting a classification result after nonlinear transformation by a gating linear unit for predicting the IV-type secretion effect protein. According to the invention, efficient coordination of sequence and structure bimodal information is realized, and the identification accuracy of the IV-type secretory effect protein is remarkably improved.

The invention relates to the technical field of bioinformatics, in particular to a transaminase screening method and device, electronic equipment and a storage medium. According to the transaminase screening method and device, the electronic equipment and the storage medium provided by the embodiment of the invention, firstly, interaction of enzyme and a substrate is learned based on a protein-substrate binding activity prediction model; the binding activity of transaminase and a substrate is rapidly predicted, and first screening is achieved; then, on the basis of a protein structure prediction model, constructing a three-dimensional structure of a compound formed by combining the transaminase subjected to the first screening and a substrate, and realizing second screening; and finally, carrying out molecular dynamics simulation on the compound subjected to the second screening. By means of the mode, deep learning and physical modeling are combined, the accuracy of transaminase-substrate interaction prediction is improved, and the transaminase screening efficiency can be improved.

The application discloses a kind of heterodimer interchain residue contact prediction method.The present application is aimed at the deficiency of existing method in prediction accuracy, long-range dependence modeling capability and generalization, and proposes a kind of deep neural network integrating multiple features and attention mechanism.Specifically, the application integrates multiple features such as protein language model as network model input, then the network adopts efficient channel attention (ECA) and spatial attention (SA) module and KAN convolution network module, effectively captures the local and global dependence features of heterodimer, so as to predict the interchain residue contact of heterodimer.Experiments show that the prediction accuracy of the application on the benchmark dataset is significantly better than that of existing methods, and the model has high robustness.The application can be widely used in the field of protein heterodimer interchain residue contact prediction and protein structure prediction, further promoting protein function research and protein drug development.

The invention provides a training method of a protein multi-conformation model and a prediction method of a protein three-dimensional structure. The training method comprises the following steps: acquiring a plurality of initial protein structure prediction models and a plurality of single conformation samples; training each initial protein structure prediction model based on the plurality of single conformation samples to obtain a plurality of teacher protein structure prediction models corresponding to the plurality of initial protein structure prediction models; obtaining a to-be-treated amino acid sequence; respectively predicting the three-dimensional structure of the amino acid sequence to be processed based on the plurality of teacher protein structure prediction models to obtain a plurality of protein three-dimensional structures respectively corresponding to the plurality of teacher protein structure prediction models; forming a multi-conformation sample by the amino acid sequence to be treated and each protein three-dimensional structure in the plurality of protein three-dimensional structures; and training a to-be-trained protein multi-conformation model based on the multi-conformation sample. Therefore, a multi-conformation sample can be generated, and the multi-conformation prediction capability of the model is improved.

The invention provides a signal peptide category and cleavage site prediction method and system based on multi-modal characteristics, and belongs to the technical field of biological information analysis. The method comprises the following steps: acquiring an amino acid sequence of a signal peptide sample, and acquiring three-dimensional structure data of the signal peptide by utilizing a protein structure prediction model; obtaining sequence modal input data of the amino acid sequence of the signal peptide, and constructing a structural diagram to obtain structural modal input data; inputting the sequence modal input data into a sequence encoder and a protein language model, and extracting sequence features; inputting the structural modal input data into a structural encoder, and extracting structural features through graph convolution operation; carrying out fusion processing on the sequence features and the structural features to obtain multi-modal feature representation; and outputting a category prediction result and a cleavage site prediction result of the signal peptide through a prediction module. According to the invention, through fusion of the sequence and the structure information, the accuracy of signal peptide prediction and the recognition capability of minority class samples are improved.

The invention discloses a novel protein structure prediction method based on AI, and particularly relates to the technical field of protein structure research, a protein amino acid sequence is converted into a multi-dimensional feature matrix, homologous fragment information is fused, and feature representation with physical and chemical properties and potential folding rules is obtained; extracting local residue relation and global sequence dependency information by combining graph convolution and a self-attention mechanism, constructing a multi-scale subsurface space, and realizing comprehensive description of a folding trend; candidate conformation generation and uncertainty indexes are introduced into the submerged space, and it is ensured that the prediction process has reliable quantization; ranking and screening the priorities of the candidate conformations in combination with an energy constraint function and structural similarity measurement, and outputting an optimized structure set with reasonable energy and coordinated trend; a prediction structure is generated through multi-modal information fusion, and credibility evaluation is performed, so that the problem that prediction accuracy and interpretability are difficult to consider at the same time in an existing method is effectively solved.

A method is proposed for protein structure prediction. In the method, for a diffusion process, an initial structure of a target protein is obtained based on composition information concerning amino acids of the target protein. The diffusion process on the initial structure is performed based on a force field prediction for the target protein and the composition information. A target structure of the target protein is determined based on a result of the diffusion process.

The application relates to the technical field of breast cancer analysis and prediction, and particularly relates to a breast cancer gene drug screening method and system based on deep learning. The screening method obtains breast cancer gene mutation information, performs matching retrieval in a MySQL database, and judges whether the breast cancer gene mutation information is existing information. If not, sequence retrieval and consistency verification are performed to obtain mutant sequence information. Based on a deep learning model, the mutant sequence information is subjected to protein structure prediction to obtain three-dimensional spatial conformation data of mutant amino acids. Based on a drug small molecule, the three-dimensional spatial conformation data is subjected to multi-dimensional functional quantitative evaluation to obtain functional influence coefficient analysis data. The drug small molecules are classified, and based on the functional influence coefficient analysis data, the classified drugs and the breast cancer gene mutation are subjected to matching degree calculation to obtain a drug recommendation index. The screening method can improve the accuracy of breast cancer gene mutation drug screening.

The present invention belongs to the field of protein structure prediction technology and relates to a protein structure prediction method, system, and device based on an optical quantum computer. The method comprises: 1) obtaining a multiple sequence alignment (MSA) matrix of the target sequence based on the target sequence alignment of the protein to be predicted; 2) encoding the obtained MSA matrix into a {0,1} matrix; 3) converting the protein's amino acid interactions into an undirected graph model with {0,1} state nodes and training the model using an optical quantum computer using a Boltzmann machine training mechanism to obtain weight coefficients for the edges connecting the nodes in the undirected graph model; and 4) obtaining interaction coefficients between different amino acids in the protein based on the weight coefficients. This method improves the computational efficiency and solution results of protein structure prediction, and solves the problem that the existing technology is difficult to calculate and cannot obtain accurate solutions for complex scheduling problems.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction and protein domain segmentation. In one aspect, a method comprises generating a plurality of predicted structures of a protein, wherein generating a predicted structure of the protein comprises: updating initial values of a plurality of structure parameters of the protein, comprising, at each of a plurality of update iterations: determining a gradient of a quality score for the current values of the structure parameters with respect to the current values of the structure parameters; and updating the current values of the structure parameters using the gradient.

The invention relates to the technical field of breast cancer analysis and prediction, in particular to a breast cancer gene drug screening method and system based on deep learning. According to the screening method, breast cancer gene mutation information is obtained, matching retrieval is conducted in a MySQL database, and whether the breast cancer gene mutation information is existing information or not is judged; if not, sequence retrieval and consistency verification are carried out, and mutant sequence information is obtained; performing protein structure prediction on the mutant sequence information based on a deep learning model to obtain three-dimensional space conformation data of mutant amino acids, and performing multi-dimensional function quantitative evaluation on the three-dimensional space conformation data based on drug small molecules to obtain function influence coefficient analysis data; and grading the drug small molecules, and carrying out matching degree calculation on the graded drug and the breast cancer gene mutation according to the function influence coefficient analysis data to obtain a drug recommendation index. The screening method can improve the accuracy of breast cancer gene mutation drug screening.

The present invention discloses a quantum computing method for predicting protein structure, comprising obtaining a protein amino acid sequence; performing coordinate generation and polar coordinate conversion on each residue and calculating interaction strength parameters to complete sequence pre-processing; constructing a continuous coordinate quantization encoder quantum circuit and realizing quantization encoding of protein continuous spatial coordinates; constructing an interaction strength quantization encoder quantum circuit and realizing quantization encoding of interaction strength between residues; iteratively updating the obtained data information to optimize the coordinate information of all residues; and performing standardization processing on the obtained data information to obtain a prediction result of the protein structure. The present invention also discloses a system for realizing the quantum computing method for predicting protein structure. The present invention not only realizes the prediction of protein structure through the quantization encoding of protein continuous spatial coordinates, the quantization encoding of interaction strength between residues and the iterative update process, but also has higher reliability, better accuracy and less computing resources occupied.

The application discloses RNase R mutants with improved reaction temperature and thermal stability, and a preparation method and application thereof, and relates to the technical field of biology.The application obtains three RNase R mutants with amino acid sequences shown in SEQ ID NO:3, SEQ ID NO:5 and SEQ ID NO:7 by using protein structure prediction related software to design, transform and screen RNase R.The reaction temperature and thermal stability of the RNase R mutants are improved compared with wild-type RNase R, and the RNase R mutants have obvious advantages in applications such as circular RNA enrichment, and the application range of RNase R in the field of RNA research is expanded.

This application discloses a method, system, device, and medium for minimizing protein conformational energy. The method includes: determining the loop region and main chain region of the protein; obtaining the potential energy function of the loop region based on hydrogen bond energy and main chain dihedral angle deviation, and obtaining the potential energy function of the main chain region based on the main chain dihedral angle; obtaining a dual potential energy function based on the loop region potential energy function and the main chain region potential energy function; and optimizing the protein conformation by dynamically adjusting the constraint force constant until the minimum value of the dual potential energy function is found. Using the embodiments of this application, the accuracy of protein structure prediction can be effectively improved, especially the accuracy of loop conformation. By employing a dual resonant potential energy constraint system, which considers the conformational characteristics of both the loop and non-loop regions, greater conformational flexibility can be given to the loop region while maintaining overall structural stability, providing an important structural basis for drug screening and structure-function studies.

The invention discloses an antibody-oriented double-branch structure feature prediction method, and relates to the technical field of protein expression learning and protein structure prediction, and the method comprises the following steps: 1, taking a given antibody amino acid sequence as an input, extracting three types of features including an MSA feature, a Pair feature and a template feature of an antibody, carrying out collaborative fusion on the three types of features; 2, constructing a double-branch structure feature prediction module, and optimizing an antibody structure; step 3, model training; and 4, testing the model to obtain an antibody structure. By adopting the antibody-oriented double-branch structure feature prediction method disclosed by the invention, efficient and accurate antibody structure feature prediction is realized, and powerful support is provided for related research and application of antibodies.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a predicted structure of a protein that is specified by an amino acid sequence. In one aspect, a method comprises: obtaining an initial embedding and initial values of structure parameters for each amino acid in the amino acid sequence, wherein the structure parameters for each amino acid comprise location parameters that specify a predicted three-dimensional spatial location of the amino acid in the structure of the protein; and processing a network input comprising the initial embedding and the initial values of the structure parameters for each amino acid in the amino acid sequence using a folding neural network to generate a network output comprising final values of the structure parameters for each amino acid in the amino acid sequence.

The invention relates to a method for introducing disulfide bonds in a protein design process, which comprises the following steps: firstly, designing main chain coordinates of all residues of a scaffold by using protein skeleton design software to enable the main chain coordinates to contain a given motif, and secondly, calculating candidate site pairs meeting disulfide bond forming conditions, then, redesigning all residues except the motif and the disulfide bond candidate sites by using protein sequence design software to obtain a protein sequence, carrying out structure prediction on the protein sequence by using protein structure prediction software to obtain a protein structure, and comparing the protein structure by using structure comparison software to obtain a protein structure; and screening out site pairs meeting conditions through calculation, and finishing the design if the site pairs meet the requirement on the number of disulfide bonds. Compared with the prior art, disulfide bonds are introduced in the design process of the protein motif scaffold, and the protein motif scaffold has diversity in the aspects of sequence length and residue distribution.