87 results about "Protein ligand" patented technology

The embodiment of the invention discloses a protein-ligand interaction prediction method and a related device. Determining a prediction interaction pair formed by atoms of the protein and atoms of the ligand molecule according to the data of the protein and the data of the ligand molecule, establishing a loss function according to the node characteristics and the edge characteristics of the real interaction pair and the node characteristics and the edge characteristics of the prediction interaction pair, and adjusting model parameters according to the loss function, the target neural network model can be used for predicting the interaction between any protein and ligand molecules. Physical priori knowledge of protein-ligand interaction is fused in model training and prediction, so that the model can learn characteristics with more biological significance, and the predicted biological correlation is improved. According to the method, the advantages of deep learning are utilized, high-dimensional features are automatically extracted, complex pattern recognition is carried out, the complex relation in protein-ligand interaction is captured, and the stability and accuracy of protein-ligand interaction prediction are improved.

The invention discloses a protein-ligand binding affinity prediction method and system based on structure perception, and belongs to the field of bioinformatics and drug research and development. In order to solve the problem of low accuracy of affinity prediction caused by neglect of structural modal information of a protein-ligand compound in the existing affinity prediction, the invention provides the affinity prediction method. The method comprises the following steps: performing integer coding on a protein sequence and a ligand SMILES character string to obtain a sequence predicted value; expressing the protein binding pocket-ligand compound as an isomeric graph, and encoding the protein-ligand compound isomeric graph to obtain predicted values corresponding to node features and edge features; on the basis of the isomerism graph, homographs are generated through two element paths of'protein atoms-ligand atoms-protein atoms' and'ligand atoms-protein atoms-ligand atoms', encoding is carried out according to the homographs of the element paths, fusion features corresponding to the two element paths are obtained, and then corresponding predicted values are obtained; and obtaining a final predicted value based on all predicted values.

The invention belongs to the technical field of biological medicines, and relates to a protein degradation system based on polyamide-amine dendrimers as well as a preparation method and application of the protein degradation system. The protein degradation system is of a nano-particle structure, and the nano-particle structure comprises silicon dioxide nano-particles and a polyamide-amine type dendritic polymer layer coating the surfaces of the silicon dioxide nano-particles. An MDM2 protein ligand, a GLUT1 protein ligand and an E3 ubiquitin enzyme ligand are connected to the polyamide-amine dendritic polymer layer through chemical bonds. The protein degradation system provided by the invention can be used for synergistically degrading the MDM2 protein and the GLUT1 protein. The synergistic degradation strategy not only can effectively inhibit proliferation and energy metabolism of tumor cells, but also can significantly enhance the stability of the p53 protein. By recovering the normal function of the p53 protein, the growth of tumor cells is further inhibited, and a new strategy is provided for tumor treatment.

The invention belongs to the field of medicines, and discloses an SERPINE1 protein degradation agent and application thereof. The general formula of the SERPINE1 protein degradation agent is # imgabs0 # or # imgabs1 #. The research finds that a structural fragment for inhibiting SERPINE1 protein and a structural sheet or a hydrophobic label of an E3 protein ligand are coupled together through a linker, the length of the linker is adjusted, the obtained SERPINE1 protein degradation agent has an unexpected anti-tumor effect, the anti-tumor effect of the SERPINE1 protein degradation agent is superior to that of a single SERPINE1 inhibitor, and the SERPINE1 protein degradation agent has a good application prospect. The drug resistance of tumor cells can be overcome, and the drug-forming target property is good.

To provide a compound comprising a cyclic peptide and a chelator, and its use.SOLUTION: The present invention provides a compound selected from the group consisting of compound Hex-[Cys(tMeBn(DOTA-AET))-Pro-Pro-Thr-Gln-Phe-Cys]-OH (3BP-3554) and compound Hex-[Cys(tMeBn(DOTA-PP))-Pro-Pro-Thr-Gln-Phe-Cys]-Asp-NH2 (3BP-3407).SELECTED DRAWING: None

The present invention discloses a method, device, terminal and storage medium for generating molecular motion trajectories, and relates to drug discovery technology. The method comprises: using a pre-trained generative model, generating the atomic coordinate information of several subsequent frames frame by frame for the atomic category sequence of the target protein-ligand complex and the atomic coordinate information of the first frame; the pre-trained generative model is trained based on the escape trajectory of an existing protein-ligand complex; and generating the molecular motion trajectory of the target protein-ligand complex according to the atomic category sequence of the target protein-ligand complex and the atomic coordinate information of all frames. The present invention simulates the molecular motion trajectory by adopting a paradigm of generating coordinates frame by frame by a generative model, and learns the inter-frame coordinate evolution law of the ligand in the process of escaping the protein pocket through the existing escape trajectory. In the inference stage, it is only necessary to input the atomic category sequence and the atomic coordinate information of the initial state of the first frame, and the atomic coordinate information of the subsequent frames can be iteratively generated quickly and accurately.

The application provides a target-specific virtual screening method and system based on machine learning. Active molecules and inactive molecules are docked with multiple conformations of a target, and protein-ligand interaction features of the docked molecules and related features of the ligands are extracted as input features of a machine learning model. A scoring function model is constructed using multiple machine learning models, and based on the advantages of multiple target-specific scoring function models, an integrated target-specific scoring function model is finally obtained by combining a model integration method. The integrated model can more effectively process complex protein-ligand interaction data, has excellent prediction performance and virtual screening capability, provides more reliable prediction results, and improves the virtual screening capability.

The present invention discloses a method and system for de novo protein reverse design based on spectrum structure-activity relationship. The method comprises: obtaining a data set including protein structural feature data, protein simulated spectral data, and protein-ligand interaction data; establishing a multi-task neural network model, training it using the data set, inputting the protein simulated spectral data into the trained multi-task neural network model, and simultaneously obtaining a distance matrix between protein backbone atoms and the number of protein amino acids; integrating the distance matrix between protein backbone atoms and the number of protein amino acids to obtain a final protein distance matrix; obtaining an initial protein PDB structure based on the final protein distance matrix; optimizing the initial protein PDB structure using the SCUBA-D protein structure optimization model to obtain an all-atom protein structure; and applying ProteinMPNN, using the all-atom protein structure as input, to obtain multiple amino acid sequences. The present invention can accelerate the drug development cycle.

The present disclosure relates to bifunctional compounds, which find utility as modulators of estrogen receptor (target protein). In particular, the present disclosure is directed to bifunctional compounds, which contain on one end at least one of a Von Hippel-Lindau ligand, a cereblon ligand, Inhibitors of Apoptosis Proteins ligand, mouse double-minute homolog 2 ligand, or a combination thereof, which binds to the respective E3 ubiquitin ligase, and on the other end a moiety which binds the target protein, such that the target protein is placed in proximity to the ubiquitin ligase to effect degradation (and inhibition) of target protein. The present disclosure exhibits a broad range of pharmacological activities associated with degradation / inhibition of target protein. Diseases or disorders that result from aggregation or accumulation of the target protein are treated or prevented with compounds and compositions of the present disclosure.

The application discloses a kind of bivalent ligand molecules for targeting BCL6 protein degradation and application thereof, it is related to the technical field of drug development;The structure general formula of the bivalent ligand molecules for targeting BCL6 protein degradation is as follows: M1-L-M2;Wherein, M1 and M2 are independent structure same or different BCL6 protein ligand;L is any chain or cyclic hydrocarbon fragment capable of forming covalent bond with BCL6 ligand.The application also provides the application of the bivalent ligand molecules in the preparation of anti-tumor and / or immune disease drugs.The bivalent ligand molecules can exert good anti-tumor activity on a variety of BCL6-dependent tumors by selectively inducing BCL6 protein degradation, and are also related to the occurrence of a variety of immune diseases, and can be used in related tumor and immune disease drugs.

The present invention relates to protein ligands for carbonic anhydrase IX (CAIX) as a biomedically relevant target. In particular, highly specific ligands can interact exclusively with an antigen, i.e., CAIX, expressed on the surface of tumor cells, sparing healthy target-expressing organs, thereby enabling efficient in vivo drug delivery applications. Ligands can exhibit particularly low dissociation constants and / or enzyme isoform specificity, making them suitable for targeted delivery of payloads, such as therapeutic and / or diagnostic agents, to sites affected by or at risk of diseases or disorders characterized by CAIX expression.

The present invention relates to a method and an apparatus for discovering an active substance through information about the three-dimensional binding structure of a protein and a ligand. An embodiment of the present invention provides a method comprising: a step for determining selected compounds among compounds to be analyzed, the selected compounds being determined on the basis of bond energy atom property information, generated from the three-dimensional binding structure of a protein to be analyzed and a ligand, and atom accessibility atom property information, generated from the three-dimensional structures of the compounds to be analyzed; a step for identifying active substances by screening the selected compounds on the basis of the ratio of key interaction property information, generated through three-dimensional docking (3D docking) of the protein to be analyzed and a positive control, to interaction property information, generated through three-dimensional docking (3D docking) of the protein to be analyzed and the selected compounds; a step for generating conformers on the basis of compound poses generated by docking the active substances with ligand derivatives; and a step for inputting the conformers to a deep learning model to determine the optimal pose and binding affinity of the compound with respect to the protein to be analyzed, wherein the bond energy atom property information and the atom accessibility atom property information are one-dimensional data compressed from the three-dimensional binding structure and the three-dimensional structure, respectively.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a predicted property score of a protein and a ligand. In one aspect, a method comprises: obtaining a network input that characterizes a protein and a ligand; processing the network input characterizing the protein and the ligand using an embedding neural network to generate a protein-ligand embedding representing the protein and the ligand, wherein the embedding neural network has been jointly trained with a generative model that is configured to: receive an input protein-ligand embedding; and generate, while conditioned on the input protein-ligand embedding, a predicted joint three-dimensional (3D) structure of an input protein and an input ligand represented by the input protein-ligand embedding; and generating a property score that defines a predicted property of the protein and the ligand using the protein-ligand embedding.

The invention discloses a protein ligand binding affinity prediction method based on two-channel hierarchical interactive learning, and particularly relates to an affinity prediction method based on two-channel hierarchical interactive learning. The method comprises the following steps: S1, based on a protein-ligand compound space structure containing a three-dimensional structure and chemical data, constructing six chemical entity interaction diagram networks from an atomic scale to a substructure scale; s2, extracting covalent and non-covalent interaction information of protein-ligands from the internal and external channels at the same time by taking a dual-channel coding framework as a backbone; and S3, adopting a hierarchical interactive learning strategy. According to the affinity prediction method based on the two-channel hierarchical interactive learning, provided by the invention, understanding of protein-ligand complex interaction is enhanced through a technology of modeling richness and complexity of protein-ligand interaction information, so that the protein-ligand binding affinity is comprehensively and accurately predicted.

The present invention discloses a method for predicting drug-target affinity based on multi-shell and extended connectivity fingerprints, using protein-ligand complexes in the PDBbind database as a data set; modeling the binding pockets of macromolecular proteins and small molecule ligands, constructing N shells outward from the geometric center of the ligand, and mapping protein atoms to each shell according to the spatial coordinates of the protein atoms; classifying ligand atoms into multiple categories through features such as atomic symbols, explicit valences, etc.; taking all specific atom pairs as the features of this shell, and superimposing the features of multiple shells to obtain the feature vector of the complex; through 3D slicing of the complex features, using Transformer to learn the shell atom pair features. The present invention solves the problem that existing methods cannot characterize long-range interactions; through 3D slicing of the complex features, Transformer can well learn the shell atom pair features, thereby changing the performance of the characterization.

The invention discloses a molecular fragment library based on protein binding site properties and a construction method and application thereof, and belongs to the field of computer-aided drug design. The construction method comprises the following steps: acquiring three-dimensional structure data of a protein-ligand compound, and preprocessing to obtain standardized protein binding sites and ligand molecules; cutting the standardized ligand molecules by adopting an iterative molecular cutting algorithm to generate molecular fragments; identifying and quantifying an interaction between the molecular fragment and an amino acid residue in the normalized protein binding site; and associating the molecular fragments, the information of the amino acid residues interacting with the molecular fragments and the corresponding interaction modes, and constructing a molecular fragment library. The interaction mode of molecular fragments and specific amino acid residues is labeled, so that the targeting property of the fragment library is improved; and the candidate fragments with specific interaction potential can be quickly positioned, so that the drug design efficiency is improved.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a predicted joint 3D structure of a protein and one or more ligands. In one aspect, a method comprises: obtaining a network input that characterizes the protein and the one or more ligands; processing the network input using an embedding neural network to generate a protein-ligand embedding of the protein and the one or more ligands; and generating, using a generative model and while the generative model is conditioned on the protein-ligand embedding, the predicted joint three-dimensional (3D) structure of the protein and the one or more ligands.

Macrocyclic peptides (MPs) are a class of compounds that have been shown to be particularly well suited for engaging difficult protein targets. However, their utility is limited by their generally poor cell permeability and bioavailability. The present disclosure reports an efficient solid-phase synthesis of novel MPs by trapping a reversible intramolecular imine linkage with a 2-carbonyl pyridine to create an imidazopyridinium (IP+)-linked ring. This chemistry is useful for the creation of macrocycles of different sizes and geometries, including head-to-side and side-to-side chain configurations. Many of the IP+-linked MPs exhibit far better passive membrane permeability than expected for "beyond Rule of 5" molecules, in some cases exceeding that of much lower molecular weight, traditional drug molecules. This chemistry has been demonstrated to be suitable for the creation of libraries of IP+-linked MPs and show that these libraries can be mined for protein ligands.

Methods, systems, and apparatus for generating predicted joint 3D structures of proteins and one or more ligands, comprising computer programs encoded on a computer storage medium. In one aspect, a method includes: obtaining network input characterizing the protein and the one or more ligands; processing the network input using an embedded neural network to generate protein-ligand embeddings of the protein and the one or more ligands; and using a generative model and, when the generative model is conditioned on the protein-ligand embeddings, generating the predicted joint three-dimensional (3D) structure of the protein and the one or more ligands.

A PAMAM-based protein degradation system and a method of preparation and use thereof are provided. The protein degradation system comprises: a silica nanoparticle core; and a poly(amidoamine) dendrimer (PAMAM) layer coated on a surface of the silica nanoparticle, wherein the PAMAM layer is linked via amide bonds to three small-molecule ligands: MDM2 protein ligand Idasanutlin, GLUT1 protein ligand Lavendustin B and E3 ubiquitin ligase ligand Thalidomide-NH—CH2—COOH. The nanoparticle protein degradation system cooperatively degrades MDM2 protein and GLUT1 protein. This cooperative degradation strategy not only effectively suppresses proliferation and energy metabolism of tumor cells, but also significantly enhances the stability of p53 protein. By restoring the normal function of p53 protein, tumor cell growth is further inhibited, providing a new strategy for cancer therapy.

Sulfonyl-triazole compounds and related sulfonyl-heterocycle compounds are described. The compounds can be used to identify reactive nucleophilic amino acid residues, such as reactive tyrosines and reactive lysines, in proteins and to modify the activity of proteins with reactive nucleophilic amino acid residues via the formation of protein adducts comprising a fragment of the compounds. Methods are also described for screening the compounds to identify ligands of proteins comprising a reactive lysine or a reactive tyrosine.

This disclosure relates generally to a method and system for designing a baseline peptide bioreceptor. State-of-the-art methods provide peptide designing through specific target selection and through desired conformational stability. However, considering individual properties of amino acid while designing a peptide sequence have a greater role in imparting stability in designing the peptide sequence. The disclosed method provides a baseline peptide sequence by identifying active binding sites for a ligand using a computational docking technique. The active sites are selected based on binding affinity of protein-ligand complex. Further, selected binding sites are utilized in identifying energetically favorable interactions of protein-ligand complex through molecular dynamics simulation performed in a biofluid environment. Finally, multi-parameter optimization model with parameters such as sequence length, binding affinity etc. is executed to obtain the baseline peptide.

The application discloses a kind of protein-ligand complex three-dimensional structure determination method, device and terminal, the method includes: simultaneously processing protein data and ligand data, generate protein pocket data and ligand pose data;Matching protein pocket data and ligand pose data, obtain first three-dimensional structure;Voxelization first three-dimensional structure, obtain several grids, including corresponding position protein-ligand binding information in grid;The grid is input into trained neural network, and the grid is sorted;And according to the first grid of sorting, obtain optimal binding site and optimal ligand pose, and combine to obtain protein-ligand complex three-dimensional structure.Through simultaneously extracting and processing protein data and ligand data, then in the form of voxelization is formed including protein-ligand binding information grid, again through neural network for grid sorting, the three-dimensional structure of protein-ligand complex can be more quickly and accurately determined by the application.

The invention aims to provide a method and equipment for optimizing the structure of a ligand in a protein-ligand compound, a medium and a program product. The method comprises the following steps: determining an optimization space corresponding to an initial structure of the ligand in the protein-ligand compound; and determining an optimized structure corresponding to the ligand in the optimized space by using a differential evolution method and combining target scoring functions, the target scoring functions including an affinity scoring function, a ligand structure rationality scoring function and a protein-ligand atomic distance constraint scoring function. According to the method, the obtained optimized structure meets the affinity condition and also meets the distance constraint condition, the situation that the ligand collides with the protein and does not conform to the physical law does not occur, and the calculation efficiency of finding the ligand structure conforming to the condition is improved.

The invention provides a protein-ligand binding affinity prediction method based on a graph convolutional network. The method comprises the following steps: firstly, constructing a protein map based on a three-dimensional structure of a protein pocket, and carrying out feature coding on sequence residues by using ESM3; meanwhile, a molecular map containing geometric information is constructed for the ligand, and chemical characteristics are extracted in combination with molecular fingerprints. And then cross-graph interaction of the protein graph and the ligand graph is realized by adopting a multi-layer message passing graph neural network, and an attention mechanism is introduced to capture key interaction sites and spatial dependency relationships. And generating a unified representation vector of a compound level through pooling, and outputting binding affinity through a prediction network. According to the method, the multi-modal association of the structure and the sequence can be automatically learned, and the accuracy and efficiency of virtual screening and lead compound optimization are effectively improved.

The present invention is related to a compound comprising a cyclic peptide and a chelator, and its use.

The application discloses a kind of based on graph neural network's protein and ligand between the prediction method of pose of docking pose, first, obtain the biological information sample set of protein-ligand complex, sample set includes sample data and sample annotation data;Second, construct the pose generation model of docking pose based on graph neural network and the pose evaluation model of docking pose based on multi-view, further adjust the parameter of model, the sample data is handled by the structure generation model obtained by training, obtain the pose of protein ligand and actually output;Finally, the stability of output result is evaluated using mainstream pose docking structure evaluation index.This application directly uses the biological structure information of ligand protein to generate the optimal docking pose structure, and evaluates the generation result through multi-angle comprehensive evaluation model, so as to improve the accuracy of ligand-protein pose structure docking prediction, and improve the effectiveness of ligand-protein pose structure docking prediction result evaluation.

The invention belongs to the field of protein ligands, and relates to a protein-ligand affinity prediction method based on ensemble learning, which comprises the following steps: acquiring a PDB file of a protein, a PDB file of a receptor and an MOL2 file of a ligand; performing feature extraction on the PDB file of the protein to obtain a protein feature vector; extracting mutual feature vectors of the protein and the ligand from the PDB file and the MOL2 file; processing the MOL2 file of the ligand to obtain a ligand feature vector; splicing the protein feature vector, the mutual feature vector and the ligand feature vector, and inputting the spliced features into an affinity prediction model to obtain an affinity prediction result; according to the method, the protein three-dimensional structure is converted into the residue contact diagram, the model input quantity is remarkably reduced while structure information is reserved to the maximum extent, the model parameter quantity is effectively reduced, the requirement for the training environment is greatly reduced, and the model has higher practicability and generalizability.

The invention discloses a molecular motion trail generation method and device, a terminal and a storage medium, and relates to a drug discovery technology. The method comprises the following steps: generating atomic coordinate information of a plurality of subsequent frames frame by frame according to an atomic category sequence of a target protein-ligand compound and atomic coordinate information of a first frame through a pre-trained generation model; the pre-trained generation model is obtained by training based on the escape trajectory of the existing protein-ligand compound; and according to the atom category sequence of the target protein-ligand compound and the atom coordinate information of all frames, generating a molecular movement track of the target protein-ligand compound. According to the method, a normal form of generating coordinates frame by frame is adopted to simulate a molecular motion track, and an inter-frame coordinate evolution rule of a ligand in an escape protein pocket process is learned through an existing escape track. In the reasoning stage, the atomic coordinate information of the subsequent frames can be rapidly and accurately iteratively generated only by inputting the atomic category sequence and the atomic coordinate information of the initial state of the first frame.

This disclosure relates to protein degraders developed based on BCL-2 family protein ligand compounds, including compounds of formula (I) or salts thereof, enantiomers, stereoisomers, solvates, prodrugs or polymorphs, and their use in treating diseases.