232 results about "Drug discovery" patented technology

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

A federated distributed computational system enables secure drug discovery and resistance tracking through hybrid simulation capabilities. The system implements a hybrid simulation orchestrator that coordinates molecular dynamics simulations with machine learning models for drug discovery analysis, while maintaining secure cross-institutional data exchange. The architecture coordinates multi-scale spatiotemporal synchronization across computational nodes, with each node containing local processing capabilities for molecular dynamics simulation and resistance pattern detection. Through a distributed graph architecture, the system enables real-world clinical data integration, resistance evolution tracking, and multi-scale tensor-based analysis with adaptive dimensionality control. The system implements real-time drug response prediction through multi-modal data analysis, enabling pharmaceutical companies and research institutions to collaborate on complex drug discovery projects while maintaining strict data privacy controls.

The invention relates to the field of artificial intelligence assisted drug discovery, in particular to a protein large language model-based molecule generation and optimization method, which comprises the following steps of: acquiring amino acid sequence information and three-dimensional structure information of a target protein pocket; encoding the amino acid sequence of the protein pocket by using a protein encoder constructed based on a protein large language model to obtain a protein pocket feature vector; using a context encoder module to encode the context information according to a preset molecule generation mode (de novo generation or optimization based on a seed compound) to obtain a latent vector; and fusing the protein pocket feature vector with the latent vector. According to the method, accurate representation of the protein pocket is realized by utilizing the protein large language model, and a generation-screening-optimization iterative drug design strategy is developed by supporting a unified framework of two generation modes, so that the targeting specificity of generated molecules and the overall efficiency of drug design are improved.

The invention relates to the technical field of drug research and development, in particular to a target AKT1 drug molecule discovery and delivery integrated system and method based on deep learning. Aiming at the problems of molecular design, optimization and delivery link separation and low research and development efficiency of drugs in the prior art, the system constructs a multi-module collaborative framework, and comprises a target analysis module for analyzing a target structure and formulating a generation strategy; the molecule generation and optimization module is used for generating and optimizing candidate molecules in combination with the generation model and reinforcement learning; the delivery scheme design module is used for matching a delivery carrier based on molecular physicochemical properties; and a verification module that predicts and evaluates the molecule-deliverer combination using molecular docking and ADMET. An evaluation result of the verification module is fed back to the molecule generation and optimization module to form a closed-loop optimization mechanism, so that an automatic process from target analysis to output of candidate drug molecules and matched delivery schemes thereof is realized. Compared with the prior art, the efficiency and success rate of early drug discovery can be improved.

The invention discloses a lung squamous cell carcinoma drug discovery method and system based on disturbance response scanning analysis, and belongs to the field of biological medicines.The method comprises the steps that lung squamous cell carcinoma protein expression profile data is downloaded and preprocessed, a robust network module is constructed and multi-scale analysis and evaluation are conducted, and drug genomic data are obtained based on drug genomic data. Predicting the drug sensitivity of the patient by using machine learning, and generating a DRN through difference analysis of the drug sensitivity; predicting drug-target protein binding affinity in combination with deep learning, quantifying node sensitivity through a PRS technology, calculating a DPI disturbance score and ranking drug priorities; high-ranking drugs are screened through comprehensive sensitivity analysis and literature investigation; a drug for a lung squamous carcinoma cell line is screened out through a pre-experiment and is relocated. According to the framework developed by the invention, by integrating proteomics, pharmacogenomics and dynamic network analysis, systematic analysis is provided for relocation drug identification of lung squamous cell carcinoma, and good news is brought to treatment of lung squamous cell carcinoma.

A molecular structure prediction method based on a multi-granularity graph neural network comprises the steps of data set preprocessing, multi-granularity level data feature construction, multi-granularity graph neural network construction, multi-granularity graph neural network training, multi-granularity graph neural network verification and multi-granularity graph neural network testing. The key connection relation between atoms, the incidence relation of substructure keys and graph-level global feature representation are determined in the molecular graph, and the problem of local information loss in graph representation learning is effectively relieved; a message passing mechanism of graph neural sub-networks with different granularities is improved, a multi-granularity molecular graph data structure is trained, unique information of each hierarchical molecular structure is fully utilized, and the modeling capability of a model for a complex chemical structure is enhanced. The method has the advantages of being high in prediction accuracy, reducing errors, relieving local information loss existing in the prediction method, being good in prediction interpretability and the like, and can be applied to the technical fields of drug discovery, molecular property prediction and the like.

The invention discloses a lead compound optimization method and system based on skeleton constraint and training enhancement, and belongs to the field of artificial intelligence drug discovery. The method comprises the following steps: performing structural treatment on an initial lead compound, extracting a growth skeleton structure, and pairing a protein pocket structure; inputting information of the skeleton structure and the protein pocket structure into a coding model based on a three-dimensional graph neural network for joint coding to obtain structure coding representation; on the basis of a Delete model, an atomic distance-based resampling mechanism and a hydrophobic group mask are introduced, and a molecular generation model is constructed; training and tuning a molecule generation model through staged pre-training and a knowledge enhancement fine tuning strategy so as to improve the structural accuracy, the binding activity and the druggability of generated molecules; and inputting the structure coding expression into a trained and optimized molecular generation model PocketGrow to generate optimized molecules, screening the generated optimized molecules, and outputting a lead compound with development potential.

The invention relates to the technical field of biology, in particular to a composition for preparing a brain organ, the brain organ and application of the brain organ. The invention further discloses a construction method of the brain organ, and on the basis of the method, different stem cells such as ESCs and iPSCs can be utilized to stably construct the three-dimensional brain organ model capable of simulating the medulla oblongata trigeminal nerve. The invention further discloses an organoid assembly which has important application potential in the fields of research on development, functions and related diseases of brain nuclei, drug discovery and the like.

The invention relates to the field of drug discovery and delivery collaboration, in particular to an autonomous evolutionary drug discovery and delivery collaboration method and system based on a large language model. The method comprises the following steps: aiming at a given biological target three-dimensional structure, generating a candidate molecular library which is complementary with a target pocket and gives consideration to druggability through an SE (3) isovariant hybrid generation model; according to a two-stage funnel type high-throughput virtual screening process, screening out the molecule with the highest comprehensive potential from the candidate molecule library; generating a customized delivery scheme through a three-stage process; in a digital twinborn model for simulating a real in-vivo tumor microenvironment, a targeted delivery process of a drug and carrier complex is simulated, and efficiency is evaluated; atomic-scale performance confirmation is carried out on a medicine, carrier and target point ternary system through molecular dynamics simulation. The invention is suitable for drug research and development.

The invention relates to the technical field of medical artificial intelligence, in particular to a drug discovery task processing method, device and equipment based on large model reasoning, and the method comprises the steps: obtaining a drug discovery task instruction of a user; the drug discovery task instruction is input to the target large model, the target large model outputs an execution result of a drug discovery task, and the reasoning process of the target large model comprises the steps that the drug discovery task instruction is analyzed to obtain an instruction intention and instruction parameters, a target key matched with the instruction intention is selected from a parameterized memory pool based on the instruction intention, and the target key is input to the target large model; the instruction parameter is mapped into a target key value, a target calling tool format is generated based on the target key and the target key value, and a corresponding target discovery tool is called based on the target calling tool format to execute a drug discovery task; and sending an execution result of the drug discovery task to the user. According to the method, the target large model automatically executes the reasoning process, various tools are automatically called, and intelligent drug discovery is achieved.

The present disclosure relates to organoids and particularly to brain organoid models. The brain organoids include neurons, microglia, astrocytes, and blood vessels. The brain organoid models can be used to create models for Alzheimer's Disease. Methods of using the brain organoids for drug discovery are also described.

Embodiments of this disclosure provide a method and apparatus for drug design, a device, a medium, and a program product. The method for drug design includes: obtaining protein data representing a three-dimensional structure of a protein and initial molecule data representing an initial molecule to be bound to the three-dimensional structure of the protein. The method further includes: determining first molecular fragment data representing a first molecular fragment in the initial molecule based on the protein data and the initial molecule data. Generating target molecule data representing a target molecule based on the first molecular fragment data and the initial molecule data. A molecular fragment is automatically determined in the initial molecule, and the initial molecule is optimized based on the determined molecular fragment, such that fragment-based artificial intelligence optimization of a drug molecule can be implemented in a targeted manner, thereby reducing time and labor costs of drug discovery.

The application provides a drug virtual screening method and device based on deep learning, wherein the method comprises the following steps: inputting all candidate compound small molecules in a candidate molecule database into a pre-trained molecular encoder respectively to obtain molecular vectorization representation of the candidate compound small molecules; constructing an index structure corresponding to the candidate compound small molecules based on the molecular vectorization representation of the candidate compound small molecules; inputting a protein target to be matched into a pre-trained protein target encoder to obtain protein target vectorization representation corresponding to the protein target; and matching the protein target vectorization representation based on the index structure to obtain a target compound small molecule corresponding to the protein target. The method establishes a full-amount mapping function of the target and the molecule through a vector calculation mode, realizes high-throughput virtual screening in a second-level calculation time, realizes rapid virtual screening of a full-amount candidate molecule library, improves the precision of the virtual screening, and increases the possibility of drug discovery.

Embodiments of the present disclosure provide a molecular property prediction method, related device and medium. The method splits and recombines a first molecule in an unlabeled molecule dataset to obtain a new second molecule, determines a training sample based on the first molecule and the second molecule, and optimizes a molecular encoder using the training sample. Then, the molecular property prediction model based on the optimized molecular encoder is trained using a labeled molecule dataset to achieve accurate prediction of the molecular property. Embodiments of the present disclosure can fully utilize the substructure information inside the molecule to improve the accuracy and generalization ability of the prediction, optimize the molecular representation ability of the molecular encoder, and enable the target molecular encoder to better understand the combination relationship between the molecular fragments, thereby improving the representation quality and prediction accuracy of complex molecular structures. Embodiments of the present disclosure can be applied to drug discovery, material science, molecular virtual screening and other scenarios.

The invention belongs to the technical field of pharmaceutical analysis, and particularly relates to a method for separating active components in tobacco based on liquid-phase segmented separation, SPR, affinity chromatography enrichment and mass spectrometry detection, a product and application. According to the method, liquid chromatography separation, SPR detection screening, affinity chromatography enrichment and mass spectrum identification technologies are fused, and active small molecules are screened and enriched from a complex system by virtue of high sensitivity of SPR and accuracy of mass spectrum. The method comprises the following steps: firstly, carrying out liquid chromatography segmented separation on extract components to improve SPR detection precision and affinity enrichment efficiency; by means of specific binding of Ni Sepharose FF (NTA) resin and a His tag, more target proteins are fixed, and the micromolecule enrichment effect is further enhanced; and finally, identifying the molecular structure by using mass spectrum, and locking the bioactive small molecule combined with the target protein. According to the strategy, efficient enrichment of small molecule ligands is achieved, and a new way is provided for early-stage development of small molecules in drug discovery. 6.

The present invention relates to the field related to artificial intelligence and drug discovery. Specifically, a drug-drug interaction (DDI) prediction method based on RGDA-DDI is invented to solve the problem that the existing DDI prediction methods are not ideal. The method is divided into a data encoding module, a feature fusion module and a prediction module. The data encoding module is composed of multiple Residual-GAT submodules, each of which is composed of a graph attention layer, a Normalize layer and a SAGPooling layer, and is used to extract multi-scale features of the input drugs; the feature fusion module is composed of two dual-attention mechanism submodules, which are used for multi-scale drug feature fusion; finally, the fused features are input into the prediction module for prediction. This method overcomes the shortcomings of the existing DDI prediction methods, which lack modeling of multi-scale drug features and lack of mining of potential drug pairs (DDP) features. Experimental verification shows that the prediction performance of this method is better than the recently disclosed drug-drug interaction prediction method.

Methods and systems are described for a high-level approach to organ generation by self-assembly using bioprinting, overcoming longstanding challenges in replicating the intricate architecture and function of complex organs. In some embodiments, these methods are used to produce lung tissues and microtissues, demonstrating how mini-lung constructs can be produced on a small scale through specialized processes and media. In such embodiments, methods and systems for generating bioprinted lung tissues and microtissues are provided, as are tissues made by such methods. The tissues find use in implantation, drug discovery, personalized medicine, and other applications. Methods for the large-scale manufacturing of lung epithelial stem cells are also provided.

The present disclosure relates to methods and compositions for generating topographically organized tissues in vitro, for the resulting cultured tissue and components thereof, and for uses of such cultured tissue and its components in drug discovery, toxicology studies, and therapy.

This invention discloses a molecular event visualization method and electronic device, proposing the concept of a molecular film. The method acquires the topological structure file of the drug molecule-target protein and the original trajectory file generated after molecular dynamics simulation of the drug molecule-target protein; based on the original trajectory file and topological structure file, it obtains the keyframe sequence of the molecular dynamics simulation of the drug molecule-target protein; it monitors the keyframe sequence to identify key event sequences of the drug molecule-target protein, and annotates the key event sequences to obtain annotated key event sequences; and it renders the annotated key event sequences to visualize and output the generated rendering data as molecular events, significantly improving the efficiency and depth of understanding molecular mechanisms of action in drug discovery and optimization.

The present application relates to a candidate drug efficacy prediction and selection method based on a graph neural network, a medium and equipment, first, a biological medicine causal chain is obtained, then an efficacy prediction model is constructed and trained according to the causal chain. Next, after the model is constructed, the target differential protein is determined, and the relationship is determined according to the type of the differential protein. Finally, the differential protein is taken as the tail entity, the relationship is taken as the edge, the candidate drug is taken as the head entity, the triple is constructed, the prediction model is input, and the efficacy prediction result of each candidate drug is output. Overall, the present application solves the problem that the prior art cannot efficiently integrate and mine the multi-dimensional association relationship among drugs, target points and diseases, constructs an interpretable, scalable and updatable knowledge network, reduces the difficulty of drug discovery, shortens the research and development cycle and the like.

Provided herein are compositions comprising a particle comprising a library encoded bead (e.g., DEL bead) coated in a polymeric matrix forming a core-shell particle, wherein the core-shell particle is further inside a 3D tissue culture. Also provided herein are methods of making such particles, and methods of using such particles for drug discovery such as identification of bioactive compounds via high-throughput cellular activity-based phenotypic screens of DNA-encoded chemical library beads.

The invention discloses a multi-modal biophysical characterization device, a multi-modal biophysical characterization system, a multi-modal biophysical characterization method and application thereof. The multi-modal, high-resolution, high-throughput, high-sensitivity, low-cost, low-damage and configurable physical characterization of single cells or multi-cell polymers can be realized, stimulation (such as mechanical stimulation, electrical stimulation and light stimulation) of different types and intensities can be performed on a to-be-detected sample, and the in-vivo microenvironment can be better simulated; and carrying out operations (such as marking, curing, ablation, cutting, extraction, sorting and the like) on samples at specific positions or regions, and carrying out comparative analysis in combination with other characterization methods (such as protein staining, histochemical staining, single cell sequencing and the like). The multi-mode biophysical characterization device is suitable for the fields of synthetic biology, diagnosis, drug discovery, tumor early screening, cell therapy, precision medical treatment and the like.

Compounds and methods for combinatorial drug discovery in nanoliter droplets are described herein. More particularly, novel synergistic agents that increase efficacy of antibiotic agents to treat bacterial infections are described.

The application relates to the technical field of computer-aided drug design, and provides a molecule generation method, system, medium and equipment for drug discovery, which comprises the following steps: acquiring a SMILES string of a ligand and an amino acid sequence of a target protein, respectively extracting a ligand feature vector and a protein feature vector, splicing and fusing, and then predicting a binding affinity value through a multilayer perception machine; taking the protein feature vector as a condition, generating a new molecular potential representation through a reverse denoising process of a conditional diffusion model; wherein, at each step of the reverse denoising process, a graph-level readout operation is performed on pure noise, an affinity value is predicted through the multilayer perception machine, a gradient of an affinity guidance loss is returned to a noise prediction network, and the new molecule generation is guided to a high affinity area; and the new molecular potential representation is decoded into a SMILES string through a pre-trained molecular language decoder. Novel molecules with high binding potential can be quickly generated.

The invention discloses a novel equivalence device structure closing and single-step repairing method and system in medical diagnosis, drug discovery and physiological status modeling, belongs to the field of medical diagnosis analysis, biological information processing and model verification, and ensures the reliability and traceability of the process through structural equivalence device detection and receipt track recording. The method monitors sequential equivalents (ABBA rectangles for checking consistency of operational orders) and conservation equivalents (triangles for checking information conservation and energy balance) during operation to find anomalies in diagnostic inference chains, drug action pathways, or physiological closed loops (such as predictor deviations, energy conservation imbalances, or model inconsistencies). When a non-equivalence condition is detected, the system selects a unique repair adapter from a geometric layer, a frame layer and a field layer for correction according to a preset priority, and the deviation metric mu is strictly reduced by one (delta mu = 1) during each repair, and is gradually converged to an equivalence closed state.

The invention belongs to the field of biological medicine, and particularly relates to application of an active component based on a radish seed extract as an angiotensin converting enzyme inhibitor. The active ingredient is sinapine (sinapine) or nasturtoside (Gluconatutin), and the active ingredient is one or more than one of the active ingredients. According to the invention, affinity ultrafiltration is combined with a UPLC-Orbitrap-MS method, potential inhibitors are rapidly screened and identified on line from radish seeds, the affinity of active compounds and ACE is researched by combining molecular docking through ACE activity inhibition experiments, and finally two potential ACE inhibitors, namely sinapine and nasturtoside, are determined by combining an affinity ultrafiltration RBA value, IC50 and a binding force of molecular docking. And further research is carried out after screening, so that the research range is greatly reduced, the time of new drug discovery and research and development processes is saved, and the screening cost and risk are reduced.

The invention relates to the technical field of computational biology and artificial intelligence assisted drug discovery, and discloses a drug-target effect prediction method and system based on multi-mode self-supervised learning. The method comprises the steps of drug side self-supervised pre-training, protein side self-supervised pre-training, multi-feature fusion, drug-protein interaction modeling and multi-task joint prediction. Drug-target effect prediction is carried out based on self-supervised pre-training and multi-modal information fusion, a self-supervised learning method is firstly used to train a deep learning model by using label-free data, and then the deep learning model is used to carry out multi-modal characterization, multi-modal fusion and interaction relationship modeling on drug molecules and protein targets. According to the method, combined prediction of drug-target interaction, affinity and action mechanism can be realized, and the prediction precision and model robustness of the model are effectively improved.

The invention belongs to the technical field of computational chemistry and artificial intelligence crossing, and provides a molecular potential energy surface prediction method based on deep learning. The method comprises the following steps: inputting a structure file of an unoptimized molecule, and reading and predicting energy and force of a current molecular structure by utilizing a machine learning potential model; and then, judging whether the structure is converged or not according to a prediction result by adopting a GeomeTRIC algorithm, and if not, adjusting coordinates to generate a new structure and performing circular prediction until the structure is converged. According to the method, the quantum chemistry and the deep learning technology are combined, the calculation efficiency can be greatly improved, complex inter-atomic interaction in molecules can be fully captured, and the prediction accuracy is ensured; and meanwhile, batch processing and automatic generation of a quantum chemistry software interface are supported, and the method is particularly suitable for high-throughput molecular structure optimization in the fields of drug discovery, material science and chemical product design.

The invention discloses a biomolecular interaction prediction method based on multi-modal attention fusion, and belongs to the technical field of artificial intelligence drug discovery. The method comprises the following steps: acquiring multi-modal characteristics of drugs, targets, diseases and genes: sequence structure characteristics, 3D structure characteristics, similarity network characteristics and biological relation network embedding characteristics; constructing a feature fusion prediction model, and performing training; inputting the multi-modal features of the two biological entities into the trained feature fusion prediction model, and outputting the probability of interaction of the two biological entities; the feature fusion prediction model comprises a Transform encoder and an MLP (Markup Language Protocol) network; the multi-modal features are input into a feature fusion prediction model for stacking and then are input into a Transform encoder, the features are processed by using a multi-head self-attention mechanism, and an output result is flattened and subjected to dimension reduction processing to obtain embedded vector representation; and finally, performing element corresponding multiplication on the embedded vectors of the two biological entities, inputting the embedded vectors into an MLP network, and outputting an interaction probability between the two biological entities.

To provide a biomimetic system that mimics the human proximal tubule, which is a high-performance in vitro model that can reproduce the physiological functions of the human proximal tubule in vitro and can be used as an evaluation tool in drug discovery.SOLUTION: The present invention provides a proximal tubule biomimetic system comprising a microfluidic device and LTL-positive cells derived from pluripotent stem cells contained within the microfluidic device. The microfluidic device has (A) a device body, (B) a first chamber provided in the device body, (C) a second chamber provided in the device body, and (D) a porous membrane positioned between the first chamber and the second chamber, separating the first chamber from the second chamber. The LTL-positive cells are contained within the first chamber and adhere to a first surface of the porous membrane facing the first chamber. The first surface of the porous membrane is coated with an extracellular matrix.SELECTED DRAWING: None