315results about "Molecular structures" patented technology

The application provides an efficient deep learning method and system based on a squeeze-excitation-network and a ConNet network, which comprises the following steps: obtaining a protein global sequence and a protein local sequence as a sample set, and setting model parameters of a DeepNet deep framework; dividing the sample set into a training set and a verification set, setting a model architecture of the DeepNet deep framework, extracting effective feature information, combining negative samples and positive samples in the protein global sequence and the protein local sequence, and sending the samples into the DeepNet deep framework for training and hyperparameter tuning; adaptively coding the protein global sequence and the protein local sequence; designing a local sequence processing branch and a global sequence processing branch, extracting network structure features and key information between long and short sequences by using different scale convolution networks, and calculating final prediction probability according to the key information. The application solves the technical problems that sufficient feature information cannot be extracted and global information is not fully considered and between global information and local information.

This invention discloses a breast cancer classification method based on Piezo1 expression. After obtaining tumor tissue samples from patients, the method detects the Piezo1 protein expression level using immunohistochemistry and classifies them into high-expression and low-expression types according to a validated scoring standard. This classification result guides individualized treatment, with high-expression patients recommended for treatment regimens including inhibitors of mechanotransmission pathways. By integrating tumor mechanotransmission characteristics into the clinical classification system, this invention can identify a subgroup of breast cancer driven by an abnormal mechanotransmission microenvironment that cannot be distinguished by traditional molecular classification. This not only improves and supplements the existing classification framework, making the understanding of breast cancer heterogeneity more comprehensive, but also more accurately predicts the invasiveness, metastasis potential, and poor prognostic risk of these patients.

Provided are a method and system for predicting an activation potency of agonist molecules on G Protein-Coupled Receptors (GPCRs). The method includes: blindly speculating complex structures formed by binding of a ligand to an activated receptor structure and an inactivated receptor structure, respectively, via global molecular docking; extracting an initial path enabling an inactivated complex structure to be activated to an activated complex structure based on an enhanced sampling algorithm; searching for a minimum free energy path closest to the initial path by applying an automatic path optimization algorithm; calculating a free energy distribution curve along the minimum free energy path by employing umbrella sampling and determining an energy barrier height and a free energy difference before and after activation, thereby determining the activation potency of the ligand structure on the GPCRs.

The present application belongs to the technical field of artificial intelligence assisted drug screening, and particularly relates to a method for screening active molecules against carbapenem-resistant enterobacteriaceae based on a LightGBM algorithm, a medium and an apparatus. The method constructs a LightGBM integrated learning framework, fuses ADME rules optimized for the outer membrane barrier characteristics of gram-negative bacteria and multi-target molecule docking verification, effectively solves the problem of data imbalance caused by the scarcity of active samples and the huge compound library, and significantly improves the hit rate of screening. The present application also provides a computer readable storage medium and an electronic device. By storing and executing the above program, the present application can quickly and standardizedly identify anti-CRE candidate molecules from a large number of compounds, greatly reducing the computing power cost and time cycle of new drug research and development. The present application is designed to overcome the bottleneck of gram-negative bacterial outer membrane permeation, and provides an efficient, accurate and intelligent screening tool for combating CRE super-bacterial infections.

A non-transitory computer-readable recording medium stores therein a training program that causes a computer to execute a process including first inputting a first image capturing a target compound to an encoder of an auto-encoder including a latent space that is isometric with respect to an input space, second inputting a latent variable output by the encoder and a typical compound model corresponding to a typical case of a three-dimensional structure of the target compound to a decoder of the auto-encoder, and updating parameters of the encoder and the decoder, based on a reconfiguration error between a second image reconfigured based on an output of the encoder and the first image.

The application provides an innovative screening method and application of a key gene of intraparenchymal cholangiocarcinoma causing vascular invasion. The application first identifies specific cells enriched in intraparenchymal cholangiocarcinoma tissues causing vascular invasion based on single-cell transcriptome data of tissues causing and not causing vascular invasion, and screens a plurality of highly expressed genes in the specific cells. At the same time, a plurality of up-regulated differential genes are screened based on ordinary transcriptome data of tissues causing and not causing vascular invasion. Subsequently, common genes from the two data sources are selected for subsequent cell phenotype screening and function verification experiments. According to the experimental results, the gene capable of reducing the budding ability of endothelial cells is identified as the key gene of intraparenchymal cholangiocarcinoma causing vascular invasion. The application aims to provide an innovative screening strategy for the discovery of the key gene of intraparenchymal cholangiocarcinoma causing vascular invasion, so as to provide a beneficial idea for the precise treatment of intraparenchymal cholangiocarcinoma.

The present disclosure provides a training method of a prediction model, a binding affinity prediction method, device and equipment. It relates to the field of artificial intelligence, and particularly relates to the fields of deep learning, natural language processing, material screening and the like. The specific implementation scheme is: performing reinforcement learning on the first representation of the protein and the first representation of the ligand respectively to obtain the second representation of the protein and the second representation of the ligand; performing fusion learning on the second representation of the protein and the second representation of the ligand to obtain the third representation of the protein and the ligand, and the third representation is the complex molecule representation of the protein and the ligand; predicting the binding affinity of the protein and the ligand based on the third representation of the protein and the ligand to obtain a binding affinity prediction value; constructing a loss function based on the binding affinity prediction value and a true value of the binding affinity; and training a prediction model for predicting the binding affinity based on the loss function. According to the scheme of the present disclosure, the prediction accuracy of the prediction model obtained by training can be improved.

This invention relates to an RNA sequence design method based on isovariant geometry and graph neural networks, comprising: first, RNA three-dimensional structure data and corresponding sequences; then, after dataset encapsulation and feature extraction, vector embeddings that can be processed by graph neural networks are generated; next, the data is fed into the Equiformer+GVP model for modeling, and the model outputs the probability distribution of four bases at each nucleotide position; finally, the bases are selected according to the probability distribution to form the predicted RNA sequence. Among these methods, E(3) isovariant constraints are introduced to achieve geometric consistency expression, and multi-scale geometric feature encoding is combined to enhance the model's understanding of local and global structures, significantly improving the model's physical rationality, prediction accuracy and universality; and the three-dimensional geometric skeleton of the RNA molecule is used as the only input, eliminating the dependence on secondary structures or external contact diagrams, and learning and generation are performed directly at the three-dimensional spatial coordinate level, thereby achieving significant improvements in physical consistency, geometric completeness and generalization ability.

A method of analysing a structure of a composition of matter in a sample comprising obtaining a data set comprising a plurality of spectra from the composition, from a first method of analysis dividing each of the spectra into a plurality of bins determining a control parameter or parameters indicative of synchronised fluctuations in signal intensity across some or all channels, resulting in universal correlation between said bins determining a partial covariance of different bins across the plurality of spectra using the control parameter to correct the correlation of intensity fluctuations between said bins.

Provided is a method for identifying an antibody that has a certain biological function in relation to an antigen using a machine learning model. The method comprises the steps of: a) obtaining antibodies from B cells of at least one animal immunized with the antigen; b) determining the sequences of the antibodies in a) or fragments thereof and at least one type of functional data thereof; c) building a machine learning model using one or more machine learning algorithms, and training the model using training data, wherein the training data comprises the sequences and functional data in b); d) using the trained model to predict the ability of sequences from B cells of the immunized animal in a) or from B cells of a different animal immunized with the antigen, to encode an antibody that has the biological function in relation to the antigen; e) generating one or more antibodies from the sequences in d) predicted to encode an antibody that has the biological function in relation to the antigen; and f) determining whether the antibodies in e) has the predicted biological function. Enrichment scores of the sequences, CDR groups, lineages and / or clusters of the selected sequences in step d) are calculated and those having a higher enrichment score are selected to generate the antibodies.

The present disclosure provides a method for embedding watermarks into protein generative models, comprising pretraining an SE(3)-equivariant watermark encoder and decoder, wherein the encoder receives a watermark code and generates a watermark-conditioned structure, and the decoder receives the watermark-conditioned structure and predicts an embedded watermark, and using a watermark-conditioned adaptation to encode a desired watermark code and generate an updated protein generative model by merging the desired watermark code into model weights from an original protein generative model, wherein the protein generative model is fine-tuned with a message retrieval loss and a consistency loss. The watermark-conditioned adaptation includes a gating vector derived from the watermark code. The method enables copyright authentication and tracking of generated protein structures while preserving structural integrity and biological functionality.

The compound molecular fingerprint prediction belongs to the technical field of mass spectrum data analysis, and from the perspective of fully mining the implicit information of mass spectrum data, neutral loss information is added behind corresponding ion peaks when a vector representation of mass spectrum data is constructed, natural language processing technology is adopted to learn the relationship between peaks and between peaks and neutral losses in the mass spectrum, a multi-dimensional spectrum vector is constructed, and molecular fingerprints are predicted. Due to the addition of neutral loss of corresponding ion peaks in the spectrum vector, more abundant structural information is contained, and the accuracy of molecular fingerprint prediction can be effectively improved.

The application relates to the field of biomedical technology, and discloses a diagnostic agent for identifying melanoma molecular subtype typing and application, wherein the diagnostic agent comprises a first antibody specifically combined with a SOX10 protein and a second antibody specifically combined with an EGR1 protein; the diagnostic agent can be applied to preparation of a diagnostic product for evaluating the prognostic effect of a melanoma patient, preparation of a diagnostic product for predicting the treatment sensitivity of melanoma to a BRAF inhibitor, and preparation of a diagnostic product for guiding an individualized treatment scheme of melanoma. The diagnostic agent for melanoma molecular subtype typing can be directly transformed into clinical practice, and can assist in realizing real individualized treatment.

This invention relates to the field of biotechnology, specifically to a method for screening highly efficient and low-toxicity mRNA delivery vectors based on an ionizable lipid library. The method includes: S1. Providing a lipid library containing at least 100 structurally diverse ionizable lipids; S2. Using an automated microfluidic platform, mixing each ionizable lipid in the lipid library with helper lipids, cholesterol, PEG-lipids, and reporter gene mRNA, respectively, to prepare a lipid nanoparticle (LNP) library in parallel; S3. Performing high-throughput in vitro screening on the LNP library; S4. Selecting the ionizable lipids corresponding to the LNPs with the top 10% efficacy scores and cell viability values ​​greater than 80% as Hit (initial positive candidates); S5. Performing rapid in vivo validation of the Hit; S6. Determining the final selected lipids based on the criteria of in vivo liver expression intensity > 200% of the positive control and ALT < 100 U / L. This method for screening highly efficient and low-toxicity mRNA delivery vectors based on an ionizable lipid library can more effectively screen for non-toxic mRNA delivery vectors.

To provide methods, systems and computer-readable media for detecting ploidy of chromosome segments or entire chromosomes, on the basis of phase determination of an allele and determination of individual and joint probabilities and of a best fit model.SOLUTION: According to some aspects, the invention provides methods, systems and computer readable media for detecting cancer or a chromosomal abnormality in a gestating fetus. The invention also provides methods for detecting circulating tumor nucleic acids on the basis of allelic imbalance ratios of polymorphic loci found by ploidy determination. The invention further provides methods for detecting single nucleotide variants on the basis of estimates of the amplification efficiency and the error rate, and methods for detecting single nucleotide variants on the basis of a median variant allele frequency for control samples derived from a plurality of individuals.SELECTED DRAWING: Figure 20A-20B

A system for binding peptide search for immunotherapy is presented. The system includes employing a deep neural network to predict a peptide presentation given Major Histocompatibility Complex allele sequences and peptide sequences, training a Variational Autoencoder (VAE) to reconstruct peptides by converting the peptide sequences into continuous embedding vectors, running a Monte Carlo Tree Search to generate a first set of positive peptide vaccine candidates, running a Bayesian Optimization search with the trained VAE and a Backpropagation search with the trained VAE to generate a second set of positive peptide vaccine candidates, using a sampling from a Position Weight Matrix (sPWM) to generate a third set of positive peptide vaccine candidates, screening and merging the first, second, and third sets of positive peptide vaccine candidates, and outputting qualified peptides for immunotherapy from the screened and merged sets of positive peptide vaccine candidates to support downstream clinical decision making.

The application provides a melanin production inhibiting peptide and a preparation method and application thereof. The amino acid sequence of the inhibiting peptide is GLPGISGGGY. The preparation method comprises the following steps: washing, degreasing and removing impure proteins of sturgeon skin, then swelling and homogenizing under an acid condition to obtain a sturgeon skin homogenate; adding 6000-6100 U / g protease into the sturgeon skin homogenate, and performing enzymolysis under the condition that the temperature is 34-36 DEG C and the pH is 6.0-7.0 to obtain an enzymolysis liquid containing sturgeon skin collagen polypeptide; and obtaining the target peptide by ultrafiltration of small molecule components and combining MITF / TYR double target virtual screening and 3D-QSAR pharmacophore model orientation. Experiments prove that the inhibiting peptide has high biological activity, low cytotoxicity and good skin safety, and has a wide application prospect in the preparation of whitening cosmetics, skin care products and pigment deposition disease treatment drugs.

A system and method of predicting efficacy of treatment of a predetermined medical condition by at least one processor may include obtaining a Drug-Drug Interaction (DDI) embedding value, representing occurrence of DDIs between a substance of interest and one or more drugs selected from a plurality of baseline drugs, in a DDI embedding space; receiving a chemical structure data element, representing a chemical structure of the substance of interest; and predicting efficacy of the substance of interest in treatment of the predetermined medical condition based on (i) the DDI embedding value and (ii) the structure data element.

The application discloses a method for improving the flux of compound-protein interaction experiment. The method of the application adopts the method of mixing a plurality of test compounds according to a certain mixing rule to form a plurality of mixture systems, and establishing the corresponding relationship between the interaction ability of each test compound and the target protein and the mixture system, and then high-throughput analyzing the corresponding target protein of the test compound. The analysis method of the application can improve the existing test compound-target protein experiment detection flux by more than 10 times, save more than 90% of the experiment cost and time, greatly reduce the labor, time and experiment cost of consumables, and has significant economic significance.

This invention discloses an antioxidant active peptide derived from Litsea cubeba, its preparation method, and its application, relating to the field of biotechnology. The amino acid sequence of this Litsea cubeba-derived antioxidant active peptide is NPYYFWDLSF. The preparation method of this Litsea cubeba-derived antioxidant active peptide includes the following steps: S1, extracting Litsea cubeba protein from Litsea cubeba seed cake; S2, enzymatically hydrolyzing the Litsea cubeba protein using acidic protease to obtain the enzymatic hydrolysis product; S3, separating the enzymatic hydrolysis product by ultrafiltration and collecting the ultrafiltration fraction; S4, screening candidate peptides with high antioxidant activity from the peptide fragments of the ultrafiltration fraction; the application of the Litsea cubeba-derived antioxidant active peptide in the preparation of drugs or functional foods for the prevention or treatment of oxidative stress-related diseases; the NPYYFWDLSF peptide obtained by the preparation method of this application can alleviate oxidative stress damage through the PI3K-AKT signaling pathway; this application provides a theoretical basis for the high-value utilization and potential application of Litsea cubeba by-products.

The application discloses a method for detecting glioma chromosome abnormalities based on targeted sequencing, and belongs to the technical field of biological medicine. The method first acquires the allele frequency of a to-be-detected sample at preset SNP sites (covering 1p, 1q, 19p, 19q, chromosome 7 and chromosome 10), and then calculates and determines whether specific chromosome arms or chromosomes have loss of heterozygosity. Meanwhile, the copy number of the region where each SNP site is located is calculated based on the sequencing depth, and the total copy number of the above-mentioned chromosomes is obtained by integration. Finally, the loss of heterozygosity determination result and the chromosome copy number information are comprehensively combined, so that the simultaneous identification of 1p / 19q co-deletion, gain of chromosome 7 (+7) and deletion of chromosome 10 (-10) is realized. The method does not require paired samples, can accurately quantify the copy number, avoid false positives, and only needs to detect part of the SNP sites, that is, can be combined with hot spot mutation detection, thereby saving cost and improving detection efficiency.

A method for simulating different ultrasonic environments by molecular dynamics and analyzing protein structures in the environments: 1) obtaining a crystal configuration of a protein from a protein database. 2) selecting a force field, creating a box. 3) adding ion neutralization system in the created box, and performing energy minimization in order to eliminate unreasonable energy barriers. 4) pre-equilibrating the system. 5) after the pre-equilibration, using GROMACS software to simulate the extracted protein under different ultrasonic conditions. 6) processing the trajectory file obtained after simulation by different software, and combining with visualization software to obtain data images related to the protein structure. By the above method, the simulation result is close to the experimental result, and the influence of ultrasonic waves on the protein structure and physicochemical properties is further explored.

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. The method further includes: generating target molecule data representing a target molecule based on the first molecular fragment data and the initial molecule data. According to embodiments of this disclosure, for the three-dimensional structure of the protein, a molecular fragment is automatically determined in the initial molecule, and the initial molecule is optimized based on the determined molecular fragment, so 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.

This invention discloses an artificial intelligence-based method for predicting drug interactions based on external entity association mapping, comprising the following components: (1) Extraction of intrinsic properties of drug molecules: The spatial geometry and atomic properties of molecules are processed using a Uni-Mol pre-trained model to obtain drug molecule characterization. (2) External entity association mapping: Projection blocks are constructed using a knowledge graph, and complex association patterns of external entities corresponding to drugs are captured through graph neural networks and global perception logic. (3) Deep fusion of multi-source heterogeneous information: Information is efficiently integrated using attention mechanisms and multilayer perceptrons to form the final fused characterization. (4) Prediction and decoding of interactions: The specific types of interactions are accurately decoded and predicted using a decoder architecture. (5) Interactive visualization and decision support: Visualization tools and AI decision support are provided to help researchers reduce trial-and-error costs and make scientific decisions.

The invention relates to a method for generating candidates of amino acid sequences of epitopes, the method comprising executing, in one or more processing devices, a neural network for generating candidates of sequences of epitopes, the neural network being a result of fine-tuning a neural network trained for generating amino acid sequences, wherein the training has been performed with data of amino acid sequences comprising amino acid sequences of non-epitopes, and the fine-tuning has been performed with data of amino acid sequences of epitopes.

This invention discloses a method for designing transmembrane regulatory proteins based on cueing strategies and generative models, belonging to the field of bioinformatics. It includes a target survey stage and a closed-loop design stage. In the target survey stage, a generative diffusion model is used to generate virtual probes targeting the membrane protein. A set of complex conformations is obtained by combining sequence design and structure prediction models, and binding hotspot regions are identified based on the spatial distribution density of the probes, overcoming the dependence on manually specified binding sites. In the closed-loop design stage, based on the identified hotspot regions, an initial backbone is generated using a generative diffusion model. A structure cueing strategy guides the sequence design and structure prediction models to perform closed-loop iterative optimization, generating sequences that selectively bind to the transmembrane domains of membrane proteins and regulate their functions. This invention achieves automated, function-guided design of transmembrane regulatory proteins, effectively expanding the range of designable targets and significantly improving the stability and functional specificity of the designed products in the membrane environment.

The application discloses a targeting superantigen fusion protein based on an improved SE(3)-Transformer and an implementation method. In an offline stage, amino acid sequences are first converted into one-hot encoding or language model embedding (such as ESM-2), and are spliced with multiple sequence alignment (MSA) features for geometric initialization. A neural network (improved SE(3)-Transformer) combined with multiple sequence alignment (MSA) and an attention mechanism is constructed to predict the coordinates of C alpha, C, N and O atoms for main chain prediction, and the neural network is trained through a gradient descent method based on a physical heuristic potential item. In a verification stage, the improved SE(3)-Transformer after training is used to generate a predicted structure, conformational stability is verified through a simplified force field, and fine tuning is performed based on a confidence score. The application can accurately predict the structure of a target antigen epitope and an antibody variable region, optimize a superantigen functional domain in combination with a graph neural network, and dynamically design a flexible connecting peptide to realize modular fusion.

A protein active site prediction method based on geometric graph neural network belongs to the field of bioinformatics and protein structure analysis. First, the original protein data is preprocessed by multi-modal feature extraction and geometric graph construction, and ProtT5 deep embedding and physicochemical properties are fused. Then, a deep ActiveSiteGNN model with explicit geometric perception ability is constructed, and the stacked geometric encoder and geometric edge update layer are used to dynamically capture the micro three-dimensional spatial features. Next, a multi-task collaborative optimization and dynamic threshold search strategy is designed, combined with weighted sampling to solve the serious sample imbalance, and the best decision threshold is selected based on the validation set in real time. The integrated reasoning and graph diffusion smoothing technology is introduced to globally calibrate the prediction probability distribution based on the biological space prior. Finally, the evaluation is carried out on the independent test set. The method has strong structure perception ability and provides a feasible solution for accurate prediction of protein functional sites.