12 results about "Molecular Databases" patented technology

The invention discloses a rapid detection method for traumatic brain injury by fusing genetic engineering and quantum dots, and relates to the technical field of traumatic brain injury detection. The method comprises the following steps: acquiring a suspected patient biological sample, extracting biomolecule components, and comparing the biomolecule components with a healthy population biomolecule database to obtain related differential expression molecules. A specifically recognizable recombinant antibody is constructed by genetic engineering, and is connected with a quantum dot through a coupling reaction to prepare a detection probe. The probe and a biological sample are mixed and reacted, and the intensity of a fluorescence signal generated by combination is collected by a fluorescence detection device. A standardized signal value is obtained through signal processing algorithm noise reduction and feature extraction, and a preliminary detection result is determined by combining a bioinformatics database evaluation sample. And finally, according to the differential expression molecule, the standardized signal value and the preliminary result, analyzing a data change trend in a preset time window by using a multivariable statistical model, and generating a diagnosis report. According to the method, various technologies are fused, and a new path is provided for traumatic brain injury detection.

This invention relates to a method for constructing a machine learning potential energy model based on hierarchical active learning, comprising the following steps: constructing a database of background solvent molecules and lithium salt molecules; initializing a machine learning potential energy model committee; outer active learning automatically exploring the chemical species composition space of the electrolyte, generating electrolyte formulations and initial structures; determining whether a structure needs to be included in the labeling range based on uncertainty calculations; automatically constructing a liquid phase environment based on classical force field simulation methods; performing high-precision simulations based on first-principles calculations and labeling the energy and force values ​​of the structures; inner active learning driving the machine learning potential energy model to explore the configuration space and label the energy and force values ​​of structures with high uncertainty; obtaining a first-principles structure database of the real liquid phase environment through several iterations; and training to obtain the final high-performance machine learning potential energy model. This invention systematically and comprehensively samples the chemical species composition space of the electrolyte and the molecular simulation configuration space based on hierarchical active learning, thereby ensuring the predictive performance and simulation accuracy of the machine learning potential model on unknown and complex electrolyte systems.

The invention discloses an oil refining model generation method and a visual display method and device. The method comprises the following steps: creating a single device model for each device based on a molecular database and a chemical reaction rule base in the oil refining field; according to the cutting condition output by the single device model, constructing a logistics connection model with a downstream single device model; according to the whole-process technological processes of the historical production schemes in different time periods, the logistics connection model is connected with a downstream single device model, and a whole-process model of each historical production scheme is constructed; and according to historical raw material information, performing simulation calculation on the whole-process model of each historical production scheme to obtain and store a result log, and based on this, providing a whole-process display function of the historical production scheme for a user through a visual UI, so that the user can visually understand the process of different production schemes in different time periods of refinery equipment, and the user experience is improved. Historical process data can be conveniently traced, and production schemes and process changes can be tracked.

A generic cancer prognosis evaluation system based on LAMA5 expression provided by the invention relates to the technical field of generic cancer prognosis evaluation, and comprises the following steps: acquiring multi-source molecular data, establishing a standardized data input path to obtain LAMA5 gene molecular information, and completing sample identification and field standardization by calculating mutation frequency and gene copy number variation of the LAMA5 gene molecular information to obtain a generic cancer prognosis evaluation result. And an LAMA5 generic cancer molecular database is formed. A standardized data input path and a unified field format are formed by establishing an LAMA5 generic cancer molecular database and integrating TCGA, GTEx, a human protein map and other multi-source molecular data, the database achieves generic cancer prognosis evaluation system calculation of LAMA5 mutation frequency and gene copy number variation, the data consistency and statistical reliability of multiple cancer species are improved, and the method is suitable for large-scale popularization and application. And a data basis is provided for pan-cancer level expression and variation analysis.

A molecular vocabulary can be added to a tokenizer of a language model. The molecular vocabulary can include character strings as words representing atomic environments, explicit atomic positions, and forward-connecting positions based on a molecular database that includes data describing molecules and their properties. A molecular syntax can be defined for the tokenizer that represents each of the molecules as a respective molecular sentence made up of tuples corresponding to a quantity of atoms in a respective molecule and including words from the molecular vocabulary. The molecules can be tokenized according to the molecular vocabulary and the molecular syntax. The language model can be trained to perform property prediction for molecules or to identify molecules having targeted properties using the tokenized molecules and their properties. The trained language model can perform property prediction for a molecule not in the molecular database or identify molecules having the targeted properties.

Embodiments of the invention provide a data screening method, a computing device, a storage medium and a program product. The data screening method comprises the steps of obtaining at least one item molecule attribute information and a verified molecule set corresponding to a target item; determining a molecule set according to the item molecule attributes and the verified molecule set; then acquiring a set access frequency and a molecular set score corresponding to each molecular set, and acquiring a molecular set weight corresponding to each molecular set according to the set access frequency and the molecular set score; determining a target sample molecule set according to the molecule set weight of each molecule set, and generating a project scoring model for the target project based on the target sample molecule set; and determining a target molecule in a molecule database according to the project scoring model. The molecules for training the scoring model are determined by obtaining the weight corresponding to each molecule set, so that the problem of poor scoring model effect caused by excessive invalid molecules when the scores for training the molecules are obtained can be avoided.

The application relates to a method and system for predicting the molecular level composition of a petrochemical production stream based on multiple models, and relates to the technical field of oil refining and chemical molecular management, and comprises the following steps: determining the molecular composition of raw materials, splicing structural units based on a structural unit-bonding moment matrix framework, and constructing a molecular digital structure topology; combining a preset molecular database, a probability density function and a molecular property predictor to construct a molecular composition model; establishing a molecular level reaction network based on a catalytic reforming reaction mechanism, combining a reaction rate expression to construct a molecular level reaction kinetics model; constructing a reactor model according to mass, energy and momentum transfer equations; constructing inactivation and separation unit models, coupling multiple models in sequence, generating a full-process reaction-separation molecular level prediction model, and predicting the molecular level composition of any stream. The application solves the problems that traditional petrochemical production relies on measured results to adjust process parameters and has operation lag, and through prediction of the molecular composition of a stream, the lag can be eliminated, and the production control precision is improved.

The application discloses a rapid detection method for traumatic brain injury by combining gene engineering and quantum dots, and relates to the technical field of traumatic brain injury detection. The method obtains a biological sample of a suspected patient, extracts biomolecular components, compares the biomolecular components with a biomolecular database of healthy people, and obtains relevant differentially expressed molecules. A recombinant antibody capable of specific recognition is constructed by gene engineering, and is connected with quantum dots through a coupling reaction to form a detection probe. The probe is mixed with the biological sample for a reaction, and a fluorescence signal intensity generated by combination is collected by a fluorescence detection device. After noise reduction and feature extraction by a signal processing algorithm, a standardized signal value is obtained, a sample is evaluated in combination with a bioinformatics database, and a preliminary detection result is determined. Finally, according to the differentially expressed molecules, the standardized signal value and the preliminary result, a multivariate statistical model is used to analyze a data change trend in a preset time window, and a diagnosis report is generated. The method combines multiple technologies and provides a new path for traumatic brain injury detection.

The invention relates to a molecular property prediction method based on topological perception generative molecular characterization, which comprises the following steps of: sampling molecular data from a public unlabeled molecular database, analyzing the molecular data into a molecular graph, and extracting a topological unit set; encoding the molecular graph by using a graph convolutional neural network and a cross-scale attention module, and obtaining a latent variable for subsequent generation; through a dynamic generation mechanism, atoms and chemical bonds are reconstructed in combination with Laplacian position codes, a molecular fingerprint prediction task is introduced, and a loss function is jointly constructed to pre-train a model; and carrying out fine tuning on the pre-trained model on a downstream reference data set MoleculeNet for specific molecular property prediction. By adopting the method disclosed by the invention, the problems of'feature inhibition ', 'shortcut learning' and the like of the existing self-supervised learning method can be solved, and the high calculation overhead of the traditional generative method is avoided, so that the molecular representation with strong discrimination is learned, and the accuracy, robustness and efficiency of molecular property prediction are improved.

The application discloses a cross-modal molecular information retrieval method, system, device and medium, wherein the application adopts a multi-modal fusion method, calculates a contrast loss through a modal extraction encoder to obtain single-modal representations of graph structure, image and text data of molecular information, so that the graph structure information and the image information are aligned to supplement and enrich the text information, and calculates a fusion loss through a modal fusion encoder to obtain multi-modal representations of the molecular information, so that the fusion of different modal data such as the graph structure, the image and the text is realized, and then in the application process, cross-modal retrieval of molecules can be performed based on the multi-modal representations of the molecular information in a molecular database according to target modal data and a target query condition of target molecular information, the demand query of multi-modal information processing is met, and therefore the accuracy and efficiency of molecular information retrieval are improved.

The invention discloses a molecule generation method and device based on a generative adversarial network, equipment, a medium and a product, and relates to the technical field of computational chemistry and batteries. The method comprises the following steps: constructing a molecule database by adopting a matrix engineering method according to atom types and quantity required by target molecules; converting a molecular structure corresponding to the candidate molecular set in the molecular database into a graph structure to obtain a molecular graph database; inputting the molecular graph database into the trained generative adversarial network, and performing molecule generation and decoding to obtain newly generated molecules; based on a preset screening rule, performing molecular screening on the newly generated molecules to obtain screened qualified molecules; converting the screened qualified molecules into three-dimensional structures to obtain three-dimensional molecules; the three-dimensional molecules are used for computational simulation and experimental verification to provide a reference basis for electrolyte design and optimization. According to the invention, molecule generation and screening can be efficiently realized.

The application discloses a drug virtual screening method based on hash learning, which comprises the following steps: firstly, obtaining a protein-molecule complex dataset; defining protein and molecule encoders respectively; defining a contrast learning objective function to learn the similarity information of the protein and the molecule; defining a multi-modal hash objective function to learn the binary vector of the protein and the molecule; constructing a final loss function by combining the contrast learning and the multi-modal hash objective function, and training a model; and representing molecules in a molecule database as binary vectors. When performing drug virtual screening, a protein target is represented as a binary vector. The Hamming distance between the binary vector of the protein target and the binary vectors in the molecule database is calculated, or an inverted index is constructed from the binary vector database to retrieve the most likely binding molecules. According to actual requirements, a certain proportion of molecules are selected as candidate drug molecules. The application improves the precision of drug virtual screening, reduces storage overhead, and improves retrieval speed.