54 results about "Chemical space" patented technology

The invention is applicable to the technical field of drug research and development, and provides a lead compound discovery method based on a large language model, which comprises the following steps: determining a target spot and constructing an initial compound library; generating fragments and forming an initial fragment library; calculating the frequency of occurrence of the fragments and the affinity contribution degree of the fragments to the target protein, and updating the fragment library; fragment sampling weight calculation and candidate fragment selection; the large language model generates molecules according to the candidate fragments; evaluating the quality of the generated molecules and updating the molecule library; and repeating the cycle until a preset iteration round number is reached. A fragment-based drug design method is combined with the large language model, rich domain knowledge of the large language model is used for replacing human experts to guide drug design, fragments are used as prompts to stimulate the internal potential of the large language model, the advantages of the two methods complement each other, exploration of the whole chemical space is completed, and the drug design efficiency is improved. The lead compound reaching the human expert level is designed in actual use, and a new technical means is provided for drug research and development.

The invention relates to the technical field of artificial intelligence application, and discloses an enzyme EC number prediction method, and the method comprises the steps: obtaining the sample sequence characteristics of a to-be-predicted sample containing a substrate SMILES sequence and a product SMILES sequence through a target BERT model; constructing a molecular object and feature coding based on atom mapping, atom truncation and sequence analysis, constructing a reaction graph of a to-be-predicted sample, inputting the reaction graph into a target graph isomorphic neural network, and constructing molecular graph features of the to-be-predicted sample based on a recursive neighborhood aggregation mechanism; and fusing the sample sequence features of the to-be-predicted sample with the molecular map features by using a bidirectional cross attention mechanism to obtain multi-modal features, inputting the multi-modal features into the multi-layer perceptron, and obtaining the prediction probability of the enzyme EC number of the to-be-predicted sample. According to the method, efficient and accurate end-to-end prediction of enzyme EC numbering is realized through the multi-dimensional chemical spatial characteristics of the collaborative modeling reaction.

The invention belongs to the technical field of green substitute design for chemical risk prevention and control, and discloses a deep learning method for designing a molecular structure of a chemical green substitute. On the basis of known chemical molecular structures and substitute target attributes, a green substitute molecular structure with synergistically optimized function and hazard attributes is obtained by applying the constructed method. The method is simple, convenient and efficient, resource investment of experimental testing can be saved, and regret replacement is prevented. The construction process of the method comprises the following steps: (1) generating a molecular structure of structural constraint based on a generative model; (2) realizing high-throughput prediction of multi-target attributes based on a decision-making model; and (3) realizing multi-target attribute collaborative optimization based on a Pareto optimization theory. The method established by the invention can effectively explore a wide chemical space, predict the multi-target attributes of the chemicals in a high-throughput manner, generate molecular structures with necessary functions and lower harmfulness, and provide a basic tool for green substitution of harmful chemicals.

The invention belongs to the technical field of computational toxicology oriented to chemical health risk evaluation and management, and discloses a chemical human carcinogenic toxicity parameter prediction method based on a dynamic weight multitask graph neural network. According to the method, on the basis of a dynamic weight multi-task graph neural network algorithm, a chemical human carcinogenic toxicity parameter multi-task prediction model assisted by in-vitro activity data is developed for the first time. The multi-task model constructed by the method has good prediction capability, the prediction accuracy is improved by 29%-105% compared with the prediction accuracy of an existing machine learning model, and the applicable chemical space of the model is expanded. The method can be used as a tool for efficiently predicting human carcinogenic toxicity parameters of the chemicals, and provides technical support for carcinogenic risk evaluation and management of the chemicals under multiple exposure approaches.

The invention provides a drug micromolecule multi-attribute optimization method combining deep learning and evolutionary computation, which comprises the following steps: S1, modeling a drug micromolecule multi-attribute optimization problem into a multi-objective optimization problem, and screening drug micromolecules meeting required characteristics from a DugBank database to obtain an initial molecular population; s2, fragmenting each drug small molecule of the molecular population, embedding the drug small molecule into a continuous submerged space, and carrying out molecular coding and marking; s3, determining the current optimal sparseness; s4, three different sub-populations are obtained; executing different mating pool selection strategies and offspring molecule generation strategies to obtain an offspring molecule set; s5, decoding the offspring molecular set back to a discrete chemical space, calculating an attribute value of the offspring molecular, mixing the parent molecular population with the offspring molecular population, and executing an environment selection strategy on the mixed population to obtain a next-generation molecular set; and S6, repeating the steps S2-S5 until a termination condition is met, and outputting an optimal molecular set. According to the method, the solving efficiency of the drug micromolecule multi-attribute optimization problem is ensured.

The application relates to the technical field of drug molecule design, in particular to a drug molecule directional generation method and system.The method comprises the following steps: firstly, a molecular representation base model is constructed, chemical space information of a drug molecule structure is transformed, updated, pooled and integrated, and a one-dimensional molecular code vector capable of reflecting molecular structure and pharmacodynamic attribute information is generated; a molecular structure generation model and a molecular attribute prediction model are constructed, and the one-dimensional molecular code vector is segmented for training, the former is subjected to dimension expansion, feature conversion and decoding to restore the vector into a drug molecule structural formula, and the latter predicts the molecular attribute; according to the molecular attribute prediction result, a new drug molecule structure with a target pharmacodynamic attribute can be directionally optimized and generated. Through accurate modeling of the distribution law of the drug chemical space, the drug research and development efficiency and success rate are effectively improved, and strong technical support is provided for the field.

Systems and methods for estimating a graph edit distance (GED) between compounds are provided. A first graph representing a first compound includes a plurality of nodes and a plurality of edges. An atom of the first compound is represented by the node of the first graph, and a bond of the first compound is represented by the edge of the first graph. A second graph representing a second compound also includes a plurality of nodes and a plurality of edges. Atoms of the second compound are represented by the nodes of the second graph, and bonds of the second compound are represented by edges of the second graph. The first graph is input into a model to generate a first potential embedding. The second graph is input into the model to generate a second potential embedding. An estimated value (GED) between the two compounds is determined from a difference between the two potential embeddings.

The present invention discloses a small drug molecule optimization method based on evolutionary computation and multi-granularity proxy model approximation, comprising: 1. modeling the multi-attribute optimization problem of small drug molecules as an expensive constrained multi-objective optimization problem; 2. uniformly generating an initial molecular population in a discrete chemical space and performing an expensive optimization target evaluation and constraint evaluation on the initial molecular population; 3. encoding the evaluated small drug molecules into a continuous latent space to obtain a continuous vector representation of the molecules; 4. using the continuous vector representation of the molecules, the corresponding target values ​​and the constraint values ​​as training data to train a multi-granularity proxy model; 5. executing a proxy model-assisted evolutionary algorithm to select high-quality small drug molecules for decoding into a discrete chemical space, and performing an expensive optimization target evaluation and constraint evaluation on the initial molecular population; 6. repeating steps 3-5 to output the optimal drug molecule. The present invention aims to efficiently optimize multiple attributes of small drug molecules using a relatively low evaluation cost, thereby providing technical support for drug research and development.

The invention discloses an artificial intelligence auxiliary drug generation method and device based on a molecular bond scaffold. The method comprises the following steps: acquiring a first bond scaffold of a first molecular map; inputting the first molecular map into an encoder, and removing molecular fragments of the first molecular map according to the first key bracket to obtain a potential space vector; predicting, by a decoder, a second key scaffold according to the submerged space vector; predicting key connection between the second key supports through a decoder; assembling the second bond scaffolds according to bond connection to obtain an intermediate molecular map; performing atom prediction on the intermediate molecular map through a decoder to obtain a target atom type; and obtaining a target molecule according to the intermediate molecular map and the target atom type. The method can expand the accessible chemical space of drug generation, and can be widely applied to the technical field of computer-aided drug generation.

The present application relates to the technical field of drug performance evaluation, and particularly relates to a drug performance evaluation method and system based on chemical space clustering, comprising: extracting structural features of known drug molecules in a calibration data set and calculating chemical space distance; adopting a density-aware clustering strategy to cluster the calibration data set, respectively performing statistical calibration in each chemical similarity cluster, and constructing a chemical space hierarchical calibration framework; adopting a graph neural network integrated model to predict the drug performance of a drug molecule to be tested, obtaining a prediction result and uncertainty estimation, determining the assignment weight of each chemical similarity cluster based on the structural features and the chemical space hierarchical calibration framework, and generating a confidence interval; according to the safety level corresponding to the drug performance to be evaluated, adjusting the sensitivity of the confidence interval, and outputting the prediction result and the confidence interval after reliability evaluation. The technical scheme of the present application provides reliable quantitative information with statistical basis for differentiated decision-making in early drug development.

This application is applicable to the field of compound analysis technology, and provides a method, apparatus, and terminal device for determining the chemical structure of a compound. The chemical structure determination method includes: determining the molecular formula of the compound to be determined and at least one adjacent mass spectrum based on the mass spectrum of the compound to be determined, each adjacent mass spectrum corresponding to a neighboring compound; determining at least one candidate compound based on the molecular formula; and determining the chemical structure of the compound to be determined based on the spatial distance between each candidate compound and each neighboring compound in the chemical space. Through the above scheme, the problem of the inability to perform structural analysis on compounds not included in the database in the prior art and the small analysis coverage is solved.

The present disclosure provides methods and systems for optimizing chemical reactions through machine learning. A chemical space is defined by grouping potential chemicals based on selected features. Representative chemicals are selected from each group and test kits are assembled. The test kits are then used to identify optimal catalysts or ligands for the catalyzed chemical reaction. In some embodiments, the system can recommend test kits, receive results from experiments, generate distance matrices, and rank potential chemicals based on scores obtained for the representative chemicals. These methods include reducing the dimensionality of chemical features and normalizing distances. The disclosed embodiments can suggest potential chemicals for optimizing chemical reactions by classifying chemicals based on scores obtained from the representative chemicals.

This application designs an artificial intelligence-based molecular characterization and soft sub-scaffold-constrained drug discovery system, comprising: a data collection module, a sub-scaffold analysis module, a 3D simulated molecular docking module, a Bayesian ridge regressor training module, a VAE generative model pre-training module, a reinforcement learning module, and a sampling evaluation module. By using sub-scaffold analysis and 3D simulated molecular docking information, this application can better understand and utilize the complexity and diversity of chemical space. Furthermore, by using a Bayesian ridge regressor and a VAE generative model, this application can generate novel, rationally structured, and potentially active drug molecules. Therefore, this artificial intelligence-based molecular characterization and soft sub-scaffold-constrained drug discovery system, by combining deep learning technology, cheminformatics, drug design, and computer-aided drug design methods, can significantly improve the efficiency and success rate of drug discovery.

This invention discloses a high-throughput experimental sequence adaptive planning method based on Bayesian optimization, relating to the field of chemical experiment automation technology. The method includes: digitally encoding multiple chemical variables involved in the experiment to construct a multi-dimensional chemical space to be searched; constructing a probabilistic prediction surrogate model based on known experimental samples; pre-setting the acquisition cost of each variable and establishing a cost function; combining the expected improvement amount and the cost function, calculating the next batch of candidate experimental points through a target optimization algorithm, prioritizing the experimental points with the largest unit cost gain; converting the candidate coordinates into instructions and sending them to the automated experimental platform, and updating the surrogate model with the returned experimental data in real time, repeating the process until convergence to the global optimum or reaching the cost ceiling. This invention, by introducing a cost-sensitive acquisition function and a heterogeneous molecular fingerprint fusion strategy, achieves synergistic optimization of experimental results and experimental costs, significantly improving the efficiency and resource utilization of high-throughput experiments.

This invention discloses an environmentally friendly insulating gas molecule and its high-throughput design method and related apparatus, belonging to the field of novel environmentally friendly insulating gas molecule design technology. By establishing a dedicated database containing microscopic discharge parameters and macroscopic physical property parameters of insulating gas molecules, a gas molecule performance evaluation and prediction model is constructed using this database. A molecular structure gene scoring system is established, dominant genes are extracted and recombinated, and chemical space for high-throughput screening is increased by adding groups to the backbone. The performance evaluation and prediction model is used to perform high-throughput screening on a massive number of molecules in an open-source database and molecules generated by adding groups to the backbone. Based on the target property range, a novel environmentally friendly insulating gas molecule is finally obtained. This invention can quickly and accurately evaluate and predict the performance of gases, improve high-throughput screening capabilities, save significant manpower, material resources, and time, and ultimately obtain a novel environmentally friendly insulating gas molecule.

This invention relates to the field of drug performance evaluation technology, and more particularly to a drug performance evaluation method and system based on chemical spatial clustering. The method includes: extracting structural features of known drug molecules from a calibration dataset and calculating chemical spatial distances; clustering the calibration dataset using a density-aware clustering strategy, performing statistical calibration within each chemical similarity cluster, and constructing a chemical spatial hierarchical calibration framework; using a graph neural network ensemble model to predict the drug performance of the drug molecule under test, obtaining prediction results and uncertainty estimates, determining the weights of each chemical similarity cluster based on structural features and the chemical spatial hierarchical calibration framework, and generating confidence intervals; adjusting the sensitivity of the confidence intervals according to the safety level corresponding to the drug performance under test, and outputting the prediction results and confidence intervals after a credibility assessment. This invention provides statistically reliable quantitative information for differentiated decision-making in early-stage drug development.

The invention belongs to the field of computational chemistry, and discloses a polyimide performance optimization method and system based on RNN-MCTS-xTB. According to the polyimide performance optimization method and system based on RNN-MCTS-xTB, a generated, evaluated and optimized closed-loop system is constructed through a linkage mechanism of an RNN model, an MCTS model and an xTB program, so that molecular design is high in efficiency, and a specific performance optimization decision can be made according to electronic structure information. According to the method, the convergence capability to the target performance can be maintained while the chemical space exploration range is maximized, the problem that a traditional method is difficult to achieve balance between high-throughput search and physical property accuracy is fundamentally solved, and a reliable means is provided for automatic and intelligent design of high-performance polyimide molecules.

The invention belongs to the field of construction of DEL libraries, and particularly relates to a method for preparing an On-DNA 2-hydroxydithiocarbamate structure compound. Comprising the step of reacting On-DNA secondary amine with carbon disulfide and an epoxy compound at a certain temperature and under a solvent condition to generate an On-DNA 2-hydroxydithiocarbamate structure compound. According to the preparation method disclosed by the invention, tens of thousands of compounds with On-DNA dithiocarbamate structures can be rapidly synthesized, the chemical space of On-DNA is enriched, and the diversity of On-DNA compounds is increased. In the field of new drug research and development, the high-throughput screening hit rate of biological targets can be improved, and the discovery efficiency and possibility of lead compounds are remarkably improved.

DrugGPT is an innovative ligand design strategy based on the autoregressive model GPT (Generative Pre-trained Transformer), specifically optimized for exploring chemical space and discovering ligands for target proteins. The model was trained from scratch using a large dataset of protein-ligand binding pairs, enabling it to learn the structural and chemical rules of drug molecules and their interactions with proteins. We selected PI3Kα as an important anti-cancer drug target to demonstrate the ability of DrugGPT in exploring potential anti-cancer ligands. The present invention provides a novel class of PI3Kα inhibitors that exhibit exceptional therapeutic potential for the treatment, prevention, and management of a wide range of diseases and conditions associated with aberrant PI3Kα activity. These compounds are particularly promising for use in oncology, metabolic disorders, inflammatory diseases, and other conditions where PI3Kα signaling plays a critical role.

The advent of ultra-large libraries of drug-like compounds has significantly broadened the possibilities in structure-based virtual screening, accelerating the discovery and optimization of high-quality lead chemotypes for diverse clinical targets. We explored new chemical spaces using reactions of sulfur(VI) fluorides to create a combinatorial library consisting of several hundred million compounds. We screened this virtual library for Cannabinoid Type II receptor (CB2) antagonists in conjunction with a rationally designed antagonist, AM10257. The top-predicted compounds were then synthesized and tested in vitro for CB2 binding and functional antagonism, achieving an experimentally validated hit rate of 55%. Our findings demonstrate the effectiveness of reliable reactions, such as Sulfur Fluoride Exchange (SuFEx) reactions, for diversifying ultra-large chemical spaces and facilitating the discovery of new lead compounds for important biological targets.

The invention discloses a large language model-based generative chemical space virtual screening method, and belongs to the technical field of generative chemical space virtual screening, and the technical key points are that the method comprises the following steps: determining a screened target protein; acquiring the real binding affinity of the molecules; training a proxy model based on a graph neural network according to the real binding affinity data to predict an affinity value; selecting a batch of molecules from the current set as a reference for the generator; the generator generates a batch of new molecules around the reference object in a prompt project mode; predicting the binding affinity of the molecules by using a graph neural network agent model; selecting a batch of molecules according to the predicted value; acquiring the real binding affinity of the molecules; generating a new batch of molecules using a generator reference; the method has the advantages that the defect that an existing method cannot escape from a predefined compound library is overcome, and the virtual screening direction cannot be guided through real-time feedback.

A machine learning system includes a processor and a memory communicably coupled to the processor. The memory stores machine-readable instructions that, when executed by the processor, cause the processor to select a training dataset comprising training material compositions and tagged material property values, select at least two material property datasets comprising material compositions with corresponding material property values, and embed the training material compositions and the material compositions of the at least two material property datasets into a chemical space of a machine learning module. The memory also stores machine-readable instructions that, when executed by the processor, cause the processor to predict, based at least in part on the training material compositions and the material compositions of the at least two material property datasets embedded in the chemical space, property values for corresponding material compositions in the at least two material property datasets.

An information processing apparatus includes a processor, in which the processor is configured to generate a display image in which marks indicating a compound group including a target compound, which is a compound to be subjected to an toxicity evaluation, and a plurality of reference compounds, which are compounds to be compared with the target compound, are mapped onto a chemical space in which a plurality of feature amounts related to a molecular structure of a compound are set as coordinate axes, in which the marks are displayed such that a result of the toxicity evaluation for each of the compounds is distinguishable, and execute control of outputting the generated display image.

The invention discloses a multi-mechanism molecular gel inducibility prediction method, relates to the technical field of computer-aided drug design, and discloses a multi-mechanism molecular gel inducibility prediction method which combines multi-modal features such as a one-dimensional sequence, a two-dimensional graph structure and a three-dimensional structure of a coding small molecule and two types of proteins to predict the inducibility of the multi-mechanism molecular gel. A three-element cross-entity feature interaction mechanism is introduced, unified prediction of the inducibility of the ternary complex under different E3, substrates and chemical space backgrounds is realized, prediction requirements under different E3, different substrates and diversified chemical space backgrounds can be met, the influence of the conformational collaboration of the ternary complex on the inducibility is comprehensively captured, and the method has the advantages of being high in adaptability and high in practicability. And the prediction efficiency and applicability of the molecular glue are improved.

The application discloses an energetic material design method and system based on multi-target property coupling, and the disclosed scheme comprises the following steps: a multi-target property prediction model and a conditional molecule generation model are constructed based on multi-target performance data; then, a molecule population is initialized, and molecule discovery is carried out through cyclic iteration; in each generation, the conditional molecule generation model is used to generate new candidate molecules by taking the performance of excellent individuals in the current population as a guide condition; then, the multi-task property prediction model is used to quickly evaluate the performance of the new molecules; through multiple iterations, a series of potential high-performance energetic materials reaching the Pareto optimality on multiple performance targets are generated. The application solves the problems of low exploration efficiency and high cost of the traditional trial-and-error method in a wide energetic material chemical space.

The invention discloses ionizable lipid as well as a design method and related application thereof, and relates to the technical field of nucleic acid delivery. The embodiment of the invention innovatively constructs a design method of ionizable lipid, and the method can efficiently explore chemical space, generate novel ionizable lipid molecules with excellent performance, greatly improve the development efficiency and success rate of ionized lipid, and provide a new way for optimization of a nucleic acid drug delivery system.

The application discloses a kind of oil molecule generation method and system based on module fusion and random disturbance, belong to oil molecule model construction technical field, this method is by inputting target parameter to improved random assembly function module, obtains the structured representation of candidate molecule;Wherein the improvement point is in: when determining module quantity, structure parameter and the preference weight of various molecular modules, introduce parameter disturbance and the multiple disturbance mechanism of weight dithering;In the module assembly control process, when starting core module selection, introduce giant nucleus priority strategy, when each module combination connection, introduce the dual-mode connection strategy of single-point covalent connection and multi-point fusion connection.The multiple disturbance mechanism of the application method expands the chemical space coverage of candidate molecule pool, through multi-point fusion connection mechanism, can directly simulate the polycyclic aromatic hydrocarbon condensation phenomenon generally existing in oil, especially heavy component.

The invention belongs to the field of organic synthetic chemistry, and particularly relates to a preparation method of an o-methoxybenzoic acid derivative, which comprises the following steps: carrying out ortho-position C-H bond methoxylation reaction on a compound 1 and methanol in the presence of a palladium catalyst, an oxidizing agent and alkali to generate the target product o-methoxybenzoic acid derivative in one step. Compared with the traditional synthesis method of the o-methoxybenzoic acid derivative, the innovative method has the advantages of short synthesis route, relatively mild conditions, wide substrate range and the like. And meanwhile, the used guiding group can be subjected to subsequent conversion, so that a molecular editing site is provided for subsequent derivatization reaction, and the chemical space of modular construction of drug molecules is greatly expanded.