474 results about "Molecular geometry" patented technology

The invention discloses a multi-agent cooperation molecular optimization method based on large language model driving. The method comprises the following steps: S1, task initialization and input analysis; s2, constructing an intelligent agent cluster; s3, task decomposition and scheduling execution; s4, performing expert optimization and tool calling; s5, performing evaluation and feedback screening; and S6, multi-round optimization and result output: the scheduling agent adjusts an optimization strategy and redistributes tasks according to a feedback result of the step S5, drives the expert agent to execute a next round of optimization operation, circulates the steps until the evaluation agent judges that an optimization target is met, and outputs a final optimization molecule and related attribute information thereof. And outputting an optimized path and an intermediate result for tracing analysis. According to the method, multi-round optimization and evaluation feedback iteration of a molecular structure are realized by fusing the knowledge reasoning ability of a large language model and an efficient interaction mechanism between intelligent agents.

The invention relates to the technical field of computer-aided drug design, in particular to a drug molecule screening and optimizing method based on artificial intelligence prediction, which comprises the following steps: S1, obtaining a dynamic protein conformation set and molecular multi-dimensional characterization: obtaining a dynamic conformation set of a target protein and a physicochemical property spatial distribution diagram of a binding pocket of the dynamic conformation set, a two-dimensional molecular map topological structure and three-dimensional conformation coordinates of the drug molecules are obtained; s2, multi-modal fusion prediction is carried out; s3, generating interpretable optimization guidance; and S4, automatic iterative optimization: performing batch prediction and screening on the new candidate molecular structure, taking the screened optimal molecule as a new starting point, repeatedly executing the interpretability optimization guidance generation step and the step until an iteration termination condition is met, and outputting a final optimized molecule list. Through the multi-modal fusion deep learning model, the interaction strength of the drug molecules and the target protein can be quickly and accurately predicted, and the screening efficiency of the drug molecules is greatly improved.

The invention relates to an inverse synthesis route planning method and system based on a multi-modal large model, and belongs to the technical field of chemical synthesis and artificial intelligence crossing. The method comprises the following specific steps: firstly, extracting three-dimensional molecular structure characteristics of a target product through a molecular encoder, and aligning the three-dimensional molecular structure characteristics with text modals of molecules; secondly, reasoning a possible reaction mechanism and a reaction type, and reducing an inverse synthesis search space; secondly, splitting a target product into reasonable synthesis subunits through structured marking and vocabulary expansion, data-driven atomic assignment learning and reaction center recognition and activity prediction; finally, SMILES representations and reaction paths of the reactants are generated. According to the method, the accuracy and interpretability of inverse synthesis path planning can be improved, and a new technical means is provided for automation and intellectualization in the fields of new drug development, material design and the like.

The embodiment of the invention relates to a method and a device for predicting optical energy characteristics of organic photovoltaic material molecules. The method comprises the following steps: constructing an optical energy characteristic prediction model for predicting ionization energy, emission energy and absorption energy according to a molecular structure, temperature, pressure intensity and wavelength sequence input by the model; constructing a first data set through data acquisition; training an optical energy characteristic prediction model based on the first data set; after the training is finished, the training is finished; a first molecular structure, a first temperature, a first pressure and a first wavelength sequence input by a user are used as a corresponding molecular structure M, a temperature x, a pressure y and a wavelength sequence Z to be input into an optical energy characteristic prediction model for processing, and ionization energy uIE, an emission energy sequence SEE and an absorption energy sequence SAE which are processed and output by the model are used as corresponding first ionization energy; the first emission energy sequence and the first absorption energy sequence are fed back to the current user. According to the invention, the prediction efficiency can be improved.

The invention relates to a generative molecule reverse design system based on reinforcement learning, which comprises a data set construction module, a multi-target performance prediction model establishment module, a pre-training module, a reward function construction module and an optimization module, and is characterized in that the data set construction module is used for constructing and screening to obtain a molecular structure performance data set; the multi-target performance prediction model establishment module is used for establishing a multi-target performance prediction model based on the constructed molecular structure performance data set; the pre-training module is used for pre-training a molecular generation model by using the screened molecular structure data; the reward function construction module is used for constructing a layered multi-target reward function; and the optimization module is used for rapidly evaluating key indexes by using a performance prediction model by adopting a reinforcement learning method, and carrying out optimization adjustment on the molecular generation model through a layered multi-target reward function. According to the invention, efficient and systematic reverse design of lithium metal negative electrode interface self-assembly molecules can be realized.

A system and method are provided for a machine-learning drive framework for predicting ionic conductivity of solid-state electrolytes. In use, the method and / or system may include receiving, at a machine learning system, two or more molecular structures from at least one structural dataset, where the two or more molecular structures relate to ionic mobility. Additionally, atomic weights are calculated for the two or more molecular structures, and the machine learning system is trained based on the two or more molecular structures, where the training relies on at least one intrinsic atomic feature and the calculated atomic weights for the two or more molecular structures. Further, a bias-correction is applied for the two or more molecular structures to improve the training of the machine learning system. Further, one or more molecular dynamics (MD) simulations are outputted, using the machine learning system, for the two or more molecular structures.

The embodiment of the invention relates to a processing method and device for carrying out structure optimization on electrolyte formula components. The method comprises the following steps: constructing a structure optimization model; constructing a first data set and a second data set; performing pre-training based on the first data set, and performing tuning based on the second data set; after the optimization is finished, taking an electrolyte formula input by a user as a current electrolyte formula, performing corresponding three-dimensional molecular structure modeling according to each component molecular sequence of the current electrolyte formula, and performing three-dimensional structure optimization on each component modeling structure based on a structure optimization model; forming a corresponding formula component structure optimization record by each component molecular sequence, the corresponding component type and the component optimization structure; and forming a corresponding formula structure optimization report by all the obtained formula component structure optimization records, and feeding back the report to a user. According to the method, the influence of human factors on the molecular structure modeling quality can be reduced, and the modeling quality and the modeling efficiency are improved.

The invention discloses a molecular property prediction method and device based on a graph neural network and a large language model, and the method comprises the steps: obtaining a molecular structure graph according to the SMILES of a molecule, and the molecular structure graph comprises the structural information of atoms and functional groups; generating a description text of each functional group by using the fine-tuned large language model, and encoding the description text by using a text encoder to obtain text information of each functional group; adding text nodes and feature information in the molecular structure diagram, and adding edges between the text nodes and corresponding functional groups to obtain a final edition molecular structure diagram; and inputting the final edition molecular structure diagram into the trained molecular property predictor to obtain a prediction result of the molecular property. According to the method, structural information and text information of atoms and functional groups in molecules are fully considered, and then the information is learned by using the message passing neural network, so that molecular property prediction is more accurate, and the accuracy of molecular property prediction is improved.

A system and method for modeling one or more characteristics of a molecule using a quantum device implemented on quantum hardware is disclosed. Through control, via modulation, of coupling strengths between qubits on the quantum device and a comparison to an experimentally-measured nuclear magnetic resonance spectrum, J-coupling values may be deduced. These J-coupling values may then be used to recover the molecular structure of the given molecule. The control of coupling strengths may take place through an iterative process until convergence to the one or more characteristics is reached. In some embodiments, such a process may be implemented as part of a quantum computing service. In such cases, the quantum hardware may be local to the quantum computing service, or may be outsourced to a quantum hardware provider.

The invention discloses a spectrum and molecular structure comparison matching system based on machine learning, and relates to the field of spectrum intelligent analysis, and the system comprises a model construction module, a training optimization module, a calculation candidate module, and an interpretation visualization module. According to the method, the deep semantic features of the spectrum and the structure are automatically extracted by constructing the multi-modal deep learning model, and the accuracy and robustness of spectrum analysis and molecular structure matching are greatly improved. A shared embedding space learning strategy is adopted, different modes are projected to the same feature space, and unified matching and similarity scoring are achieved. An attention mechanism is introduced, visual mapping between spectrum peaks and molecular structure fragments is achieved, understanding of corresponding chemical groups or atoms behind each spectrum peak is facilitated, and interpretability of a matching result is enhanced.

The invention relates to the technical field of molecular simulation, and provides a method for constructing a heavy component average molecular structure of thickened oil, which comprises the following steps: inputting parameters, generating a core aromatic ring unit, constructing an inner-layer aliphatic ring unit, constructing an outer-layer aliphatic ring unit, generating a side chain unit, and storing and outputting structural information. A plurality of molecular structures meeting experimental data are generated at a time through a traversal algorithm thought, composition characteristics of a heavy oil complex mixture are met, more available molecular structures are provided for molecular simulation, the accuracy and efficiency of molecular modeling are improved, the molecular structures completely meeting the experimental data can be rapidly generated, and the method is suitable for large-scale popularization and application. And only the mass spectrometer, the elemental analyzer, the nuclear magnetic resonance hydrogen spectrum and the infrared spectrum data need to be input, so that the experiment cost is reduced.

The invention provides a simulation calculation method for the electron blocking capability of a complex compound, which comprises the following steps: S1, according to the molecular composition of a compound target material, simulating and constructing a microscopic all-atomic molecular structure of the target material by using a computer; s2, randomly generating more than ten thousands of ion movement tracks, and counting a distribution function group of closest distances between the ions and various atoms in the target material when the ions pass through the target material; s3, 10-100 short tracks capable of enabling the comprehensive overlap index to reach 95% or above are screened out from the ion movement tracks; and S4, simulating the process that the ions pass through the target material along the selected trajectories by using a time-dependent density functional method, wherein the ratio of the sum of energy changes of each simulation system to the sum of the lengths of the ion trajectories is the electron blocking capability of the compound on the ions. According to the scheme provided by the invention, the electron blocking capability of a complex compound on ions can be quickly and accurately calculated, and complex and high-cost experimental measurement is avoided. Wherein the calculation cost is reduced to 10% of the calculation cost of the random incidence method through the screening track method.

A method and apparatus with organic molecule spectrum prediction are disclosed. The method includes accessing a molecular structure representation of an organic molecule; generating parameters of an approximated Franck-Condon progression by inputting the molecular structure representation to a neural network model that infers the parameters from the molecular structure representation; and generating a spectrum of the organic molecule based on the generated parameters.

The invention discloses an alloy high-temperature and high-pressure environment simulation method under radiation action based on molecular dynamics, which comprises the following steps: establishing a molecular structure framework of an alloy according to a crystal structure and a lattice constant of the alloy, and setting initial parameters to construct an initial simulation model; performing relaxation operation on the molecular structure model in a high-temperature and high-pressure environment; performing irradiation damage simulation on the relaxed model based on molecular dynamics, selecting a central atom as a primary off-site atom, and setting incident energy and incident direction of the primary off-site atom to simulate atom cascade collision; keeping the incident direction unchanged, and adjusting the incident energy of the primary off-site atoms to obtain defect distribution and defect density under different energies; and analyzing the defect evolution law of the alloy in the high-temperature and high-pressure environment according to the simulation result. According to the method, the alloy material is observed from a microscopic atomic scale, so that a powerful support is provided for simulating a defect evolution process in a high-temperature and high-pressure environment and reflecting atomic collision of the alloy in a real radiation environment.

The invention discloses a three-dimensional molecule generation method fusing conditional flow matching and Van der Waals radius constraint, which comprises the following steps: processing a molecule training data set, and extracting a total number of atoms and a training element component histogram; based on the optimal transmission path interpolation, combining the sampling time step and the standard Gaussian noise to construct a noise coordinate and a target condition velocity field; the noise coordinates are input into a continuous flow matching prediction model, node features are extracted through affine transformation modulation, a prediction velocity field is obtained, soft atom type distribution is generated, and the expected Van der Waals radius of each atom type is calculated; calculating flow matching loss through a prediction velocity field and a target condition velocity field, calculating a geometric collision penalty term in combination with an expected Van der Waals radius and a noise coordinate, and constructing a total loss function training model parameter; and defining an ordinary differential equation by using the trained parameters for solving, and outputting a three-dimensional molecular structure file. According to the method, atom space overlapping is inhibited, and the physical rationality and chemical effectiveness of generated molecules are improved.

Systems and methods for determining a molecular structure include obtaining mass spectrum data for an unknown parent ion. The mass spectrum data is recorded at each collision energy of a series of collision energies and includes an abundance of one or more substructures of the unknown parent ion. The molecular structure of the unknown parent ion is determined by composing the mass spectrum data into a fragmentation profile and embedding the fragmentation profile into a reduced dimension profile. The reduced dimension profile is mapped into a fragmentation space. One or more proximate molecules in the fragmentation space are identified using the mapping and a candidate for the parent ion is identified using the one or more proximate molecules.

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 embodiment of the invention relates to a processing method and device of an organic molecule maximum absorption peak prediction model. The method comprises the following steps: constructing a maximum absorption peak prediction model for predicting the maximum absorbance and the maximum absorption wavelength of a maximum absorption peak according to a molecular structure, environment temperature, environment illumination intensity and an environment PH value input by the model by taking an MLP model and a Un i-Mo < l > model as a core component, wherein the maximum absorption peak prediction model is used for predicting the maximum absorbance and the maximum absorption wavelength of the maximum absorption peak according to the molecular structure, the environment temperature, the environment illumination intensity and the environment PH value input by the model; constructing a first data set through data acquisition, and training a maximum absorption peak prediction model based on the first data set; and after the model training is finished, receiving a first molecular structure and a first environment parameter set input by the user, and predicting the maximum absorption peak information of the first molecular structure under all first environment parameters by using the maximum absorption peak prediction model to obtain a corresponding first prediction vector set to be fed back to the current user. According to the method, the task processing real-time performance of the maximum absorption peak recognition task can be improved, and the personalized prediction level can be improved.

The embodiment of the invention provides a drug structure-activity relationship analysis method and device based on a multi-level structure, and the method comprises the steps: carrying out the multi-level molecular structure characterization of a compound, the multi-level molecular structure comprises a clustering structure, an original structure and a fragment structure; calculating the weights of the clustering structure, the original structure and the fragment structure based on the research and development state of the compound; and determining an activity relationship between the compound and the target, and calculating a target association credibility score based on the activity relationship, the evidence supporting the activity relationship and the research and development state weight of the compound.

The invention discloses an additive molecule screening design method for optimizing the performance of ester-based insulating oil, and relates to the technical field of electrical insulating materials. The invention provides an additive molecule design method combined with a deep molecule generation model, aiming at solving the problems that the breakdown voltage performance is insufficient due to the fact that ester-based insulating oil is easy to generate rapid streamer under high-strength lightning impulse, and time and labor are consumed when an appropriate additive is found through an experiment. The method comprises the following steps: acquiring molecular data with target electronic attributes; taking the fragment of the molecular structure as the input of the model, and designing a new additive molecular structure by utilizing the molecular generation model; performing molecular screening according to target characteristics; and the performance of the screened molecules is verified through streamer discharge simulation. According to the method, generative design of ester-based insulating oil additive molecules is realized by using the deep autoregressive neural network, the molecular screening efficiency is remarkably improved, and a new technical route is provided for improving the breakdown voltage performance of the ester-based insulating oil.

Disclosed herein are methods and systems that acquire mass spectrum peak data for fragment ions from a mass spectrum of fragment ions generated in an LC-MS / MS measurement instrument, acquire molecular structure and fragment ion map data for fragment ions by using the acquired data, and determine fragment ion map data for fragment ions. And a candidate molecular structure of the target substance is obtained by assembling the fragment ion diagram.

The invention discloses a method and device for predicting the transmembrane capability of a substance molecule, terminal equipment and a storage medium, and the method comprises the steps: obtaining a target molecular substance, and determining a molecular structure diagram corresponding to the target molecular substance; according to a pre-trained prediction model, determining a permeation free energy prediction value of the target molecular substance; according to the prediction model, multilevel feature extraction is carried out on a molecular structure diagram of sample substance molecules by utilizing a graph neural network model, contribution values of atoms in the sample substance molecules to transmembrane behaviors are evaluated through a gradient weighted class activation mapping method, and permeation free energy prediction values corresponding to the sample substance molecules are output. The graph neural network is trained to obtain the prediction model, and the prediction model is adopted to predict the transmembrane capability of the target molecular substance, so that intelligent screening of the transmembrane capability of a large-scale drug molecular library can be realized, the prediction efficiency and flux are remarkably improved, and intelligent prediction of the transmembrane free energy of substance small molecules is realized.

The invention discloses a multi-target drug molecule generation model construction method and a multi-target drug design method, and relates to computer drug design and bioinformatics. Determining a corresponding two-dimensional molecular map based on the SMILES sequence; the fully-connected pharmacophore diagram and the two-dimensional molecular diagram are used as input of a GatedGCN module, each atomic node in the two-dimensional molecular diagram is connected with all pharmacophore nodes in the fully-connected pharmacophore diagram in message transmission, and information exchange between different nodes is achieved; the masked SMILES sequence serves as the input of an encoder, and the decoder generates an SMILES sequence conforming to pharmacophore characteristics in an autoregression mode; freezing the network parameters of the GatedGCN module and the encoder; and training the multi-target drug molecule generation model through the elite multi-target molecule set, and reversely optimizing and updating decoder network parameters according to an output result. According to the method, the model fully learns the multi-target molecular structure characteristics, and the multi-target drug molecule generation accuracy is improved.

The invention discloses an ultra-low interfacial tension surfactant screening method and system based on AI4S, and relates to the technical field of oil and gas exploitation. The method comprises the following steps: constructing a database covering molecular structures of typical surfactants; constructing a prediction model for predicting the surface tension; generating candidate molecules by using a generative artificial intelligence model comprising a variational auto-encoder and a generative adversarial network; inputting the candidate molecules and the experimental conditions into the trained prediction model to predict the interfacial tension of the prediction model under the target condition, and screening the candidate molecules with the predicted performance reaching the standard; and performing experimental determination on the screened candidate molecules until molecules with target performance are obtained, and feeding back experimental results to a database to form closed-loop optimization of data, prediction and experiments. The research and development efficiency and success rate of the chemical oil-displacing agent can be remarkably improved, the research and development period is shortened, the research and development cost is reduced, and effective technical support is provided for improving the oil and gas recovery efficiency and guaranteeing energy safety.

The invention discloses a biomass pyrolytic reaction network prediction method based on a graph theory and quantum chemistry, which comprises the following steps: analyzing the molecular structure of a biomass initial reactant, abstracting the molecular structure into a directed graph molecular model, marking a potential conversion path after molecular mechanics optimization, generating a unique identifier by using an atom numbering rule and a Hash algorithm, and predicting the biomass pyrolytic reaction network. Functional groups are extracted and packaged into sub-graph modules, chemical bond parameters are obtained in combination with quantum chemistry calculation and are converted into fracture probabilities, basic reaction building blocks are predefined to traverse and mark breakable bonds, fragments are recombined and then de-weighted through Hash, and then reaction activation energy weights are given to side chemical bond fracture reactions; an energy optimal path is screened by means of a priority queue search algorithm, accurate analysis of a chemical bond fracture path and intermediate product conversion in the biomass pyrolysis reaction network is finally achieved, reaction path and product distribution are efficiently predicted, and the calculation efficiency and precision of a complex system are balanced.

The training method of the molecular characterization information generation model comprises the following steps: acquiring first molecular information of a target molecule; performing diffusion processing to obtain second molecular information; determining real trajectory information of the target molecule; taking the second molecular information as input of a target neural network model, and outputting molecular characterization information; according to the molecular characterization information, track information is really simulated; determining a first loss value according to the difference between the real trajectory information and the simulated trajectory information; determining first comparison information and second comparison information according to the molecular characterization information; performing comparative learning by taking the first comparison information as a positive sample and the second comparison information as a negative sample, and determining a second loss value; and performing iterative training according to the first loss value and the second loss value to obtain a molecular characterization information generation model. In the training process, the comparison change of the molecular motion trail and the molecular structures at different moments is considered, so that the molecular characterization information has rich molecular information and can be used for various downstream tasks.

An autoencoding device for a synthesizable molecule generative model may include a memory configured to store chemical reaction data, chemical reaction learning information, and molecular structure information; and a processor configured to learn a neural network for a molecular generative model based on the chemical reaction data, the chemical reaction learning information, and the molecular structural information. The molecular generative model may include: a reaction sequence encoder configured to generate a latent space based on the chemical reaction learning information; a seed molecule encoder configured to generate an embedding space based on seed structural information for a seed molecule that is a final product of chemical reaction; and a decoder configured to output a reconstruction reaction sequence by decoding a reaction molecule predictive neural network and a reaction template prediction model generated from the latent space and the embedding space.

The invention discloses a method and system for determining the reaction activity of material molecules based on quantum computing, and relates to the technical field of material performance analysis based on quantum computing, and the method comprises the following steps: generating a secondary quantization molecular Hamiltonian based on a target material molecular structure; traversing non-zero coefficient excitation terms in the molecular Hamiltonian, and screening an excitation operator conforming to the symmetry of a molecular point group as a target excitation operator; generating symmetric unitary coupling cluster single-double excitation simulation according to the target excitation operator; constructing a quantum circuit based on the configuration; and determining the reaction activity of the target material molecule by using the quantum circuit. According to the method, traditional manual symmetry analysis is avoided, professional knowledge is not needed, and the operation process is simplified. The method is systematized, easy to program and implement, high in universality and capable of being automatically expanded to any molecule, the design cost is remarkably reduced, and the molecular energy level solving efficiency is improved.

The invention discloses a multi-mode chemical reaction yield prediction method based on adaptive data screening, and belongs to the technical field of chemical synthesis and machine learning crossing. According to the method, a multi-modal input system containing one-dimensional chemical attribute data, a two-dimensional molecular structure map and a three-dimensional spatial configuration is constructed, so that multi-dimensional analysis of molecular interaction is realized; and meanwhile, a multi-stage training process is adopted to simulate a human cognitive rule, so that the model progressively learns layer by layer from a basic reaction feature to a complex reaction mechanism. According to the method, the screening threshold is dynamically adjusted, noise interference is effectively suppressed, and the adaptability to long-tail distribution data is improved. Compared with a traditional single-mode prediction model, the method has the advantages that the prediction accuracy on a noisy data set is improved, the trial and error cost of chemical synthesis experiments is remarkably reduced, and reliable technical support is provided for efficiently screening reaction conditions and accelerating research and development of new compounds.

This invention relates to a method and apparatus for predicting molecular properties by integrating three-dimensional structure and prior features. The method includes: identifying a set of predicted properties and a set of prior properties; constructing a molecular property prediction model based on the predicted and prior property sets; constructing a model training dataset and training the molecular property prediction model based on the dataset; after model training, receiving first molecular information input by the user, preparing model input data based on the first molecular information and the prior property set, and inputting the three-dimensional molecular structure M and prior characteristic vector X obtained from this data preparation into the molecular property prediction model to predict the corresponding property prediction vector Y, which is then fed back to the current user. This invention can reduce prediction complexity, shorten prediction time, and improve prediction efficiency.