19 results about "Molecular property" patented technology

A foundation model for performing molecular-level tasks by learning multimodal data in the form of one-dimensional text and two-dimensional graphs, and a system therefor, according to an embodiment of the present invention, enable various molecular-unit tasks such as chemical reaction prediction, molecular attribute prediction, and natural language description generation to be effectively processed through a single foundation model. In addition, it is possible to increase prediction accuracy of the model by maximizing utilization of two-dimensional molecular graph information, and automatically generate, on the basis of statistical sparsity, high-quality descriptive text that emphasizes core and distinctive features of each molecule.

The application discloses a molecular property prediction method based on spectral position coding and bionic side inhibition gating, and relates to the field of olfactory perception. The method comprises the following steps: constructing a molecular structured input comprising atomic types, a Coulomb matrix and graph Laplacian eigenvector; fusing atomic chemical attributes and spectral domain topological positions through a feature extraction module to generate initial atomic features; using a multi-scale aggregation module, hierarchical neighborhood aggregation is carried out based on preset scale constraints to extract multi-level structure features covering chemical bonds, functional groups and molecular skeletons; with the help of a global interaction module of bionic side inhibition gating, local features are dynamically modulated by a global query signal to realize adaptive denoising and semantic sharpening; finally, through mask pooling and a decoupled multi-label prediction head, the scores of each odor attribute of the molecule are output. The application significantly improves the accuracy, structure perception ability and cross-task generalization performance of molecular property prediction.

The application relates to the technical field of electric digital data processing, and discloses a molecular design constraint condition generation method, system, device and medium based on an interpretable artificial intelligence, which comprises the following steps: acquiring molecular structure data marked with active / inactive labels, and extracting molecular property features and / or molecular fingerprint structure features; training a molecular activity prediction model by using a machine learning algorithm; applying the model to a to-be-tested molecule, analyzing a prediction result by using interpretability analysis, and generating a molecular design constraint condition. The application can convert the prediction result of the artificial intelligence model into specific and executable molecular design guidance, and breaks through the limitation that a traditional model can only output "whether active" but cannot explain "why active" and "how to design". The application can be flexibly adapted to various molecular feature input modes, can provide the most comprehensive design prompt, significantly reduces the dependence on expert experience, and improves the efficiency and success rate of molecular design.

The application discloses a molecular odor prediction method based on cross-modal attention fusion, relates to the fields of chemical informatics and deep learning, and comprises the following steps: acquiring a molecular dataset, extracting basic molecular property features, molecular fingerprint features and SMILES sequence features for each molecule in parallel, performing molecular odor prediction model training, wherein the molecular odor prediction model comprises a modal encoder, a cross-modal attention fusion module and a classification head connected in sequence, inputting the corresponding basic molecular property features, molecular fingerprint features and SMILES sequence features of a to-be-predicted molecule into the trained molecular odor prediction model to obtain prediction probabilities of corresponding odor categories, and determining an odor category prediction result of the to-be-predicted molecule based on the prediction probabilities. Through multi-modal feature fusion, an interpretable cross-modal attention and a gating mechanism, the method realizes more reasonable representation modeling of molecular odor, and effectively improves the accuracy of odor label prediction.

Systems and methods are provided for identifying compounds in a combinatorial synthesis library (CSL) having particular molecular properties. The CSL is accessed using an autoencoder comprising an encoder and a decoder. The encoder maps compounds in the CSL into latent codes in a learned latent space. The decoder retrieves molecular structures of the compounds using such codes. A policy selects a batch of latent codes, and identifies a plurality of compounds from the batch of latent codes using the decoder. Molecular properties of these compounds are determined, and a reward function value for each compound is determined using the molecular properties. A probability density under a target distribution is determined using the reward function values, in which latent codes are sampled from the CSL by the autoencoder with probabilities proportional to the harmonic reward function values. Policy parameters are updated using at least one difference between the probability density and the target distribution using an alpha-divergence based objective function.

The present disclosure provides a molecular data processing method and device, electronic equipment and storage medium, relates to the technical field of computers, in particular to the technical field of data processing, deep learning, artificial intelligence and the like. The specific implementation scheme is as follows: collecting from a source domain and a target domain to obtain a molecular data set; determining first original molecular features contained in the source domain and second original molecular features contained in the target domain from the molecular data set; determining model parameters based on the association relationship between the first original molecular features and the second original molecular features; and training based on the model parameters to generate a molecular property prediction model.

This invention provides a class of near-infrared molecular probes that specifically bind to human serum albumin, their preparation methods, and applications. The near-infrared molecular probes are one of NFH-1, NFH-2, NFH-3, NFH-4, NFH-5, NFH-6, and NFH-7, with the general formula: [Formula omitted for brevity]. In this formula, R is selected from methyl, benzyl, fluorobenzyl, phenethyl, 2,4-dimethylbenzyl, 3-methoxybenzyl, and p-carboxybenzyl. This invention uses a hydroxyl hemicyanine dye as the fluorophore and introduces a series of hydrophobic functional groups (-R) onto the phenolic hydroxyl group to regulate molecular properties to match the hydrophobic domains of human serum albumin. These probes can avoid background interference from endogenous substances in clinical blood samples, improve the signal-to-noise ratio and accuracy of detection, and are simple to prepare, fluorescently sensitive, highly resistant to interference, and highly stable, providing an efficient tool for clinical human serum albumin detection.

The application relates to the field of drug discovery and molecular design, and particularly relates to a molecular attribute prediction method and device based on a heterogeneous graph neural network and a medium. The method obtains structure information of a to-be-predicted molecule and a target attribute category to be predicted; extracts atomic-level features to construct atomic nodes and atom-atom edges; connects corresponding atomic nodes and pharmacophore nodes; connects virtual molecule nodes and attribute nodes, so as to construct a task-specific heterogeneous molecular graph containing atomic nodes, globally shared pharmacophore nodes, attribute nodes, virtual molecule nodes, atom-atom edges, atom-pharmacophore edges, molecule-attribute edges and pharmacophore-attribute edges; inputs the graph into a pre-trained heterogeneous graph neural network model; generates a global representation vector through a cross-layer adaptive attention mechanism, and outputs a prediction result of the target attribute category. The method can capture the complex hierarchical relationship in a molecule and realize effective molecular attribute prediction under a small sample condition.

The application discloses a method for predicting ADMET properties of drug compound molecules based on deep learning fusion of molecular graphs and molecular point cloud, and comprises the following steps: obtaining SMILES code of a candidate drug molecule for which drug molecular property prediction is needed; processing the SMILES code of the candidate drug molecule; generating a corresponding two-dimensional molecular graph based on the number of atoms and the number of chemical bonds in the SMILES code of the candidate drug molecule, extracting atom node features and edge features of atomic bonds in the drug molecule from the SMILES code of the candidate drug molecule, adding the atom node features and the edge features of the atomic bonds in the drug molecule into the two-dimensional molecular graph, and obtaining a drug molecular graph; extracting corresponding point cloud features of the candidate drug molecule based on the SMILES code of the candidate drug molecule; and inputting the drug molecular graph and the corresponding point cloud features of the candidate drug molecule into a trained deep learning model to obtain an ADMET property prediction result of the candidate drug molecule.

This invention relates to the field of molecular property prediction, specifically disclosing a method for molecular property prediction driven by multimodal feature fusion through reinforcement learning. The method includes loading and preprocessing molecular data; processing the SMILES expressions in the data items, converting them into multimodal feature vectors that can be received by a multilayer perceptron agent; merging multiple feature information through feature fusion and inputting it into the agent participating in meta-training; reconstructing the environment rules and reward function for DiscoRL meta-training; furthermore, using a dynamic equilibrium sampling method for the agent's molecular sampling strategy in the environment rules; dynamically monitoring the validation set performance of the rules by continuously extracting stage-specific meta-network weights during training and embedding them into a fast adaptation loop, recording and saving the best-performing rule weights; this invention significantly outperforms current state-of-the-art methods based on large language models on the MoleculeNet molecular property prediction benchmark, and has significant implications for research in the field of drug discovery.

Methods and systems for molecule generation include filtering a set of molecular properties to remove properties with low variance. The filtered set of molecular properties is embedded to a vector in a disentangled semantic space generating a molecule using an encoder. A new molecule from the vector is generated using a diffusion model.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a prediction characterizing a molecule. According to one aspect, there is provided a method comprising: receiving data identifying a molecule; generating data defining a protonation state graph for the molecule, wherein: each node in the graph represents a respective protonation state of the molecule; and each edge in the graph corresponds to a respective protonation site on the molecule and connects a respective pair of nodes in the graph that represent a corresponding pair of possible protonation states of the molecule that differ only in a protonation state of the corresponding protonation site on the molecule; and each edge in the graph is associated with a predicted micro pKa value of the corresponding protonation site; and processing the data defining the graph for the molecule to generate a prediction characterizing the molecule.

The application discloses a general drug property prediction method and device based on a conditional perception graph neural network, and the method comprises the following steps: constructing a condition-specific training data set; constructing a prediction model, wherein the prediction model is a double-branch architecture, and comprises a semantic extraction module, a double-branch molecular graph encoder and a conditional mixed expert prediction head; the double-branch molecular graph encoder comprises a conditional perception branch and a structure reservation branch; a phased pre-training strategy is adopted to train the prediction model based on the training data set, thereby obtaining a trained general molecular property prediction model, wherein the phased pre-training strategy comprises physicochemical property perception pre-training and large-scale biological activity pre-training; and the trained general molecular property prediction model is used to process a molecular chemical structure in combination with task and experimental condition description, and a property prediction value of the molecule under specific task and experimental conditions is output. The application can effectively integrate truncated information.

Methods and systems for molecule generation include filtering (314) a set of molecular properties to remove properties with low variance. The filtered set of molecular properties is embedded (408) to a vector in a disentangled semantic space generating a molecule using an encoder. A new molecule from the vector is generated (316) using a diffusion model.

This invention belongs to the interdisciplinary field of artificial intelligence and computational chemistry, specifically relating to a method and system for predicting molecular properties based on multi-view equivariant graph neural networks, particularly suitable for high-precision molecular potential surface fitting and large-scale molecular dynamics simulations. Addressing the problems of existing equivariant networks relying on tensor products, resulting in high computational complexity, and being limited by local views in capturing long-range interactions, this invention first constructs a multi-granularity topological view encompassing microscopic atoms, mesoscopic motifs, and macroscopic pharmacophores. Second, utilizing vector inner products and scalar gating mechanisms, it performs scalar-vector decoupled equivariant interactions without tensor products, implicitly extracting local geometric features. Subsequently, it performs equivariant information fusion through cross-view attention, aggregating long-range nonlocal interactions. Finally, it combines physical priors to infer energy and forces, thereby obtaining molecular properties.

This application relates to the field of polymer materials informatics and molecular property prediction technology, and discloses a polymer property prediction method based on a periodic attention mechanism. The method includes: obtaining the repeating unit structure representation of the polymer to be predicted, determining the polymerization connection points, constructing an initial molecular graph based on the actual bonding relationships, and generating node features; establishing virtual edges across connection points between adjacent atoms to generate a periodic molecular graph; further determining the set of adjacent atoms and the set of second-order neighboring atoms, performing two-level attention aggregation in combination with topological offset encoding, and obtaining the periodic feature representation of the polymer through graph-level aggregation, and outputting the target property prediction result, thereby improving the completeness of the polymer periodic structure characterization and the accuracy and stability of property prediction.