专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US12027240B2 Electronic device, and computer-readable storage medium 有权
公开(公告)号：US12027240B2
公开(公告)日：2024-07-02
申请号：US17522702
申请日：2021-11-09
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Yaodong Yang , Hongyao Tang , Guangyong Chen , Shengyu Zhang , Changyu Hsieh , Jianye Hao
IPC分类号： G16C20/50 , G06F30/27 , G16C20/10
CPC分类号： G16C20/50 , G06F30/27 , G16C20/10
摘要： Embodiments of this application relate to a retrosynthesis processing method and apparatus, an electronic device, and a computer-readable storage medium. A retrosynthesis processing method is performed by a computer device. The method includes determining molecular representation information of a target molecule. The method includes inputting the molecular representation information into a target neural network. The method includes performing, via the target neural network, retrosynthesis processing on the target molecule based on the molecular representation information of the target molecule, to obtain a respective retrosynthesis reaction of the target molecule for each step of the retrosynthesis processing. The target neural network is obtained by training a predetermined neural network according to a sample cost dictionary that is generated by concurrently performing retrosynthesis reaction training on each of a plurality of sample molecules, and the respective retrosynthesis reaction is performed according to a preset retrosynthesis reaction architecture.

2. 发明公开

US20240212796A1 REACTANT MOLECULE PREDICTION USING MOLECULE COMPLETION MODEL 审中-公开
公开(公告)号：US20240212796A1
公开(公告)日：2024-06-27
申请号：US18597636
申请日：2024-03-06
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Ziqiao MENG , Peilin ZHAO
IPC分类号： G16C20/20 , G16C20/50 , G16C20/70
CPC分类号： G16C20/20 , G16C20/50 , G16C20/70
摘要： A method for predicting reactant molecules includes obtaining a product molecule, and selecting bonds of the product molecule to be broken to obtain a molecule to be completed, the product molecule defining a compound molecule of a reactant molecule to be predicted. The method further includes applying a molecule completion model to complete the molecule to be completed to obtain a completion result indicating a reactant molecule of the product molecule based on the molecule to be completed. The molecule completion model is obtained by training based on sample compound molecules and sample molecules to be completed obtained by masking sub-structures in the sample compound molecules.

3. 发明公开

US20240185963A1 PROTEIN KINETIC ENSEMBLE PLATFORM FOR DISCOVERY OF BINDING POCKETS AND NOVEL LIGANDS 审中-公开
公开(公告)号：US20240185963A1
公开(公告)日：2024-06-06
申请号：US18528393
申请日：2023-12-04
申请人： ENSEM THERAPEUTICS, INC.
发明人： Minghong Hao
IPC分类号： G16C20/50
CPC分类号： G16C20/50
摘要： The invention provides a kinetic ensemble system for identifying non-obvious target pockets and/or generating lead compound structures and/or structural components, comprising computational components and experimental components or processes, wherein the computational components comprise: physics-based simulation and artificial intelligence; and the experimental components or processes comprise biophysical components and chemical biology components.

4. 发明公开

US20240144092A1 GENERATIVE MACHINE LEARNING SYSTEMS FOR DRUG DESIGN 审中-公开
公开(公告)号：US20240144092A1
公开(公告)日：2024-05-02
申请号：US18394019
申请日：2023-12-22
申请人： Preferred Networks, Inc.
发明人： Kenta OONO , Justin CLAYTON , Nobuyuki OTA
IPC分类号： G06N20/00 , G06N3/047 , G06N7/01 , G16C20/50
CPC分类号： G06N20/00 , G06N3/047 , G06N7/01 , G16C20/50 , G16C20/70
摘要： A computer system includes one or more memories and one or more processors configured to cause a generative model to generate structural information regarding a chemical compound by inputting a latent representation into the generative model, wherein the generative model has been trained such that differences between structural information regarding other chemical compounds and reconstructions of the structural information regarding the other chemical compounds generated by the generative model are reduced, the reconstructions being generated by inputting latent representations into the generative model, the latent representations being generated based on the structural information regarding the other chemical compounds.

5. 发明公开

US20240029835A1 Process for Predictive Optimization Algorithm Development for Molecular Structural Synthesis 审中-公开
公开(公告)号：US20240029835A1
公开(公告)日：2024-01-25
申请号：US18468731
申请日：2023-09-17
申请人： Anika Mahajan Jena
发明人： Anika Mahajan Jena
IPC分类号： G16C20/50 , G16C20/20
CPC分类号： G16C20/50 , G16C20/20
摘要： The invention provides a process for developing a quantitative algorithm to illustrate and predict the outcome of molecular structural synthesis, from optimized component formulations, for result optimization. Formulations, such as those involved in molecular structural synthesis, involve multiple interacting components. Performance lies on a gradient success scale. Iterative formulations, syntheses, and evaluation under controlled fabrication parameters are followed by rounds of regression and integration. The result of integration is a predictive algorithm that contains all salient component quantities as variables and presents an optimized formulation and risk-tolerance region. The algorithm's output formulations yield optimally performing, efficient syntheses under the specified conditions desired.

6. 发明公开

US20230402135A1 LIGAND SCREENING MODEL CONSTRUCTION METHOD AND DEVICE, A SCREENING METHOD, A DEVICE, AND A MEDIUM 审中-公开
公开(公告)号：US20230402135A1
公开(公告)日：2023-12-14
申请号：US17931917
申请日：2022-09-14
申请人： Ainnocence Technologies LLC
发明人： Junfeng Wu , Yutong Jin , Lurong Pan
IPC分类号： G16C20/50 , G06N3/04 , G06N3/08 , G16C20/70 , G16C20/80
CPC分类号： G16C20/50 , G06N3/04 , G06N3/08 , G16C20/70 , G16C20/80
摘要： A ligand screening model construction method, a ligand screening model construction device, and a drug ligand screening method for drug screening, comprising that obtain a drug ligand training set, and the drug ligand training set includes a drug ligand chemical formula and a classification label; a ligand graph network is drawn, in which atoms are nodes and chemical bonds are edges connecting nodes; use a random initialization vector to identify the weight vector of each node in the ligand graph network; reconstruct each node of the ligand graph network to obtain a reconstruction network, and repeat the reconstruction steps to obtain at least two layers of reconstruction networks; perform deep learning on the ligand graph network and the at least two-layer reconstruction graph network according to the classification labels, and construct a ligand screening model.

7. 发明公开

US20230368871A1 METHOD, COMPUTER PROGRAM, VIDEO GAME AND SYSTEM FOR OPTIMIZING A MOLECULE FOR MEDICAL APPLICATIONS 审中-公开
公开(公告)号：US20230368871A1
公开(公告)日：2023-11-16
申请号：US18091141
申请日：2022-12-29
申请人： MOLOMICS BIOTECH, S.L.
发明人： Giovanni Cincilla , Simone Masoni , Jascha Blobel
IPC分类号： G16C20/50 , G16C20/30 , G16C20/80 , G06F3/04845
CPC分类号： G16C20/50 , G16C20/30 , G16C20/80 , G06F3/04845
摘要： The invention relates to a method, a computer program a system, a video game system and a video game for designing a molecule for medical applications by optimization of an associated drug score (101) of the molecule, comprising the steps of: a) providing a computer-readable representation of a selected molecule (100) and a drug score (101) associated to the selected molecule (100), b) determining (201) a first moiety (110) of the selected molecule (100) and a second moiety (120) of the selected molecule (100), wherein the selected molecule (100) consists of the first moiety (110) and second moiety (120), c) determining (202) a first moiety pharmacophore (130), wherein the first moiety (110) of the selected molecule (100) fits to the first moiety pharmacophore (130), d) providing (203) a graphical user interface (150), e) displaying (204) a graphical representation of a selected part (131) of the first moiety pharmacophore (130) on the graphical user interface (150), f) determining a starting point (160) on the graphical user interface (150) in relation to the graphical representation of the selected part (131) of the first moiety pharmacophore (130), g) from the starting point (160), arranging or rearranging graphical representations of molecular building blocks (170) on the graphical user interface (150), wherein the graphical representations of the molecular building blocks (170) are interconnected and form a graphical representation of a modified first moiety of a molecule (180), h) assigning (207) the graphical representation of the modified first moiety of the molecule (180) to a modified first moiety (111) of the selected molecule (100), i) determining (208) a modified molecule (190) consisting of the modified first moiety (111) and the second moiety (120) of the selected molecule (100), j) estimating (209) the associated drug score (101) for the modified molecule (190), k) disclosing (210) the associated drug score (101) of the modified molecule (190).

8. 发明公开

US20230335229A1 STRUCTURED DATA GENERATION METHOD AND APPARATUS, DEVICE, MEDIUM, AND PROGRAM PRODUCT 审中-公开
公开(公告)号：US20230335229A1
公开(公告)日：2023-10-19
申请号：US18333140
申请日：2023-06-12
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： Lanqing LI , Ziqi Gao
IPC分类号： G16C20/50 , G16C20/70
CPC分类号： G16C20/50 , G16C20/70
摘要： Disclosed are a structured data generation method and apparatus that can acquire a structure feature representation and a node feature representation of sample structured data; generate a hidden-layer feature representation based on the structure feature representation and the node feature representation; input the hidden-layer feature representation into a to-be-trained decoder for structure reconstruction to obtain predicted structured data; and train the to-be-trained decoder based on the predicted structured data to obtain a specified decoder, the specified decoder being configured to perform structure reconstruction on inputted sampled data to obtain reconstructed structured data.

9. 发明公开

US20230335228A1 Active Learning Using Coverage Score 审中-公开
公开(公告)号：US20230335228A1
公开(公告)日：2023-10-19
申请号：US18138021
申请日：2023-04-21
申请人： EXSCIENTIA AI LIMITED
发明人： Willem Paul VAN HOORN
IPC分类号： G16C20/50 , G16C20/70
CPC分类号： G16C20/50 , G16C20/70
摘要： A method for computational drug design includes defining a population of a plurality of compounds. Each compound includes one or more molecular properties. The method includes defining a training set of compounds from the population for which one or more biological properties are known. The method includes selecting, from the population, a subset of one or more compounds that are not in the training set. The method includes determining a subset score of the selected subset based on molecular properties of the one or more compounds in the selected subset, and evaluating the selected subset based on the determined subset score. The subset score is determined based on a frequency of the molecular properties in the population and on a frequency of the molecular properties in a sampled set comprising the training set and the selected subset.

10. 发明公开

US20230335227A1 Molecule Designing Method, Device and Program 审中-公开
公开(公告)号：US20230335227A1
公开(公告)日：2023-10-19
申请号：US18123370
申请日：2023-03-20
申请人： Asahi Kasei Kabushiki Kaisha
发明人： Hiroyuki Tsujimoto , Natsumi Yamakawa , Ippei Kimura , Hideki Yamamoto
IPC分类号： G16C20/50
CPC分类号： G16C20/50
摘要： It is intended to provide a method, a device, and a program that are capable of outputting a molecule designing result having more appropriate performance in the range of molecule designing with which synthesis is realistically possible. A method executes, by a device, a sensitivity estimation step of inputting candidate information A, information B, and reference information C to a model to output sensitivity information D of a receptor constituted by using a polymer for an analyte, the candidate information A being related to the polymer, the information B being related to the analyte, the reference information C being related to a film constitution of the receptor.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式