利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

74 条记录 (耗时 0.012 秒)

    GENERATIVE STRUCTURE-PROPERTY INVERSE COMPUTATIONAL CO-DESIGN OF MATERIALS
    41.
    发明公开
    GENERATIVE STRUCTURE-PROPERTY INVERSE COMPUTATIONAL CO-DESIGN OF MATERIALS 审中-公开

    公开(公告)号：EP3800586A1

    公开(公告)日：2021-04-07

    申请号：EP20179214.0

    申请日：2020-06-10

    申请人： Samsung Electronics Co., Ltd.

    发明人： HEGDE, Ganesh ,  SIMKA, Harsono S.

    IPC分类号： G06N3/04 ,  G06N3/08 ,  G16C20/50

    摘要： A method and a system for material design utilizing machine learning are provided, where the underlying joint distribution p(S,P) of structure (S) - property (P) relationships is explicitly learned simultaneously and is utilized to directly generate samples (S,P) in a single step utilizing generative techniques, without any additional processing steps. The subspace of structures that meet or exceed the target for property P is then identified utilizing conditional generation of the distribution (e.g., p(P)), or through randomly generating a large number of samples (S,P) and filtering (e.g., selecting) those that meet target property criteria.

    METHOD FOR PREDICTING AND OPTIMIZING PROPERTIES OF A MOLECULE
    46.
    发明公开
    METHOD FOR PREDICTING AND OPTIMIZING PROPERTIES OF A MOLECULE 审中-公开

    公开(公告)号：EP4227951A1

    公开(公告)日：2023-08-16

    申请号：EP22156423.0

    申请日：2022-02-11

    申请人： Samsung Display Co., Ltd.

    发明人： Ruoff, Patrick ,  Schmalzl, Markus ,  Schniewind, Matthias

    IPC分类号： G16C20/30 ,  G16C20/50 ,  G16C20/70

    摘要： A computer-implemented method for predicting a value of a physical and/or chemical property (180a, 180b) of a molecule, said method uses as input a molecular structure of the molecule as an atom-bond-graph (100) comprising atoms of the molecular structure and bonds of the molecular structure as n nodes nodes of the atom-bond-graph (100), and provides as output the predicted value of the physical and/or chemical property (180a, 180b). The method comprises the steps of extracting (120) for each node of the atom-bond-graph (100) a feature vector of dimension d features , the feature vector comprising a node type, the node type preferably being one of atom, bond and global, and further data on the node in case of the node type being atom or bond, generating a feature matrix of dimension n nodes × features based on the extracted n nodes feature vectors; calculating a squared distance matrix D of dimension n nodes × n nodes based on distances between atoms and bonds of the molecular structure, and applying a trained neural network comprising a transformer using (140) the squared distance matrix D for self-attention decay on the feature matrix to generate a prediction (180a, 180b) of the value of the physical and/or chemical property of the molecule.

    DESIGN OF MOLECULES
    49.
    发明公开
    DESIGN OF MOLECULES 审中-公开

    公开(公告)号：EP4105935A1

    公开(公告)日：2022-12-21

    申请号：EP22162348.1

    申请日：2010-11-22

    申请人： Exscientia Al Limited

    发明人： BESNARD, Jérémy ,  HOPKINS, Andrew, Lee

    IPC分类号： G16C20/50 ,  G16C20/70

    摘要： A method for computational drug design using an evolutionary algorithm, comprises evaluating virtual molecules according to vector distance (VD) to at least one achievement objective that defines a desired ideal molecule. In one method the invention comprises defining a set of n achievement objectives (O A 1-n ), where n is at least one; defining a population (P G=0 ) of at least one molecule; selecting an initial population (P parent ) of at least one molecule (I 1 -I n ) from the population (P G=0 ); and evaluating members (I 1 -I n ) of the initial population (P parent ) against at least one of the n achievement objectives (O A 1-x ), where x is from 1 to n.