Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022003997 - PATHWAY GENERATION DEVICE, PATHWAY GENERATION METHOD, AND PATHWAY GENERATION PROGRAM

Publication Number WO/2022/003997
Publication Date 06.01.2022
International Application No. PCT/JP2020/043961
International Filing Date 26.11.2020
IPC
G16B 5/20 2019.1
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
5ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
20Probabilistic models
G06N 5/04 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
G06N 20/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G16H 50/20 2018.1
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
20for computer-aided diagnosis, e.g. based on medical expert systems
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 5/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
G16B 5/20
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
5ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
20Probabilistic models
G16H 50/20
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
20for computer-aided diagnosis, e.g. based on medical expert systems
Applicants
  • 株式会社FRONTEO FRONTEO, INC. [JP]/[JP]
Inventors
  • 豊柴 博義 TOYOSHIBA Hiroyoshi
Agents
  • 橘 和之 TACHIBANA Kazuyuki
Priority Data
2020-11465802.07.2020JP
Publication Language Japanese (ja)
Filing Language Japanese (JA)
Designated States
Title
(EN) PATHWAY GENERATION DEVICE, PATHWAY GENERATION METHOD, AND PATHWAY GENERATION PROGRAM
(FR) DISPOSITIF DE GÉNÉRATION DE CHEMIN, PROCÉDÉ DE GÉNÉRATION DE CHEMIN ET PROGRAMME DE GÉNÉRATION DE CHEMIN
(JA) パスウェイ生成装置、パスウェイ生成方法およびパスウェイ生成用プログラム
Abstract
(EN) This pathway generation device is provided with: a related molecule estimation unit 12 which, by inputting to a first trained model a disease feature vector specified for a disease to be analyzed, estimates multiple molecules related to the disease; a molecular property estimation unit 13 which, by inputting to a second trained model the disease feature vector and molecule feature vectors specified for the multiple molecules estimated by the related molecule estimation unit 12, estimates the probability that the properties of a molecule acting on the disease are causal; and a pathway generation unit 14 which uses the properties of the molecules estimated by the molecular property estimation unit 13 to generate a pathway – with the interactions between molecules represented as a path diagram – such that the causal molecules are upstream and the responsive molecules are downstream, and reflecting known connectional relations between molecules.
(FR) La présente invention concerne un dispositif de génération de chemin qui est pourvu : d'une unité d'estimation de molécule associée (12) qui, en entrant dans un premier modèle formé un vecteur de caractéristiques de maladie spécifié pour une maladie à analyser, estime de multiples molécules associées à la maladie ; d'une unité d'estimation de propriété moléculaire (13) qui, en entrant dans un second modèle formé le vecteur de caractéristiques de maladie et les vecteurs de caractéristiques de molécule spécifiés pour les multiples molécules estimées par l'unité d'estimation de molécule associée (12), estime la probabilité que les propriétés d'une molécule agissant sur la maladie soient causales ; et d'une unité de génération de chemin (14) qui utilise les propriétés des molécules estimées par l'unité d'estimation de propriété moléculaire (13) pour générer un chemin – avec les interactions entre des molécules représentées en tant que diagramme de trajet – de telle sorte que les molécules causales soient en amont et que les molécules sensibles soient en aval, et reflétant les relations de connexion connues entre les molécules.
(JA) 分析対象とする疾患について特定される疾患特徴ベクトルを第1学習済みモデルに入力することにより、疾患と関連がある複数の分子を推定する関連分子推定部12と、疾患特徴ベクトルおよび関連分子推定部12により推定された複数の分子について特定される分子特徴ベクトルを第2学習済みモデルに入力することにより、疾患に対して作用する分子の性質が原因性である確率を推定する分子性質推定部13と、分子性質推定部13により推定された分子の性質を用いて、原因性の分子が上流側で応答性の分子が下流側となり、かつ、既知の分子間接続関係性を反映させるように分子間相互作用を経路図として表したパスウェイを生成するパスウェイ生成部14とを備える。
Related patent documents
Latest bibliographic data on file with the International Bureau