Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020109608 - MACHINE LEARNING FOR PROTEIN BINDING SITES

Publication Number WO/2020/109608
Publication Date 04.06.2020
International Application No. PCT/EP2019/083188
International Filing Date 29.11.2019
IPC
G16B 15/30 2019.01
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
15ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
30Drug targeting using structural data; Docking or binding prediction
G16B 40/20 2019.01
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
40ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
20Supervised data analysis
CPC
G16B 15/30
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
15ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
30Drug targeting using structural data; Docking or binding prediction
G16B 40/20
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
40ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
20Supervised data analysis
Applicants
  • BENEVOLENTAI TECHNOLOGY LIMITED [GB]/[GB]
Inventors
  • MEYERS, Joshua
  • SEGLER, Marwin
  • SIMONOVSKY, Martin
Agents
  • TRICHARD, Louis
  • HILL, Justin
  • REES, Alexander
  • JANSSON-HEEKS, Marie
  • DAWSON, Elizabeth Ann
Priority Data
1819498.529.11.2018GB
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) MACHINE LEARNING FOR PROTEIN BINDING SITES
(FR) APPRENTISSAGE MACHINE POUR L'IDENTIFICATION DE SITES DE LIAISON PROTÉINIQUE
Abstract
(EN)
A computer-implemented method of training a machine learning model to learn ligand binding similarities between protein binding sites is disclosed. The method comprises inputting to the machine learning model: a representation of a first binding site; a representation of a second binding site, wherein the representations of the first and second binding sites comprise structural information; and a label comprising an indication of ligand binding similarity between the first binding site and the second binding site. The method also comprises outputting from the machine model a similarity indicator based on the representations of the first and second binding sites; performing a comparison between the similarity indicator and the label; and updating the machine learning model based on the comparison.
(FR)
Une méthode mise en oeuvre par ordinateur d'entraînement d'un modèle d'apprentissage machine à apprendre les similarités de liaison aux ligands entre des sites de liaison protéinique, est divulguée. La méthode consiste à entrer dans le modèle d'apprentissage machine : une représentation d'un premier site de liaison ; une représentation d'un deuxième site de liaison, les représentations des premier et deuxième sites de liaison comprenant des informations structurelles ; et une étiquette comprenant une indication de similarité de liaison aux ligands entre le premier site de liaison et le deuxième site de liaison. La méthode consiste également à produire en sortie, à partir du modèle machine, un indicateur de similarité en fonction des représentations des premier et deuxième sites de liaison ; à effectuer une comparaison entre l'indicateur de similarité et l'étiquette ; et à mettre à jour le modèle d'apprentissage machine sur la base de la comparaison.
Latest bibliographic data on file with the International Bureau