Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022026551 - DEEP LEARNING FOR DE NOVO ANTIBODY AFFINITY MATURATION (MODIFICATION) AND PROPERTY IMPROVEMENT

Publication Number WO/2022/026551
Publication Date 03.02.2022
International Application No. PCT/US2021/043461
International Filing Date 28.07.2021
IPC
G16B 30/00 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
30ICT specially adapted for sequence analysis involving nucleotides or amino acids
G16B 40/20 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
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 30/00
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
30ICT specially adapted for sequence analysis involving nucleotides or amino acids
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
  • FLAGSHIP PIONEERING INNOVATIONS VI, LLC [US]/[US]
Inventors
  • COSTELLO, Zachary, Kohl
  • FEALA, Jacob
  • BEAM, Andrew, Lane
Agents
  • BALICKY, Eric, M.
Priority Data
63/057,37628.07.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) DEEP LEARNING FOR DE NOVO ANTIBODY AFFINITY MATURATION (MODIFICATION) AND PROPERTY IMPROVEMENT
(FR) APPRENTISSAGE PROFOND POUR LA MATURATION (MODIFICATION) DE NOVO DE L'AFFINITÉ ENVERS LES ANTICORPS ET L'AMÉLIORATION DES PROPRIÉTÉS
Abstract
(EN) Controlling antibody affinity and expression are key to clinical applications. High affinity antibodies correlate with higher specificity and can be used at lower doses. Presently, antibody maturation is tackled with directed evolution methods. In this case, an initial library of mutated binders is seeded into a process and affinity is improved through multiple rounds of mutation and selection. However, the present disclosure employs a machine learning approach to computationally mature antibody sequences using a process having parallels to directed evolution. These antibody sequences can be manufactured into physical antibodies after their computation and verification. Additionally, the present method has the potential to outperform directed evolution when targeting a specific affinity, and is applicable to general protein-protein interactions.
(FR) Le contrôle de l'affinité et de l'expression des anticorps est essentiel pour les applications cliniques. Les anticorps à haute affinité correspondent à une spécificité supérieure et peuvent être utilisés à des doses plus faibles. Actuellement, la maturation d'anticorps est abordée avec des méthodes d'évolution dirigée. Dans ce cas, une bibliothèque initiale de liants mutés est introduite dans un processus et l'affinité est améliorée par l'intermédiaire de multiples cycles de mutation et de sélection. Cependant, la présente invention utilise une approche d'apprentissage machine pour effectuer la maturation par calcul de séquences d'anticorps en utilisant un processus ayant des parallèles avec l'évolution dirigée. Ces séquences d'anticorps peuvent être fabriquées en anticorps physiques après leur calcul et leur vérification. En outre, le procédé de la présente invention a le potentiel de surpasser l'évolution dirigée lors du ciblage d'une affinité spécifique, et est applicable aux interactions protéine-protéine générales.
Latest bibliographic data on file with the International Bureau