Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022072722 - DEEP LEARNING SYSTEM FOR PREDICTING THE T CELL RECEPTOR BINDING SPECIFICITY OF NEOANTIGENS

Publication Number WO/2022/072722
Publication Date 07.04.2022
International Application No. PCT/US2021/053006
International Filing Date 30.09.2021
Chapter 2 Demand Filed 02.05.2022
IPC
A61K 35/17 2015.1
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
KPREPARATIONS FOR MEDICAL, DENTAL, OR TOILET PURPOSES
35Medicinal preparations containing materials or reaction products thereof with undetermined constitution
12Materials from mammals; Compositions comprising non-specified tissues or cells; Compositions comprising non-embryonic stem cells; Genetically modified cells
14Blood; Artificial blood
17Lymphocytes; B-cells; T-cells; Natural killer cells; Interferon-activated or cytokine-activated lymphocytes
C07K 14/705 2006.1
CCHEMISTRY; METALLURGY
07ORGANIC CHEMISTRY
KPEPTIDES
14Peptides having more than 20 amino acids; Gastrins; Somatostatins; Melanotropins; Derivatives thereof
435from animals; from humans
705Receptors; Cell surface antigens; Cell surface determinants
G06N 3/08 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
A61K 35/17
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
KPREPARATIONS FOR MEDICAL, DENTAL, OR TOILET PURPOSES
35Medicinal preparations containing materials or reaction products thereof with undetermined constitution
12Materials from mammals; Compositions comprising non-specified tissues or cells; Compositions comprising non-embryonic stem cells; Genetically modified cells
14Blood; Artificial blood
17Lymphocytes; B-cells; T-cells; Natural killer cells; Interferon-activated or cytokine-activated lymphocytes
C07K 14/705
CCHEMISTRY; METALLURGY
07ORGANIC CHEMISTRY
KPEPTIDES
14Peptides having more than 20 amino acids; Gastrins; Somatostatins; Melanotropins; Derivatives thereof
435from animals; from humans
705Receptors; Cell surface antigens; Cell surface determinants
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • THE BOARD OF REGENTS OF THE UNIVERSITY OF TEXAS SYSTEM [US]/[US]
Inventors
  • LU, Tianshi
  • WANG, Tao
Agents
  • YORE, Campbell, A.
  • GANGULY, Amritaa
  • GAO, Xin
  • CONRAD, Zachary
  • BIFANO, Larissa
Priority Data
63/085,91130.09.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) DEEP LEARNING SYSTEM FOR PREDICTING THE T CELL RECEPTOR BINDING SPECIFICITY OF NEOANTIGENS
(FR) SYSTÈME D'APPRENTISSAGE PROFOND POUR PRÉDIRE LA SPÉCIFICITÉ DE LIAISON AU RÉCEPTEUR DE LYMPHOCYTES T DE NÉOANTIGÈNES
Abstract
(EN) Neoantigens play a key role in the recognition of tumor cells by T cells. However, only a small proportion of neoantigens truly elicit T cell responses, and fewer clues exist as to which neoantigens are recognized by which T cell receptors (TCRs). To help determine the TCRs that interact with particular neoantigens, prediction models that predict TCR-binding specificities of neoantigens presented by different classes of major histocompatibility complex (MHCs) were developed. To confirm the applicability of the model to clinical settings, the prediction models were comprehensively validated by a series of analyses. The validated prediction models used a flexible transfer learning approach and differential learning schema to achieve highly accurate prediction of TCR binding specificity only using TCR sequence data, antigen sequence data, and MHC alleles.
(FR) Les néo-antigènes jouent un rôle clé dans la reconnaissance de cellules tumorales au moyen des lymphocytes T. Cependant, seule une petite proportion de néo-antigènes provoquent véritablement des réponses des lymphocytes T, et moins d'indices existent quant au fait de savoir quels néo-antigènes sont reconnus par quels récepteurs de lymphocytes T (TCR). Pour aider à déterminer les TCR qui interagissent avec des néo-antigènes particuliers, des modèles de prédiction qui prédisent des spécificités de liaison aux TCR de néo-antigènes présentés sous forme de classes différentes de complexes majeurs d'histocompatibilité (MHC) ont été développés. En vue de confirmer l'applicabilité du modèle à des conditions cliniques, les modèles de prédiction ont été validés de manière complète par une série d'analyses. Les modèles de prédiction validés ont utilisé une approche d'apprentissage de transfert flexible et un schéma d'apprentissage différentiel de sorte à obtenir une prédiction très précise de la spécificité de liaison aux TCR uniquement à l'aide de données de séquence de TCR, de données de séquence d'antigènes et d'allèles de MHC.
Latest bibliographic data on file with the International Bureau