Unlock instant, AI-driven research and patent intelligence for your innovation.

Systems and methods to classify antibodies

A technology for antigen-binding molecules and antigens, applied in the field of systems and methods for classifying antibodies, capable of solving problems such as reducing antigen binding

Pending Publication Date: 2021-12-28
ETH ZZURICH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This may result in screening for only minor changes (e.g., single point mutations)
Querying such a small portion of the protein sequence space also means that solving one development problem often leads to another problem or even a complete reduction of antigen binding, making multiparameter optimization challenging

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Systems and methods to classify antibodies
  • Systems and methods to classify antibodies
  • Systems and methods to classify antibodies

Examples

Experimental program
Comparison scheme
Effect test

example

[0106] This example describes an exemplary application of the systems and methods described herein to the CDRH3 of the trastuzumab (Herceptin) antibody and to classify the antibody binding to the corresponding target HER2 antigen.

[0107] A. Results

[0108] 1) Deep mutation scanning to determine the antigen-specific sequence landscape (landscape) and guide rational antibody library design

[0109] Since the amino acid sequence of CDRH3 of an antibody is a key determinant of antigen specificity, deep mutation scanning (DMS) was performed on this region to resolve the specificity-determining residues. First, a hybridoma cell line expressing a trastuzumab variant unable to bind the HER2 antigen (mutated CDRH3 sequence) was used ( FIG. 9 ). Libraries were generated by CRISPR-Cas9-mediated homology-directed mutagenesis (HDM) (Mason et al. (2018) Nucleic Acids Research 46(14):7436–49) utilizing the CDRH3 The Cas9-targeted gRNA and the pool of homologous templates in the form of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present disclosure describes systems and methods to make predictions classifying one or more properties of a binding protein such as an antibody, for example, antibody affinity or specificity for an antigen. The system can include one or more machine learning models that can extrapolate complex relationships between amino acid sequence and function. The system can be trained on high-quality training data generated through a two-step single-site and combinatorial deep mutational scanning approach. The trained models can then make predictions on novel variant sequences generated in silico. The present disclosure describes amino acid sequences generated by the systems and methods provided, and uses of the generated sequences to produce proteins for therapeutic and diagnostic use.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to U.S. Provisional Patent Application No. 62 / 831,663, filed April 9, 2019, which is hereby incorporated by reference in its entirety. Background technique [0003] In antibody drug discovery, screening of phage or yeast display libraries is standard practice to identify therapeutic antibodies and often yields many potential lead variant candidates. However, the time and costs associated with lead candidate optimization often occupy a large portion of the drug preclinical discovery and development cycle. This is mainly because lead optimization of antibody molecules often involves processing multiple parameters in parallel, including expression levels, viscosity, pharmacokinetics, solubility, and immunogenicity. Once a lead candidate is found, additional engineering is often required. The fact that almost all therapeutic antibodies need to be expressed as full-length IgG in mammalian c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G16B20/20
CPCG16B20/20G16B20/30G16B40/20G06N5/022
Inventor D·梅森S·弗利单森C·韦伯S·雷迪
Owner ETH ZZURICH