Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains
Antibodies are a popular and powerful class of therapeutic due to their ability to exhibit high affinity and specificity to target proteins. However, the majority of antibody therapeutics are not genetically human, with initial therapeutic designs typically obtained from animal models. Humanization...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | mAbs |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19420862.2024.2434121 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576618293362688 |
|---|---|
| author | Lewis Chinery Jeliazko R. Jeliazkov Charlotte M. Deane |
| author_facet | Lewis Chinery Jeliazko R. Jeliazkov Charlotte M. Deane |
| author_sort | Lewis Chinery |
| collection | DOAJ |
| description | Antibodies are a popular and powerful class of therapeutic due to their ability to exhibit high affinity and specificity to target proteins. However, the majority of antibody therapeutics are not genetically human, with initial therapeutic designs typically obtained from animal models. Humanization of these precursors is essential to reduce immunogenic risks when administered to humans.Here, we present Humatch, a computational tool designed to offer experimental-like joint humanization of heavy and light chains in seconds. Humatch consists of three lightweight Convolutional Neural Networks (CNNs) trained to identify human heavy V-genes, light V-genes, and well-paired antibody sequences with near-perfect accuracy. We show that these CNNs, alongside germline similarity, can be used for fast humanization that aligns well with known experimental data. Throughout the humanization process, a sequence is guided toward a specific target gene and away from others via multiclass CNN outputs and gene-specific germline data. This guidance ensures final humanized designs do not sit ‘between’ genes, a trait that is not naturally observed. Humatch’s optimization toward specific genes and good VH/VL pairing increases the chances that final designs will be stable and express well and reduces the chances of immunogenic epitopes forming between the two chains. Humatch’s training data and source code are provided open-source. |
| format | Article |
| id | doaj-art-6406647f7b7649089c8989c43f5d8b0c |
| institution | Kabale University |
| issn | 1942-0862 1942-0870 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | mAbs |
| spelling | doaj-art-6406647f7b7649089c8989c43f5d8b0c2025-01-31T04:19:37ZengTaylor & Francis GroupmAbs1942-08621942-08702024-12-0116110.1080/19420862.2024.2434121Humatch - fast, gene-specific joint humanisation of antibody heavy and light chainsLewis Chinery0Jeliazko R. Jeliazkov1Charlotte M. Deane2Department of Statistics, University of Oxford, Oxford, UKProtein Design and Informatics, Research Technologies, GSK R&D, Upper Providence, USADepartment of Statistics, University of Oxford, Oxford, UKAntibodies are a popular and powerful class of therapeutic due to their ability to exhibit high affinity and specificity to target proteins. However, the majority of antibody therapeutics are not genetically human, with initial therapeutic designs typically obtained from animal models. Humanization of these precursors is essential to reduce immunogenic risks when administered to humans.Here, we present Humatch, a computational tool designed to offer experimental-like joint humanization of heavy and light chains in seconds. Humatch consists of three lightweight Convolutional Neural Networks (CNNs) trained to identify human heavy V-genes, light V-genes, and well-paired antibody sequences with near-perfect accuracy. We show that these CNNs, alongside germline similarity, can be used for fast humanization that aligns well with known experimental data. Throughout the humanization process, a sequence is guided toward a specific target gene and away from others via multiclass CNN outputs and gene-specific germline data. This guidance ensures final humanized designs do not sit ‘between’ genes, a trait that is not naturally observed. Humatch’s optimization toward specific genes and good VH/VL pairing increases the chances that final designs will be stable and express well and reduces the chances of immunogenic epitopes forming between the two chains. Humatch’s training data and source code are provided open-source.https://www.tandfonline.com/doi/10.1080/19420862.2024.2434121antibodyhumanisationmachine learningv-genepaired |
| spellingShingle | Lewis Chinery Jeliazko R. Jeliazkov Charlotte M. Deane Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains mAbs antibody humanisation machine learning v-gene paired |
| title | Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains |
| title_full | Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains |
| title_fullStr | Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains |
| title_full_unstemmed | Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains |
| title_short | Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains |
| title_sort | humatch fast gene specific joint humanisation of antibody heavy and light chains |
| topic | antibody humanisation machine learning v-gene paired |
| url | https://www.tandfonline.com/doi/10.1080/19420862.2024.2434121 |
| work_keys_str_mv | AT lewischinery humatchfastgenespecificjointhumanisationofantibodyheavyandlightchains AT jeliazkorjeliazkov humatchfastgenespecificjointhumanisationofantibodyheavyandlightchains AT charlottemdeane humatchfastgenespecificjointhumanisationofantibodyheavyandlightchains |