Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo
Abstract Based on the success of cancer immunotherapy, personalized cancer vaccines have emerged as a leading oncology treatment. Antigen presentation on MHC class I (MHC-I) is crucial for the adaptive immune response to cancer cells, necessitating highly predictive computational methods to model th...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-54887-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559296576323584 |
|---|---|
| author | William John Thrift Nicolas W. Lounsbury Quade Broadwell Amy Heidersbach Emily Freund Yassan Abdolazimi Qui T. Phung Jieming Chen Aude-Hélène Capietto Ann-Jay Tong Christopher M. Rose Craig Blanchette Jennie R. Lill Benjamin Haley Lélia Delamarre Richard Bourgon Kai Liu Suchit Jhunjhunwala |
| author_facet | William John Thrift Nicolas W. Lounsbury Quade Broadwell Amy Heidersbach Emily Freund Yassan Abdolazimi Qui T. Phung Jieming Chen Aude-Hélène Capietto Ann-Jay Tong Christopher M. Rose Craig Blanchette Jennie R. Lill Benjamin Haley Lélia Delamarre Richard Bourgon Kai Liu Suchit Jhunjhunwala |
| author_sort | William John Thrift |
| collection | DOAJ |
| description | Abstract Based on the success of cancer immunotherapy, personalized cancer vaccines have emerged as a leading oncology treatment. Antigen presentation on MHC class I (MHC-I) is crucial for the adaptive immune response to cancer cells, necessitating highly predictive computational methods to model this phenomenon. Here, we introduce HLApollo, a transformer-based model for peptide-MHC-I (pMHC-I) presentation prediction, leveraging the language of peptides, MHC, and source proteins. HLApollo provides end-to-end treatment of MHC-I sequences and deconvolution of multi-allelic data, using a negative-set switching strategy to mitigate misassigned negatives in unlabelled ligandome data. HLApollo shows a 12.65% increase in average precision (AP) on ligandome data and a 4.1% AP increase on immunogenicity test data compared to next-best models. Incorporating protein features from protein language models yields further gains and reduces the need for gene expression measurements. Guided by clinical use, we demonstrate pan-allelic generalization which effectively captures rare alleles in underrepresented ancestries. |
| format | Article |
| id | doaj-art-88376e34692f4be3b01c7ff6168a47d6 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-88376e34692f4be3b01c7ff6168a47d62025-01-05T12:36:50ZengNature PortfolioNature Communications2041-17232024-12-0115111610.1038/s41467-024-54887-7Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApolloWilliam John Thrift0Nicolas W. Lounsbury1Quade Broadwell2Amy Heidersbach3Emily Freund4Yassan Abdolazimi5Qui T. Phung6Jieming Chen7Aude-Hélène Capietto8Ann-Jay Tong9Christopher M. Rose10Craig Blanchette11Jennie R. Lill12Benjamin Haley13Lélia Delamarre14Richard Bourgon15Kai Liu16Suchit Jhunjhunwala17Early Clinical Development Artificial Intelligence, GenentechOncology Bioinformatics, GenentechEarly Clinical Development Artificial Intelligence, GenentechMolecular Biology Department, GenentechMolecular Biology Department, GenentechMolecular Biology Department, GenentechMicrochemistry, Proteomics and Lipidomics, GenentechOncology Bioinformatics, GenentechCancer Immunology, GenentechCancer Immunology, GenentechMicrochemistry, Proteomics and Lipidomics, GenentechProtein Chemistry, GenentechMicrochemistry, Proteomics and Lipidomics, GenentechMolecular Biology Department, GenentechCancer Immunology, GenentechOncology Bioinformatics, GenentechEarly Clinical Development Artificial Intelligence, GenentechOncology Bioinformatics, GenentechAbstract Based on the success of cancer immunotherapy, personalized cancer vaccines have emerged as a leading oncology treatment. Antigen presentation on MHC class I (MHC-I) is crucial for the adaptive immune response to cancer cells, necessitating highly predictive computational methods to model this phenomenon. Here, we introduce HLApollo, a transformer-based model for peptide-MHC-I (pMHC-I) presentation prediction, leveraging the language of peptides, MHC, and source proteins. HLApollo provides end-to-end treatment of MHC-I sequences and deconvolution of multi-allelic data, using a negative-set switching strategy to mitigate misassigned negatives in unlabelled ligandome data. HLApollo shows a 12.65% increase in average precision (AP) on ligandome data and a 4.1% AP increase on immunogenicity test data compared to next-best models. Incorporating protein features from protein language models yields further gains and reduces the need for gene expression measurements. Guided by clinical use, we demonstrate pan-allelic generalization which effectively captures rare alleles in underrepresented ancestries.https://doi.org/10.1038/s41467-024-54887-7 |
| spellingShingle | William John Thrift Nicolas W. Lounsbury Quade Broadwell Amy Heidersbach Emily Freund Yassan Abdolazimi Qui T. Phung Jieming Chen Aude-Hélène Capietto Ann-Jay Tong Christopher M. Rose Craig Blanchette Jennie R. Lill Benjamin Haley Lélia Delamarre Richard Bourgon Kai Liu Suchit Jhunjhunwala Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo Nature Communications |
| title | Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo |
| title_full | Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo |
| title_fullStr | Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo |
| title_full_unstemmed | Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo |
| title_short | Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo |
| title_sort | towards designing improved cancer immunotherapy targets with a peptide mhc i presentation model hlapollo |
| url | https://doi.org/10.1038/s41467-024-54887-7 |
| work_keys_str_mv | AT williamjohnthrift towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT nicolaswlounsbury towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT quadebroadwell towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT amyheidersbach towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT emilyfreund towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT yassanabdolazimi towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT quitphung towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT jiemingchen towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT audehelenecapietto towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT annjaytong towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT christophermrose towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT craigblanchette towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT jennierlill towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT benjaminhaley towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT leliadelamarre towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT richardbourgon towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT kailiu towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo AT suchitjhunjhunwala towardsdesigningimprovedcancerimmunotherapytargetswithapeptidemhcipresentationmodelhlapollo |