Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo
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.
Authors
- Amy Heidersbach (ORCID: https://orcid.org/0000-0002-5601-2073)
- Richard Bourgon (ORCID: https://orcid.org/0000-0002-5890-4374)
- Suchit Jhunjhunwala (ORCID: https://orcid.org/0000-0003-3484-0588)
- Aude-Hélène Capietto (ORCID: https://orcid.org/0000-0002-6782-3867)
- Yassan Abdolazimi
- Emily Freund (ORCID: https://orcid.org/0009-0006-6103-4900)
- Craig Blanchette (ORCID: https://orcid.org/0000-0003-4560-9613)
- Jieming Chen (ORCID: https://orcid.org/0000-0003-3767-9486)
- Ann-Jay Tong (ORCID: https://orcid.org/0009-0003-8793-8025)
- Benjamin Haley (ORCID: https://orcid.org/0000-0002-0074-0020)
- Lélia Delamarre (ORCID: https://orcid.org/0000-0001-9122-5181)
- Qui Phung (ORCID: https://orcid.org/0000-0001-6472-4567)
- Jennie R. Lill (ORCID: https://orcid.org/0000-0002-7142-253X)
- William John Thrift (ORCID: https://orcid.org/0009-0004-5022-2119)
- Christopher M. Rose (ORCID: https://orcid.org/0000-0002-7502-3368)
- Quade Broadwell
- Nicolas Lounsbury (ORCID: https://orcid.org/0000-0002-5214-3404)
- Kai Liu (ORCID: https://orcid.org/0000-0002-3456-8281)
Institutions
- Intel (United States) (US)
- Gene Therapy Laboratory (FR)
- Freenome (United States) (US)
- Allen Institute for Artificial Intelligence (US)
- Artificial Intelligence in Medicine (Canada) (CA)
Publication Details
- Journal
- Nature Communications
- Published
- 2024-12-30
- DOI
- https://doi.org/10.1038/s41467-024-54887-7
- Citations
- 9
- Primary Topic
- vaccines and immunoinformatics approaches
- Type
- article
- Field-Weighted Citation Impact
- 2.10
Funders
- Genentech