2022-02-18 14:00 ~ 16:00

• 零号湾460会议室

Human leukocyte antigen (HLA) can recognize and bind foreign peptides to present them to specialized immune cells and then initiate an immune response. Computational prediction of the peptide and HLA (pHLA) binding can speed up immunogenic peptide screening and facilitate vaccine design. However, there is lack of an automatic program to optimize mutated peptides with higher affinity to the target HLA allele. To fill this gap, we develop the TransMut framework composed of TransPHLA for pHLA binding prediction and an automatically optimized mutated peptides (AOMP) program, which can be generalized to any binding and mutation task of biomolecules. Firstly, TransPHLA is developed by constructing a transformer-based model to predict pHLA binding, which is superior to 14 previous methods on pHLA binding prediction, neoantigen and human papilloma virus vaccine identification. For vaccine design, the AOMP program is then developed by exploiting the attention scores generated by TransPHLA to automatically optimize mutated peptides with higher affinity to the target HLA and with high homology to the source peptide.

2022-02-18 14:00 ~ 16:00

• 零号湾460会议室

Personalized medicine, in which treatments are tailored to each individual patient, probably is transforming the way we treat disease. By considering the molecular profile of every patient, personalized medicine will potentially ensure a more successful outcome with a more favorable safety profile. The recent rapid development in high-throughput sequencing and profiling methods provides the opportunities to perform the measurement of such complex molecular profiles. For example, mass spectrometry (MS) plays a critical role in measuring quantitative proteome profiles of patients, providing one of the fundamental data for clinical diagnosis, prognosis and therapy. In this talk, I will describe a series of computational and statistical methods that we have developed for MS-based proteomics data. These methods encompass most of the critical steps in data analysis and can be used together as a workflow. In addition to generalized method development, we initiated the SysteMHC Atlas project, the first data respiratory dedicated to the public dissemination and analysis of immuno-peptidome data, which aims to identify novel signals that potentially alter immune responses to tumors and post-translationally spliced peptides that could be of significant importance as potential targets for cancer immunotherapy.