Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Predicting SARS-CoV-2 antibody escape using machine-learning guided protein engineering
Background
Antibodies represent a central component of the adaptive immune response, able to bind to virtually any foreign agent encountered by the host with high affinity and specificity to promote target neutralization and elimination. While advances in protein engineering have accelerated the development and approval of monoclonal antibody therapeutics across a range of disease indications, there remains a paucity of monoclonal antibodies approved to combat infectious diseases. This is in part attributed to the inherent challenge of optimizing antibody binding to dynamically evolving pathogens such as SARS-CoV-2, whose natural evolution has led to antibody escape. Thus, we reason that resistance to viral escape is another key antibody feature which must be systematically evaluated and optimized to effectively translate antibodies into the infectious disease space.
To address this challenge, the Reddy Group recently established a machine learning-guided protein engineering framework for predicting antibody escapability – the vulnerability of the antibody itself to being evaded by the targeted pathogen via evolution. This technology, termed deep mutational learning (DML), enables the functional impact of combinatorial mutations on viral protein function to be accurately forecasted by linking yeast display experimental screening with deep sequencing and machine learning. DML was used to accurately predict the phenotype of billions of SARS-CoV-2 receptor-binding domain (RBD) variants, enabling the prospective identification of key combinatorial mutations which catalyze escape from several classes of monoclonal antibodies.
For more information, please refer to the related publication: https://pubmed.ncbi.nlm.nih.gov/36150393/
Project description
We are currently looking for a highly motivated Master's student to join a research project that involves the application and expansion of DML for antibody escape profiling. The project will focus on two main areas: (i) evaluating promising SARS-CoV-2 antibodies in the therapeutic pipeline to assess their resistance to evolution, and (ii) analyzing germline-coupled pairs of antibodies obtained from SARS-CoV-2 patients to study the effects of affinity maturation on antibody escapability. This opportunity will provide students with hands-on experience in state-of-the-art experimental techniques such as FACS, yeast display, and next-generation sequencing. Additionally, students will gain proficiency in advanced computational methods, including biological sequence data analysis and deep learning.
The project will be conducted at the Laboratory for Systems and Synthetic Immunology led by Professor Sai Reddy, in the Department of Biosystems Science and Engineering in Basel.
If you are interested in applying, please send your CV and indicate your desired start date (preferably autumn/winter 2023) to Jiami Han at jiahan@ethz.ch.
Keywords: Deep mutational learning, affinity maturation, antibody, SARS-CoV-2, yeast library
The project will last preferably 6 months. All research takes place in the Lab for Systems and Synthetic Immunology at the ETH Zurich, Department of Biosystems Science and Engineering in Basel (https://bsse.ethz.ch/lsi) in the lab of Professor Sai Reddy. Students can expect to obtain experimental skills involving antibody expression, yeast display, high-throughput sequencing library preparation, computational skills in deep learning, and biological data analysis.
Related publication:
https://www.sciencedirect.com/science/article/pii/S0092867422011199
The project will last preferably 6 months. All research takes place in the Lab for Systems and Synthetic Immunology at the ETH Zurich, Department of Biosystems Science and Engineering in Basel (https://bsse.ethz.ch/lsi) in the lab of Professor Sai Reddy. Students can expect to obtain experimental skills involving antibody expression, yeast display, high-throughput sequencing library preparation, computational skills in deep learning, and biological data analysis. Related publication: https://www.sciencedirect.com/science/article/pii/S0092867422011199
Not specified
To apply, please send a CV, your earliest possible start date, and how long you plan to work on the project, and a brief cover letter regarding your interest and experience, to jiahan@ethz.ch).
To apply, please send a CV, your earliest possible start date, and how long you plan to work on the project, and a brief cover letter regarding your interest and experience, to jiahan@ethz.ch).