High-throughput screening of mAb formulations to identify sequence/excipient determinants of stability using machine learning
Project ID: 2531bc1591
(You will need this ID for your application)
Research Theme: Healthcare Technologies
Research Area(s):
Advanced manufacturing and clean growth
Healthcare Technologies
UCL Lead department: Biochemical Engineering
Lead Supervisor: Paul Dalby
Partner Organisation: Medimmune Limited
Stipend enhancement: £ 2,500
Project Summary:
Importance
There is a critical need for tools to enable predictions of formulations for new therapeutic monoclonal antibody candidates earlier in the development cycle.
Who we are
This project will be part of the UCL-AstraZeneca Centre of Excellence (CoE) that is a joint collaboration between University College London (UCL) and AstraZeneca. The department of Biochemical Engineering at UCL has pioneered high throughput formulation and protein stability analysis, as well as simulation and machine learning approaches to build predictive models for loss of antibody stability.
The project
The project will use high throughput automation to generate a rich monoclonal antibody formulation database unavailable anywhere else. The emerging data will then be used to generate statistical and machine learning models that are able to predict stability and viscosity for new formulations. Such predictive tools for formulation will significantly reduce the time taken to develop new monoclonal antibody products, and will also identify formulations for the challenging next generation of complex biological therapies.
Who you are
We are looking for someone keen to create a major impact on the ability of industry to bring the next generation of therapies to patients, and to treat a wide range of diseases. You will be trained in a unique combination of experimental and computational approaches to create a significant advance in the field of therapeutic protein formulation.