Using big data to classify antibodies and improve therapeutic drugs

UCB Pharma
University of Oxford

Aleksandr is developing new approaches to analyzing large datasets of antibody sequences, which may improve the effectiveness of identifying antibodies that potentially could be used as therapeutic drugs. Antibodies are proteins produced by our immune system, and have become increasingly used in the pharmaceutical industry because of their high specificity for binding specific cells or proteins. This gives them the potential to treat diseases including cancer, Alzheimer’s and multiple sclerosis, which involve the body’s own cells. Aleksandr’s research will provide ways of classifying and characterising antibodies, opening the door to drugs that are potentially more effective in targeting the causes of disease.

Creating a high-level system of antibody classification is important because it allows data from previous studies and databases to be combined. This means the antibody sequences with the greatest potential can be easily identified, leading to more efficient development of novel disease therapeutics. Aleksandr’s project has already resulted in an error-correction tool for using antibody data, and a meta-database of antibody datasets: his future work will continue to help researchers develop new drugs.

Aleksandr is completing a DPhil at Oxford University in the Department of Statistics, working in close collaboration with UCB Pharma via the DTP Icase SCHEME. He previously graduated with an MSc in Pharmacology from the University of Glasgow.

Aleksandr Kovaltsuk Thumbnail