AI-enabled design of aptamer sensors


DNA aptamers, small sequences of single-stranded DNA, offer a potential powerful tool for biological sensors, cell therapies, immunotherapy as well as alternatives to antibodies in therapies, and as specific markers for testing or sorting viral particles or exosomes. Aptamers can broaden the application of biosensors, be massively synthesized via chemical progress offering more cost-effective biosensor fabrication, are more robust, can be used in a wide range of assay conditions, and offer fabrication versatility. COVID-19 represents a clear and compelling case for rapid innovation in diagnostic testing data in order to minimize the spread, treat the disease and inform policy and action. The project is a collaboration with McGill University and the NRC. McGill University brings expertise in computational-theoretical chemistry and applies artificial intelligence (AI) methods to problems in the molecular sciences. The NRC provides AI expertise in biological and biomedical problems. In addition, McGill will collaborate directly with the University of Ottawa to develop AI methods to augment and speed up aptamer design. The University of Ottawa will provide expertise in experimental development of aptasensors for COVID-19 diagnostics.

Project team

Dr. Lena Simine

Dr. Lena Simine is an assistant professor in the Chemistry Department at McGill University in Montreal, Canada. Her expertise is in development of computational simulations of chemical phenomena evidenced by a solid track record of high-calibre publications. As an independent researcher at McGill, she is focussed on adapting artificial intelligence algorithms for simulations of disordered molecular systems.

Dr. Miroslava Cuperlovic-Culf

Dr. Miroslava Cuperlovic-Culf is a senior research officer and team lead at the National Research Council of Canada. Her research interest lies in the application of machine learning and data mining to life sciences with particular focus on the development of novel diagnostic and treatment methods and simulation methods for in silico medicine. Her unique training in both experimental and data sciences for molecular and high-throughput data analysis allows her to work very productively with experimentalists, clinicians, computer scientists and mathematicians.

Find out more about Dr. Cuperlovic-Culf.