Using artificial intelligence to understand how diseases alter human cells and to help identify new drugs and treatments is the ambition behind a new research direction being launched at INSAIT, part of Sofia University “St. Kliment Ohridski” in Bulgaria.
The new research direction will be led by Dr. Aleksandrina Goeva, an internationally recognised Bulgarian scientist with extensive research experience in the United States and Canada.
She is returning to Bulgaria from the University of Toronto, where she founded and led her own research group in machine learning and computational biology. Before that, she spent seven years at the Broad Institute of MIT and Harvard.
At INSAIT, she will have the opportunity to continue her research while contributing her knowledge and experience to the development of Bulgarian science and technologies with potential applications in medicine. The new research direction will bring together advances in artificial intelligence, mathematics and biology to address an important question in modern medicine: how to identify disease-related changes at an earlier stage and help restore cells to healthy functioning.
The research will focus on AI’s ability to analyse large volumes of biological data and identify patterns that may remain undetected using conventional methods.
This could help researchers predict how cells respond to different drugs and identify compounds or combinations with the greatest therapeutic potential. This is particularly important because the number of possible combinations is virtually limitless, while laboratory experiments can investigate only a small proportion of them.
Aleksandrina Goeva began her scientific career in Bulgaria. She graduated from the Sofia High School of Mathematics and studied Applied Mathematics at Sofia University. She continued her education in the United States, earning a master’s degree in Mathematics and a PhD in Statistics from Boston University.
Her research has been published in leading scientific journals, including Science, Cell, Nature Biotechnology, Nature Communications and Cell Reports. According to Google Scholar, her work has received more than 7,200 citations.
She also developed HiDDEN, a machine learning method that identified previously overlooked cellular changes associated with blood cancer development and dysfunction of the blood-brain barrier. Her work provides new opportunities for studying disease mechanisms and improving the understanding of serious medical conditions.






