Dr.
Elena Xerxa

Elena Xerxa received a diploma in Cellular and Molecular Biology and a PhD in Functional and Structural Genomics from the International School of Advanced Studies (SISSA) in Trieste, Italy. During her studies she collaborated with prestigious academic institutions, including the Karolinska Institute in Stockholm, Sweden, where she spent approximately two months as a visiting scientist.

Following her PhD, she was a postdoc at the International Centre of Genetic Engineering in Trieste, Italy. In this position, she investigated the molecular effects of protein kinase inhibitors on various types of leukemia using both classical biochemistry and high-throughput transcriptomic analysis.

Alongside her primary focus on biology, during her research experience she matured a keen interest in computational biology. In 2020, she decided to further explore this passion by enrolling in the Life Science Informatics Master’s program in Bonn. Elena conducted her master’s thesis project at Professor Bajorath’s group, successfully obtaining her diploma in April 2023.

Currently, she continues her research journey in Bajorath’s group as a Research Fellow, with a primary research focus on medicinal chemistry, Machine Learning, and the development of computational methods for drug discovery. Beside this, she has the role of Life Science Area Coordinator at Lamarr Institute.

Current research topics:

• Systematic investigation and definition of the best practices for chemical data curation to enhance the reliability of Machine Learning (ML) and deep learning (DL) models.
• Shedding light on the molecular features learned by ML and DL models in tasks related to small drug molecule activity and/or property prediction.
• Exploring structural-activity relationships of protein kinase inhibitors to rationalize their interaction with protein targets and support kinase drug discovery.

Special interests:

Utilizing computational data analysis, ML, and Artificial Intelligence (AI) algorithms in drug discovery and related bio-chemical field, with a specific emphasis on enhancing interpretability and explainability of black-box models.