(4gf) Computational Biomolecular Discovery and Development

The discovery and development of novel therapies and materials is crucial for the continued well-being of modern society. Our ability to simulate the behavior of soft matter systems, predict molecular properties, and navigate chemical space is central to an efficient discovery and development process. My research focuses on the use of data science and computation to accelerate the discovery and development of organic and biological molecules for pharmaceutical applications. In this poster, I will provide an overview of my past and present work in biomolecular simulation, machine learning, and design of experiment. For instance, I will discuss the use of atomistic molecular dynamics simulations for the computation of drug binding free energies, the use of deep learning for drug formulation development, and the development of active learning algorithms for design of experiment.

Research Interests: My research interests lie at the interface of computer science with chemistry and biophysics. In particular, I am interested in how computer simulations and machine learning can be leveraged to accelerate and reduce the cost of developing new molecules and materials with medical and pharmaceutical applications.

Teaching Interests: I am interested in teaching physical and biophysical chemistry courses, such as thermodynamics and statistical mechanics. In addition, I would be particularly interested in teaching data science and machine learning courses for chemical engineers. At the graduate level, I would be keen to teach more specialised coursed in computational chemistry and biophysics, and machine learning for molecular sciences.

References:

[1] Aldeghi, M., Heifetz, A., Bodkin, M. J., Knapp, S. & Biggin, P. C. Accurate calculation of the absolute free energy of binding for drug molecules. Chem. Sci. 7, 207–218 (2016).

[2] Aldeghi, M., Heifetz, A., Bodkin, M. J., Knapp, S. & Biggin, P. C. Predictions of Ligand Selectivity from Absolute Binding Free Energy Calculations. J. Am. Chem. Soc. 139, 946–957 (2017).

[3] Aldeghi, M., Gapsys, V. & de Groot, B. L. Predicting Kinase Inhibitor Resistance: Physics-Based and Data-Driven Approaches. ACS Cent. Sci. 5, 1468–1474 (2019).

[4] Hase*, F., Aldeghi*, M. et al. Olympus: a benchmarking framework for noisy optimization and experiment planning. Mach. Learn. Sci. Technol. (2021). [* equal contribution]

[5] Aldeghi, M., Häse, F., Hickman, R. J., Tamblyn, I. & Aspuru-Guzik, A. Golem: An algorithm for robust experiment and process optimization. arXiv:2103.03716 (2021).