Volgenau School of Engineering

Amarda Shehu, PhD


PhD, Computer Science, Rice University

Key Interests
Artificial Intelligence | Generative Models | Bioinformatics | Biophysics | Molecular Modeling | Structure Prediction | Molecular Design | Cancer | Macromolecular Docking

Research Focus

My research focuses on novel algorithms to bridge between computer and information science, engineering, and the life sciences and emphasizes problem solving in AI, search, planning, and optimization for high-dimensional and non-linear variable spaces, and machine learning for the simulation, analysis, and characterization of complex dynamics systems operating in the presence of constraints. Application domains are diverse and span from bioinformatics and computational biology, to computer-aided engineering design, and human-machine teaming. In the computational biology domain, I work on linking molecular sequence to structure, dynamics, and function. Several projects in my laboratory focus on elucidating disease mechanisms at a molecular level via characterization of wildtype and pathogenic variants, as well as leveraging of experimentally-available data for synthesis of novel therapeutics. Our research is highly interdisciplinary and is supported by various NSF programs, including Intelligent Information Systems, Computing Core Foundations, and Software Infrastructure, as well as state and private research awards.

Current Projects

■ Mapping protein energy landscapes to elucidate stable and meta-stable structural states and activity-modulating structural rearrangements

■ Mining of computationally-obtained energy landscapes of wildtype and pathogenic protein variants to elucidate the impact of mutations on structure, dynamics, and dysfunction

■ In-silico synthesis of novel antimicrobial peptides to combat antibiotic resistance

■ Improving decoy generation and decoy selection to advance template-free protein structure prediction

Select Publications

W. Qiao et al., From mutations to mechanisms and dysfunction via computation and mining of protein energy landscapes. BMC Genomics 19(Suppl 7), 671 (2018).

D. Veltri et al., Deep learning improves antimicrobial peptide recognition. Bioinformatics 34(16), 2740- 2747 (2018).

N. Akhter & A. Shehu, From extraction of local structures of protein energy landscapes to improved decoy selection in template-free protein structure prediction. Molecules 23(1), 216 (2018).

T. Maximova et al., Sample-based models of protein energy landscapes and slow structural rearrangements. Journal of Computational Biology 25 (2018).


Nguyen Engineering Building | 4511 Patriot Circle, Fairfax, VA 22030