Our lab focuses on developing algorithms to bridge between computer science and the life sciences. Our research contributions are in computational structural biology, biophysics, and bioinformatics. We investigate from a computational perspective problems concerning sequence, structure, dynamics, function, and interactions of biological molecules. >
Our methods build on probabilistic search, optimization, and machine learning approaches, often combining ideas from sampling-based robot motion planning and evolutionary computation. Our research projects are diverse, detailed under Research. Highlights include:
Evolutionary Search Strategies for Sampling Local Minima of the Protein Energy Surface:
- This work appears in: Brian Olson and Amarda Shehu. Evolutionary- inspired Probabilistic Search for Enhancing Sampling of Local Minima in the Protein Energy Surface. Proteome Science 2012, 10 (Suppl1): S5.
Probabilistic Path Sampling to Connect Protein Functional States:
- This work appears in: Kevin Molloy and Amarda Shehu. A Robotics-inspired Method to Sample Conformational Paths Connecting Known Functionally-relevant Structures in Protein Systems Comput Struct Biol Workshop (CSBW), Philadelphia, PA, 2012.
Evolutionary- and Geometry-driven Search of Protein-protein Structural Assemblies:
- This work appears in: Irina Hashmi, Bahar Aklbal-Delibas, Nurit Haspel, and Amarda Shehu. Guiding Protein Docking with Geometric and Evolutionary Information. J Bioinf and Comp Biol 2012, 10(3): 1242008.
Adaptive Probabilistic Tree-based Search to Sample Conformations of the Protein Native State:
- This work appears in: Brian Olson, Kevin Molloy, and Amarda Shehu. In Search of the Protein Native State with a Probabilistic Sampling Approach. J Bioinf and Comp Biol 2011, 9(3):383-398.
Evolutionary Algorithms For Feature Generation and SVM Kernel Optimization:
- This work appears in: Uday Kamath, Jack Compton, Rezarta Islamaj Dogan, Kenneth A. De Jong, and Amarda Shehu, An Evolutionary Algorithm Approach for Feature Generation from Sequence Data and its Application to DNA Splice-Site Prediction, Trans Comp Biol and Bioinf 2012, 9(5):1387-1398.
Spatially-structured Evolutionary Algorithms for Parallel Machine Learning:
- This work appears in: Uday Kamath, Johan Kaers, Amarda Shehu, and Kenneth A. De Jong. "A Spatial EA Framework for Parallelizing Machine Learning Methods." Intl Conf on Parallel Problem Solving From Nature (PPSN), LNCS vol. 7491, pg. 206-215, Taormina, Italy, 2012.