A common theme of Yasser’s research in the area of bioinformatics is the development and the application of state-of-the-art machine learning algorithms to decipher the underlying mechanisms controlling different types of macromolecular interactions including: antibody-antigen recognition; major histocompatibility complex (MHC)-restricted antigen recognition; protein-protein interactions; protein-nucleic acid interactions; and promoter recognition by RNA polymerase.
A complete let of past bioinformatics projects is available here. The vast majority of these projects focus on the development of prediction models using features extracted from amino acid sequence. Our future work will entail the development of more reliable prediction models by integrating other available types of information (e.g., protein structures or data from high-throughput experiments).
El‐Manzalawy, Y., Munoz, E. E., Lindner, S. E., & Honavar, V. (2016). PlasmoSEP: Predicting surface exposed proteins on the malaria parasite using semi‐supervised Self‐training and expert‐annotated data. Proteomics, 1-10.
Abbas, M., Mohie-Eldin, M., & EL-Manzalawy, Y. (2015). Assessing the effects of data selection and representation on the development of reliable E. coli sigma 70 promoter region predictors. PLoS One, 10(3):e0119721. doi: 10.1371/journal.pone.0119721
Walia, R. R., Xue, L. C., Wilkins, K., EL-Manzalawy, Y., Dobbs, D., & Honavar, V. (2014). RNABindRPlus: A Predictor that Combines Machine Learning and Sequence Homology-Based Methods to Improve the Reliability of Predicted RNA-Binding Residues in Proteins. PloS one, 9(5), e97725.
EL-Manzalawy, Y., Dobbs, D., & Honavar, V. (2011). Predicting MHC-II binding affinity using multiple instance regression. Computational Biology and Bioinformatics, IEEE/ACM Transactions on, 8(4), 1067-1079.