My research interests are in Computational Functional Genomics and Computer Science Education.
A Modular Pipeline for Computational Prediction of Imprinted Human Genes
We inherit a maternal and a paternal copy of each gene. Both copies are usually functional. However, in the case of imprinted genes, only one copy is expressed while the other is silenced, according to its parent-of-origin. These genes have often been implicated in many diseases and developmental disorders. Experimental identification being a complex time-consuming process, we propose using machine learning algorithms to screen candidate genes. We present a modular pipeline to download publicly available data, extract novel epigenomic and genomic features, select the most discriminative features and finally classify the genes in order to predict their imprinted status.
Publications
-
Epigenetic maturation in colonic mucosa continues beyond infancy in mice.
Kellermayer R, Balasa A, Zhang W, Lee S, Mirza S, Chakravarty A, Szigeti R, Laritsky E, Tatevian N, Smith CW, Shen L, Waterland RA.
Human Molecular Genetics, 2010. - Epigenomic profiling indicates a role for DNA methylation in early postnatal liver development.
Waterland RA, Kellermayer R, Rached MT, Tatevian N, Gomes MV, Zhang J, Zhang L, Chakravarty A, Zhu W, Laritsky E, Zhang W, Wang X, Shen L.
Human Molecular Genetics, 2009.
Posters
- A Modular Pipeline for Computational Prediction of Imprinted Human Genes.
Grace Hopper Conference, 2010 (Winner ACM Graduate Student Research Competition) - Teaching Across Boundaries: Classes in the Online Environment.
Grace Hopper Conference, 2010
Other Research Projects
- Classification of Imprinted Genes. (Technical Report)
- Exploring the Co-occurrence of DNA Methylation and Histone Modifications. (Technical Report and the Methylation Viewer)
- Handwritten Digit Classification. (Technical Report)
