I am a PhD student at the NYU Center for Data Science, advised by Kyunghyun Cho and Richard Bonneau. My work focusses on the application of generative modelling and self-supervised learning to molecular graphs and gene regulatory networks. Prior to joining NYU, I completed a Masters degree at the University of Cambridge under the supervision of José Miguel Hernández-Lobato.

Publications

Mahmood, O., Mansimov, E., Bonneau, R., Cho, K. Masked graph modeling for molecule generation. Nat Commun 12, 3156 (2021). https://doi.org/10.1038/s41467-021-23415-2 [ Paper | Code ]

Tjärnberg A, Mahmood O, Jackson CA, Saldi GA, Cho K, et al. (2021) Optimal tuning of weighted kNN- and diffusion-based methods for denoising single cell genomics data. PLOS Computational Biology 17(1): e1008569. https://doi.org/10.1371/journal.pcbi.1008569 [ Paper | Code ]

Mansimov, E., Mahmood, O., Kang, S., and Cho, K. Molecular Geometry Prediction using a Deep Generative Graph Neural Network. Sci. Rep., 9(1):1–13, 2019. doi:10.1038/s41598-019-56773-5. [ Paper | Code ]

Mahmood, O.; Hernández-Lobato, J. M. A COLD Approach to Generating Optimal Samples. CoRR, 2019, abs/1905.09885. [ Paper ]

Miscellaneous

Slides providing an introduction to variational autoencoders and their extensions.

Slides providing a brief survey of machine learning for chemical reaction prediction.