Methods development

Encoder of a message-passing deep learning network.

With the growth in genomic data availability, there is a need for tools that scale better. I have been involved with the development of tools that enable scalable and reproducible simulations, within stdpopsim and tskit. More recently, I have been developing a deep learning method for population genetic inference that takes tree sequences, a scalable format for population genomic data, with Andrew Kern and Nate Pope

Efficient ancestry and mutation simulation with msprime 1.0
Expanding the stdpopsim species catalog, and lessons learned for realistic genome simulations

Murillo F Rodrigues
Murillo F Rodrigues
Computational Biologist

Researcher interested in evolutionary genomics and computational biology.