I am Anurag Limdi, a Machine Learning Scientist at European Bioinformatics Institute (EMBL-EBI) , where I build generative modeling to large-scale genetic and genomic datasets for drug discovery in rare diseases.
Research Interests
These days, I think about problems that span human genomics, protein design, molecular evolution, and applying machine learning to problems in biology. Trained as a systems biologist at the intersection of computational and lab science, I believe in deeply understanding the quirks and biases in biological datasets, particularly large genomics datasets, in order to build generalizable models.
My PhD Research
I got my PhD at Harvard with Michael Baym, I explored how bacterial genomes function and evolve, through a combination of high-throughput experiments, theory and computational approaches. My projects include:
- Mapping fitness landscapes over thousands of generations of the long-term evolution experiment, published in Science as co-first author (Code). Our paper got featured in Nature Reviews Genetics and I chatted with ScienceAdviser about what we found and implications for the field of evolutionary biology.
- Fitness assay design using theory, Monte-Carlo simulations to explore tradeoffs in design parameters (Paper, Code).
- Methods development for correcting for PCR-related artifacts in transposon sequencing experiments (Code).
- Modeling DNA-binding biases of the mariner transposon (Code).