Decoding Life Science with Data

Dr. Yennamalli grew up in a family of artists and educators who encouraged discussion without worrying about taboo. As a young child, he would collect caterpillars from his garden and study their development. This early interest in biology was bolstered by Dr. Yennamalli’s excellent schoolteacher, whose teaching methods he has incorporated in his own pedagogy. School provided him an opportunity to visit the Topslip wildlife sanctuary, where he was exposed to India’s amazing biodiversity. When he was later confronted with the choice of his undergraduate studies, he was once again inspired by his teacher to pursue microbiology. We like to think that great scientists are forged in the lecture halls of great universities or in labs. While that is true, we’ve observed a repeating pattern of great scientists being inspired to pursue biology by their schoolteachers. We must ensure that this fact doesn’t go underappreciated.

What began as an exploratory foray into computational biology at JNU turned into a lifelong career for Dr Yennamalli. He believes that computational biology is indispensable for answering some of our most challenging questions. It allows us to collect enormous amounts of data over a long period of time. This deluge of data hides within it solutions to difficult problems. If we analyse the data well, those insights could be ours. If any scientist wants to access this goldmine of data, Dr. Yennaamlli recommends starting with learning Python. Data for computational analysis can’t be generated without experiments. To ensure that collaboration between experimental and data scientists is fruitful, he recommends that the insights of computational biologists should be included in experimental design itself. On the other hand, computational biologists can be more empathetic to the challenges that experimental scientists face if they’re aware of how experiments are done. Collaboration is always a two-way street.

Dr Yennamallai, being a computational biologist, we couldn’t resist asking him what he thinks the role of AI will be in biology. He sees AI as a tool which can speed up work for researchers. He is optimistic that AI-driven high-throughput data analysis is coming. He envisions a future where agentic systems would be deeply ingrained in research, right from the level of hypothesis generation. But he cautions against blindly trusting AI. He emphasises that, at least for the near future, AI must be supervised by humans, and its outputs need to be verified by scientists. Science runs on scepticism, which should naturally extend to AI as well.

Dr Yennamalli’s insights are too voluminous to summarise in a short

blog. We invite you to watch the full podcast here: https://www.youtube.com/watch?v=hjX1twfILcI

Blog Written by Deven Matkari