Manolis Kellis

Manolis Kellis is a computational biologist whose research spans genomics, AI-driven drug discovery and protein foundation models. He spent most of his childhood in Athens, earned MIT's B.S., S.M., and Ph.D. in 1999, 2000, and 2003, completed a postdoctoral fellowship at the Broad Institute, and joined the MIT faculty in 2004. His group led integrative analysis for modENCODE, and he received the 2010 PECASE and the 2011 Niki Award. He coauthored the 2015 analysis of 111 reference human epigenomes and the 2024 protein foundation model ProCyon. As of October 2026, he is a professor of computer science at MIT, a member of CSAIL and the Broad Institute, and directs MIT's Computational Biology Group; his research also includes Mantis, a cognitive cartography platform.

Now at: Broad Institute and MIT CSAIL
Born: 1977
Badges: Loyal

Years link to their sources.

Timeline

By 2003

Athens childhood and MIT degrees

He spends most of his childhood in Athens. At MIT, he earns a B.S. in 1999, an S.M. in 2000, and a Ph.D. in computer science in 2003.
2003–2004

Broad postdoc and MIT faculty

He works as a postdoctoral fellow at the Broad Institute of MIT and Harvard from 2003 to 2004. He joins the MIT faculty in 2004 and becomes a member of CSAIL and the Broad Institute.
2009–2010

Integrative analysis for modENCODE

His group receives an NIH award in September 2009 to lead integrative analysis for modENCODE. Its analysis papers appear in Science and Nature in December 2010.
2010

A Presidential Early Career Award

He receives the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2010.
2011

The 2011 Niki Award

He receives the 2011 Niki Award from Athens Information Technology for his research into the human genome at the MIT Computational Biology Group.
2015

The 111 epigenome analysis

He coauthors the 2015 integrative analysis of 111 reference human epigenomes. The study profiles histone modification patterns, DNA accessibility, DNA methylation, and RNA expression.
2024

ProCyon for protein phenotypes

In 2024, he coauthors ProCyon, a foundation model that predicts protein phenotypes across five knowledge domains. It processes interleaved protein and natural-language inputs and uses ProCyon-Instruct, a dataset of 33 million protein-phenotype instructions.
As of October 2026

Professor and lab director

On January 6, 2025, he appears on MIT CSAIL's Building 32 podcast to discuss AI and human-AI collaboration. In 2026, he advises an MIT SuperUROP project on the effects of APOE genotypes on development and aging in the brain, listed under AI for Healthcare and Life Sciences and Artificial Intelligence and Machine Learning. As of October 2026, he is a professor of computer science at MIT, a member of CSAIL and the Broad Institute, and directs MIT's Computational Biology Group; his research spans computational biology, genomics, AI-driven drug discovery, and the development of Mantis, a cognitive cartography platform.