Mehdi Yazdani-Jahromi

I’m Mehdi Yazdani-Jahromi, a Ph.D. candidate in Computer Science at the University of Central Florida, where I specialize in AI for computational biology, with a focus on representation learning, sequence modeling.

My research aims to bridge deep learning and biology by developing models that capture the underlying structure of genomic data. I am the lead author of several published works, including HELM (Hierarchical Encoding for mRNA Language Modeling), which introduces a novel approach to modeling mRNA sequences using biologically informed hierarchical priors. I’ve also developed FragXsiteDTI, a fragment-level interpretable model for drug-target interaction prediction, and FairBiNN, a framework for balancing fairness and accuracy via bilevel optimization.

My work has been published at top venues such as NeurIPS and ICLR and has gained attention from national media outlets and academic institutions for its impact on drug discovery and ethical AI. I’ve had the opportunity to collaborate with industry leaders during research internships at Johnson & Johnson, applying AI to real-world problems in therapeutic development.

I’m passionate about building transparent, biologically grounded AI systems and expanding the capabilities of machine learning to drive discovery in the life sciences.