Mehdi Yazdani-Jahromi
Computer Science PhD Student at University of Central Florida

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.
News
Jan 22, 2025 | Our paper, “HELM: Hierarchical Encoding for mRNA Language Modeling,” has been accepted to ICLR 2025. Our work introduces a novel approach to understanding mRNA sequences by leveraging hierarchical language modeling, outperforming existing baselines by ~8% across six downstream property prediction tasks. Check out the paper at: arXiv |
---|---|
Sep 25, 2024 | Our paper, “Fair Bilevel Neural Network (FairBiNN): On Balancing Fairness and Accuracy via Stackelberg Equilibrium,” has been accepted to NeurIPS 2024. We introduce a novel bilevel optimization approach to enhance fairness in machine learning, achieving superior results on key datasets. |
Apr 20, 2024 | I will be presenting our work at RECOMB 2024 in Cambridge Boston at MIT campus! Join me on the 30th of April from 14:00 - 14:55 as I present our paper titled “FragXsiteDTI: Revealing Responsible Segments in Drug-Target Interaction with Transformer-Driven Interpretation.” |
Dec 22, 2023 | Thrilled to announce that our paper (FragXsiteDTI) has been accepted at RECOMB 2024, following its acceptance at the NeurIPS 2023 AI for Drug Discovery and Development Workshop! ![]() ![]() |
Dec 11, 2023 | We are excited to unveil DeepDrugDomain, an advanced Python toolkit tailored for enhancing drug-target interaction and drug-target affinity prediction through deep learning. GitHub Link |
Latest Posts
Selected Publications
-
- In International Conference on Research in Computational Molecular Biology , 2024