About
“The capacity to learn is a gift; the ability to learn is a skill; the willingness to learn is a choice.” — Brian Herbert
I am a PhD student in Computer Science at the University of Central Florida, working in the Computational Biology & Machine Learning Lab. My research sits at the intersection of deep learning, NLP, and computational biology — I build on methods from natural language processing to tackle problems in genomics, proteomics, and post-transcriptional gene regulation.
Research Interests
A central question driving my work: Can the same architectures that decode human language also decode the language of life? I explore how large language models can be adapted to understand genomic sequences, protein structures, and the regulatory mechanisms that govern cellular processes — with applications in drug discovery and cancer research.
I leverage advanced ML techniques including diffusion models, reinforcement learning, RLHF, retrieval-augmented generation (RAG), and classifier-free guidance (CFG) to model complex biological systems and generate novel therapeutic candidates.
Currently, I work on:
- Genome language models for polyadenylation site prediction
- Diffusion models for protein structure, function, and drug discovery
- Computational tools for alternative splicing and polyadenylation analysis
Background
Before starting my PhD, I was a Machine Learning Engineer at Reve Systems, where I built production NLP systems for Bangla — a low-resource language. I also served as a Lecturer at the University of Asia Pacific, and organized the first shared task on Violence-Inciting Text Detection at EMNLP 2023 (27 teams, 16 papers).
I completed my B.Sc. in Computer Science & Engineering from Shahjalal University of Science & Technology (SUST), graduating with distinction (CGPA: 3.79).
Feel free to reach out if you’d like to discuss research, collaboration, or anything related to my work.
Recent Updates
03/2026 Passed my PhD Qualifying Review at the University of Central Florida.
12/2025 Paper accepted! PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models accepted in Computational and Structural Biotechnology Journal (CSBJ), Elsevier, Q1, Impact Factor 5.2.
03/2025 New publication! Co-authored a comprehensive survey on Computational Methods for Alternative Polyadenylation and Splicing in Post-Transcriptional Gene Regulation published in Experimental & Molecular Medicine (Nature Publishing Group, Q1, IF 12.8). [6 citations]
08/2024 Started serving as Graduate Teaching Assistant for Introduction to Computer Concepts at UCF.
08/2024 Started PhD at University of Central Florida! Working on genome language models and diffusion models in proteomics.
04/2024 Our paper Data, Annotation, and Meaning-Making: Faith-Based Communal Violence has been accepted at ACM FAccT 2024! [9 citations]
04/2024 Our paper BnPC: A Gold Standard Corpus for Paraphrase Detection in Bangla has been accepted at BUCC Workshop @ LREC-COLING 2024! [4 citations]
02/2024 Started position as Lecturer at University of Asia Pacific, teaching Data Structures, OOP, and Software Development.
12/2023 Two papers accepted at BLP Workshop @ EMNLP 2023! Vio-Lens: Annotated Social Network Posts Leading to Communal Violence [30 citations] and BLP Shared Task 1: Violence-Inciting Text Detection [18 citations].
12/2023 Successfully organized the first shared task on Violence-Inciting Text Detection at BLP Workshop @ EMNLP 2023. 27 teams participated, 16 papers accepted.
07/2023 Started as Machine Learning Engineer at REVE Systems, working on Bangla grammatical and spelling error detection.
02/2023 Our paper garNER at SemEval-2023 Task 2: Knowledge Augmentation for Multilingual NER has been accepted at SemEval @ ACL 2023! Team garNER achieved Top 10 rankings in 10 tracks. [1 citation]
05/2023 Graduated from Shahjalal University of Science and Technology with B.Sc. in CSE (Distinction, CGPA: 3.79/4.00).