AI & Computational Biology Researcher | Medicinal Science Enthusiast | Innovator

I'm a passionate student researcher at Argonne National Laboratory, specializing in AI for genomics and computational biology. My focus is on leveraging artificial intelligence to drive innovation in medicine, ranging from gene sequence interpretation to mutation prediction and drug discovery.

Developed a novel method to analyze genetic data by creating biologically relevant representations with large language models.

• Key Contributions: Introduced Codon-Pair Encoding (CPE), a new representation that is faster, more accurate, and biologically meaningful, improving performance for over 2,500 researchers.
• Technology: Genome-scale language models, Python, TensorFlow.

Created GeneNN, which converts genetic sequences into graph-based representations to enable distributed and parallel training, improving scalability and performance in genomic data analysis.

• Key Contributions: Enhanced AI models for large-scale genomic analysis, enabling efficient training on graph structures.
• Technology: Graph Neural Networks (GNNs), Python, PyTorch.

Designed an innovative approach to convert genomic sequences into image data, applying Vision Transformers to improve genetic sequence analysis.

• Key Contributions: Achieved better accuracy in analyzing sequences by using image-based AI models, allowing for a more detailed capture of genetic information.
• Technology: Vision Transformers (ViT), Python, Keras, TensorFlow.

Developed MethylFormer, an AI-driven tool that improves the accuracy of methylation site prediction—crucial for cancer detection and epigenomic research.

• Key Contributions: Enhanced the speed and accuracy of identifying DNA methylation sites with AI models, leading to faster insights into cancer-related epigenetic markers.
• Technology: AI for biological sequences, Python, PyTorch, deep learning.

Created an AI-based model to simulate the natural evolution of gene sequences and predict beneficial mutations without requiring detailed prior knowledge of gene function.

• Key Contributions: Reduced the number of experimental rounds needed in gene function research, enhancing the efficiency of mutation predictions for various biological systems.
• Technology: AI-driven mutation prediction, Python, TensorFlow.

Developed an iterative method for phase-field simulations within the MEUMAPPS framework, achieving a 1500x reduction in computation time.

• Key Contributions: Significantly accelerated simulations related to materials science, improving the efficiency of research workflows in the domain.
• Technology: Symbolic regression, phase-field modeling, Python.

• 2024 International Research Olympiad Finalist (Top 15/1000+)
• HOSA 2023 ILC Dallas, TX: Top 10 in Biochemistry, Medical Math, Leadership
• Presidential Volunteer Service Award (Gold) for 250+ hours of biomedical and medical volunteering
• 2024 Riley’s Way Youth Leader (1/100 selected nationally)
• Georgia Junior Science Symposium Biomedical Finalist (10/100 in the state)
• Certified Phlebotomy Technician - National Healthcareer Association
• CS50x: Introduction to Computer Science - Harvard University
• CS50P: Programming with Python - Harvard University
• CS1301: Introduction to Computing - Georgia Tech
• Good Clinical Practice - National Institute on Drug Abuse
• CPR/AED/First Aid - American Red Cross
• Health Service, Medical Terminology I & II - Hometown Health

• Programming Languages: Python, JavaScript, SQL
• Frameworks: TensorFlow, PyTorch, Keras
• AI & Machine Learning: Deep Learning, Natural Language Processing, Vision Transformers
• Biological Data Analysis: Genomics, Epigenetics, Mutation Prediction
• Tools: Git, Docker, Jupyter, Pandas, SciPy, NumPy