research/

My research sits at the intersection of machine learning, computational genomics, and precision medicine, where I work to develop novel computational approaches for disease diagnostics and treatment optimization. Through my work, I aim to bridge the gap between complex biological data and actionable clinical insights, particularly focusing on early disease detection.

Currently, my primary research focuses on developing multimodal deep learning frameworks for cancer diagnostics, specifically in lung adenocarcinoma. By integrating histopathological image analysis with genomic data, I’m working to create more accurate and robust prediction models for cancer-related mutations. This work has particular significance in resource-constrained healthcare settings, where access to comprehensive genetic testing may be limited.

My technical approach leverages advanced machine learning architectures, including attention mechanisms and graph neural networks, to process and analyze diverse biological data types. I’ve developed several novel methods for integrating multiple data modalities, such as combining gene expression profiles with high-resolution tissue data. This has led to improved accuracy in mutation prediction and better understanding of genotype-phenotype relationships.

Looking ahead, I aim to expand this work to other cancer types and diseases, while also incorporating additional data modalities such as clinical records and molecular profiles.

I am actively seeking research opportunities in computational genomics and ML-driven disease diagnostics. With experience in multimodal deep learning for cancer mutation prediction and a strong foundation in bioinformatics, I would welcome the chance to discuss potential collaborations or openings in your lab.