Deep Learning, Bioinformatics, Computer Vision
Ali Heydari is an Applied Mathematics Ph.D. student and a graduate research assistant at UC Merced. His research lies at the intersection of deep learning, computer vision, and bioinformatics, but he is also very interested in natural language processing and machine learning in general. The goal of m his research is to develop computational methods for better downstream analysis of treatments (and personalized treatments). To achieve this, he has used a deep generative model to generate realistic synthetic single-cell data. Creating realistic in-silico data will help scientists with more robust analysis and more reproducible research. The next aspect of his research focuses on developing large-scale deep learning models for predicting the absorption, distribution, metabolism, excretion, and toxicity (ADME-Tox) of drugs in patients. They plan to help researchers predict the ADME-Tox of treatments by developing a large-scale pre-trained deep learning model that can be fine-tuned with a limited amount of data to meet the needs of specific tasks.