https://mazziotti.uchicago.edu/emc2/tags/machine-learning/ Recent content in Machine Learning on E=mc² Hugo en-us Wed, 31 Dec 1969 18:33:45 -0600 https://mazziotti.uchicago.edu/emc2/years/2025/ahdout_j/ Wed, 31 Dec 1969 18:33:45 -0600 https://mazziotti.uchicago.edu/emc2/years/2025/ahdout_j/ <p>Many promising drug candidates fail because they are broken down too quickly by the body before they can have a therapeutic effect. Predicting metabolic stability early in the drug development process is therefore an important challenge, but available experimental data is often limited. In this project, I explored whether machine learning models could improve these predictions by learning meaningful representations of molecular structure from millions of compounds. Using variational autoencoders and chemical fingerprints, I developed a framework that provides additional context for data-sparse property prediction and helps identify molecules with favorable metabolic stability.</p>