BIOS 442: Computational Applications of High-Throughput Protein Data for Machine Learning

Course Description

This course introduces computational approaches for analyzing high-throughput protein data. Students will gain hands-on experience working with gene expression matrices, protein sequence embeddings from pretrained language models, and subcellular localization features derived from microscopy images. Emphasis is placed on data preprocessing, exploratory analysis, and training simple machine learning models for tasks such as classification, function prediction, and data integration across modalities. The course is designed for PhD students with primarily experimental backgrounds who wish to develop practical computational skills for interpreting biological data.