Machine Learning in Computational Biology Fall 2024

Explore the intersection of machine learning and computational biology through this comprehensive lecture series taught by Manolis Kellis and Eric Alm. Master fundamental and advanced techniques for analyzing biological data, starting with expression analysis, clustering, and classification methods before progressing to single-cell analysis and sequence alignment algorithms. Delve into epigenomics and Hidden Markov Models, then examine regulatory circuitry and biological networks. Learn protein structure prediction, folding algorithms, and modern transformer-based approaches for protein analysis. Discover protein and DNA language models, convolutional neural networks for genomic data, and their applications in computational biology. Investigate drug development processes, chemistry-focused graph neural networks, and molecular generation techniques. Understand neural network training principles specifically for biological applications. Examine disease genetics through genome-wide association studies, polygenic risk scores, and disease mechanism analysis. Explore electronic health records analysis, comparative genomics, and evolutionary biology concepts. Conclude with metabolic modeling and computational metabolomics approaches for understanding cellular processes and biochemical pathways.