William Andreopoulos

William Andreopoulos serves as an Assistant Professor in the Department of Computer Science at San José State University's College of Engineering. With a strong interdisciplinary background spanning computer science, bioinformatics, and molecular biology, he bridges computational methods with biological applications. His academic journey has taken him through prestigious institutions including Lawrence Berkeley National Laboratory, Columbia University, and TU Dresden.

• Ph.D. in Computer Science and Engineering, York University, Toronto, Canada (2006)
• M.Sc. in Computer Science, University of Toronto, Canada (2001)
• B.Sc. in Computing and Software, McMaster University, Canada (1999)

Dr. Andreopoulos specializes in applying machine learning and computational approaches to biological problems, with particular emphasis on genomics, metagenomics, and bioinformatics. His research spans fungal genomics, microbial community analysis, plasmid identification, and the development of tools for omics data integration. He has extensive experience working with environmental data as well as cancer datasets from PCAWG and TCGA projects.

His publication record reveals a strong interdisciplinary focus, with recent work spanning from fungal genomics and microbial identification to natural language processing applications. The research demonstrates consistent integration of machine learning techniques across diverse biological contexts, with notable contributions in developing computational pipelines for high-throughput sequencing data analysis.

As an educator, Dr. Andreopoulos has mentored numerous graduate students through CS297/CS298 projects and CS280/CS180 courses, with students working on bioinformatics-related computational projects. His professional experience includes 8 years as a data scientist at the Joint Genome Institute, Lawrence Berkeley National Laboratory, where he developed software pipelines for automated processing of high-throughput sequencing data.

His laboratory focuses on computational biology projects that require expertise in Java, Python, Linux command line, machine learning libraries, and data visualization tools. Current research directions include strain separation in microbial communities, plasmid identification, 16S sequence reconstruction, and deep learning applications to molecular biology problems.