Learning objectives

• Understand how extreme environments (temperature, pH, radiation) shape genome-wide compositional patterns in microbes.
• Learn how alignment-free, k-mer–based machine learning detects genomic signatures beyond traditional sequence alignment.
• Explore evidence of cross-domain genomic convergence between bacteria and archaea driven by shared environmental pressures.
• Discover how interpretable AI reveals codon usage biases and adaptive signals underlying survival in extreme conditions.

Speaker Bio

Dr. Gurjit S. Randhawa is an Assistant Professor in the School of Computer Science at the University of Guelph. His research integrates AI with comparative genomics to uncover evolutionary relationships and demonstrate how data-driven pattern discovery reveals mechanisms of biological adaptation and resilience across diverse life forms. He developed the Machine Learning with Digital Signal Processing (MLDSP) framework, an alignment-free method for rapid and scalable genome analysis. His work advances interpretable AI for metagenomics and extreme-environment biology, and extends to robotics and precision agriculture, integrating autonomous vision systems and multi-sensor intelligence for data-driven environmental monitoring and decision support.