Joshua Kangas

Papers

Total Citations

H-Index

About

Joshua Kangas is a leading researcher at the intersection of machine learning, laboratory automation, and high-throughput biological experimentation. His work centers on developing intelligent systems that can autonomously design, execute, and monitor experiments, dramatically accelerating the pace of scientific discovery. Kangas’s major contributions include pioneering active machine learning-driven experimentation to determine compound effects on protein patterns, a method that reduces the need for separate, costly biological screens by intelligently selecting which experiments to perform next. This foundational work has garnered 57 citations and established a new paradigm for data-driven experimental design. More recently, Kangas has advanced the field of automated laboratory safety and monitoring, introducing deep video anomaly detection to ensure the reliability and precision of robotic workflows. His 2025 paper on this topic, already accumulating 5 citations, addresses a critical but overlooked challenge in fully automated experimentation. By integrating computer vision with robotics and machine learning, Kangas is not only improving experimental efficiency but also building the trust necessary for widespread adoption of autonomous laboratories. His work is essential reading for anyone interested in the future of AI-driven scientific discovery.