In this webinar, Gabriel Rocklin, Sara Volz, and Andra Campbell discuss how large-scale biophysical datasets and machine learning are advancing protein design. They will discuss how megascale biophysical experiments are being integrated with machine learning to improve protein design. The session will examine approaches for generating and analyzing large protein datasets using oligo pools, DNA sequencing, and mass spectrometry. Speakers will also discuss how these methods support prediction of protein stability and aggregation resistance while enabling the development of functional enzymes across previously unexplored sequence space.