Deep Dive into Machine Learning Models For Directed- Evolution Of Enzymes

Time: 3:40 pm
day: Day One


  • Discuss the increased interest in using machine learning to assist in enzyme redesign in the pharmaceutical industry
  • Benchmark the performance of prediction models built using an array of machine learning methods and protein descriptor types (sequence and structure-based) against a variety of datasets
  • Evaluate the results suggest that Convolution Neural Network models built with amino acid property descriptors could be the most widely applicable technique for enzyme reengineering