Andreas Krause

Breaking the Synthesis Barrier for AI-Designed DNA Libraries

This paper introduces PGLD, an AI method that designs cost-effective DNA libraries for high-throughput experiments by optimizing synthesis-aware stochastic libraries.

Enhanced Sequence-Activity Mapping and Evolution of Artificial Metalloenzymes by Active Learning

This paper improves enzyme engineering by combining active learning and experimental screening to efficiently discover high-performing artificial metalloenzymes.

ChromaX: a fast and scalable breeding program simulator

ChromaX simulates genetic recombination and breeding value calculations using GPU acceleration, offering faster performance than existing tools.

Learning Single-Cell Perturbation Responses using Neural Optimal Transport

This paper introduces a method to predict single-cell perturbation responses using neural optimal transport, showing improved performance over existing methods on drug-treated cells.