• Martin Steinegger

Abstract: Protein analysis has witnessed a revolution through machine-learning methods. At the forefront are highly accurate structure prediction methods such as AlphaFold2 and ESMFold. These have generated an avalanche of publicly available protein structures. The AlphaFold database and ESMatlas contain over 214 and 620 million predicted structures, respectively, covering nearly every protein sequence in our largest protein reference databases. This unprecedented access to structural information is not just critical for structural biology but impacts most fields of biology. In this talk, I will discuss how this data is revolutionizing genomic and proteomic annotations and introduce fast and sensitive methods to search and cluster this data to extract new biological insights.