[초청강연] 현대생물학 콜로퀴움 - Mega-scale in-silico structure predictions

Title: Mega-scale in-silico structure predictions

◈Speaker: Assistant Prof. Martin Steinegger (School of Biological Sciences, SNU)

The protein folding problem, where you try to predict the 3D structure from a string of amino acids, is one long-standing fundamental problem in biology. Recent advances in machine learning and computational methods enabled our method AlphaFold2 [1] to predict structures at a margin of error similar to crystal structures. Its performance was validated in the most recent Critical Assessment of protein Structure Prediction (CASP) [2,3]. We are expecting a many order of magnitude increase in available structures due to this technology. To extract new insights from this structures we need tools to efficiently analyze them. In this talk we will discuss AlphaFold2 and propose method we develop to compress, organize and compare millions of novel protein structures.


[1] John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Kathryn Tunyasuvunakool, Olaf Ronneberger, Russ Bates, Augustin Žídek, Alex Bridgland, Clemens Meyer, Simon A Kohl, Anna Potapenko, Andrew J Ballard, Andrew Cowie, Bernardino Romera-Paredes, Stanislav Nikolov, Rishub Jain, Jonas Adler, Trevor Back, Stig Petersen, David Reiman, Martin Steinegger, Michalina Pacholska, David Silver, Oriol Vinyals, Andrew W Senior, Koray Kavukcuoglu, Pushmeet Kohli, Demis Hassabis (2020) High Accuracy Protein Structure Prediction Using Deep Learning, CASP14

[2] J Moult, J T Pedersen, R Judson, K Fidelis (1995) A large-scale experiment to assess protein structure prediction methods, Proteins, doi: 10.1002/prot.340230303

[3] https://predictioncenter.org/casp14/