***  PLEASE NOTE  THIS MEETING HAS BEEN POSTPONED  ***

Artificial intelligence touches every aspect of our lives whether we realise about it or not. Researchers are exploiting AI in a variety of ways including pilot driverless cars and autonomous robotics systems, algorithms to help doctors diagnosing patients, models to help predict and discover new materials, or new tools to enhance trust and security in communication and financial operations. AI is also revolutionising the de novo design of proteins, protein drugs and small molecular drugs. With all its usefulness though, AI needs to be augmented by physics-based methods in order to deliver physical insight.

Determining how the initial linear sequence of amino acids that comprise a protein dictates the specific and complex structure that it folds intoand finding the underlying principles that lead proteins constituted of almost entirely different residues to fold into similar structures has been a grand challenge in biology until recently. Likewise, understanding finely orchestrated protein-protein interactions is crucial and at the heart of virtually all fundamental cellular processes. Altering these processes or encoding new functions in proteins have been a long-standing goal in computational protein design. These methods commonly rely on scoring functions that seek to identify amino acid sequences that optimize structural configurations of atoms while minimizing a variety of physics-based and statistical terms. The objectives of most computational design protocols have focused on obtaining a predefined structural conformation. The design of functional proteins based solely on computational calculations or routinely introducing a functional aspect on protein design remains a challenge, but AI is transforming the field. The AI system AlphaFold is the best-known example recognised as a solution to the folding grand challenge. This breakthrough demonstrates the impact AI can have on scientific discovery. For drug discovery, there are possibilities but also challenges since AI tools cannot help with realising new targets and rely on multitude of data that is not always available.

While structural analysis and site-directed mutagenesis offer critical insights into the principles underlying protein folding and how physicochemical details determine structure-activity relationships, the de novo design of functional proteins place the understanding of the underlying basic principles to complementary and critical tests. Ultimately, the ability to create proteins with novel functions is transformative allowing researchers to make structurally new proteins that function as therapies or to develop synthetic biology approaches to enable complex engineering efforts e.g. in plant systems for applications in agriculture and sustainability, and other protein-based biotechnologies. Recent advancements in computational techniques, such as machine learning, Internet of Things (IoT), and big data, accelerate the deployment of new avenues in various of these applications. In parallel, improvement in both scale and accessibility of physics-based methods enables us to study enzymes more accurately which is also important for enzyme design.

This workshop will be dedicated to bringing together diverse speakers working in protein design and bioengineering who employ both experimental and computational approaches, primarily but not exclusively artificial intelligence (AI). The workshop will provide a premier interdisciplinary platform for researchers to present and discuss the most recent innovations, trends, and concerns as well as practical challenges encountered, and solutions adopted in the de novo design of proteins, protein drugs and small molecular drugs.. Beyond biotechnological applications, study how diverse metabolisms evolved in animals, plants and microbes and their impact on the environment is crucial in aspects as diverse as antibiotic resistance,regulation of gene expression, post-translational modifications, or hypoxic responses.

References 

[1] P. Gainza, F. Sverrisson, F. Monti, E. Rodolà, D. Boscaini, M. Bronstein, B. Correia, Nat. Methods., 17, 184-192 (2019)

[2] A. Scheck, S. Rosset, M. Defferrard, A. Loukas, J. Bonet, P. Vandergheynst, B. Correia, PLoS. Comput. Biol., 18, e1009178 (2022)

[3] M. Chalkley, S. Mann, W. DeGrado, Nat. Rev. Chem., 6, 31-50 (2021)

[4] C. Krivacic, K. Kundert, X. Pan, R. Pache, L. Liu, S. O Conchúir, J. Jeliazkov, J. Gray, M. Thompson, J. Fraser, T. Kortemme, Proc. Natl. Acad. Sci. U.S.A., 119, (2022)

[5] J. Jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvunakool, R. Bates, A. Žídek, A. Potapenko, A. Bridgland, C. Meyer, S. Kohl, A. Ballard,

A. Cowie, B. Romera-Paredes, S. Nikolov, R. Jain, J. Adler, T. Back, S. Petersen, D. Reiman, E. Clancy, M. Zielinski, M. Steinegger, M. Pacholska, T. Berghammer, S.

Bodenstein, D. Silver, O. Vinyals, A. Senior, K. Kavukcuoglu, P. Kohli, D. Hassabis, Nature, 596, 583-589 (2021)

[6} Nature 617, 438 (2023)