Overview
Very exciting new developments in artificial intelligence, particularly in deep learning, have achieved spectacular performances when applied to biological problems. For instance, the AlphaFold system produces protein 3D models based on their sequences, with an accuracy competitive with experimental structures, and this has greatly expanded proteomes structural coverage. Promising steps have also been taken for determining protein interacting partners and complex 3D structures, predicting the functional outcome of point mutations, and designing new proteins with desired shapes or functions. This summer school will offer an overview of the most recent deep neural network architectures and learning algorithms, and their application to protein-related problems. The participants will acquire theoretical knowledge and practical know-how on data representation, architecture design, and training/testing protocols. We will put a particular emphasis on the specific properties of protein sequences and structures, and on how these properties can be leveraged for improving the learning process. Proteins will be used as “case studies” to illustrate general issues associated with machine learning and the definition of meaningful representations in “digital” biology. The participants will be able to transfer the knowledge acquired during the school to other problems and objects (e.g. variant calling in DNA/RNA sequences from nanopore sequencing data, genotype-to-phenotype mapping…). The school will gather leading scientists coming from different backgrounds, namely biology, mathematics, computer science and physics, and working at the interface between artificial intelligence and biology. It is mainly intended for PhD students and post-doctoral fellows in biology and bioinformatics with some interest in using, understanding and developing machine learning methods.  

Teachers

• Sophie Barbe, TBI, INSA – CNRS – INRAE 
• Claire Boyer, LPSM, Sorbonne University
• Alessandra Carbone, LCQB, CNRS – Sorbonne University 
• Krzysztof Fidelis, University of California, Davis
• Tatiana Galochkina, DSIMB, INSERM – University of Paris 
• Jean-Christophe Gelly, DSIMB, INSERM – University of Paris 
• Sergei Grudinin, LJK, CNRS
• Elodie Laine, LCQB, CNRS – Sorbonne University

The mornings will be dedicated to lectures, and the afternoons to practical sessions. The first day will give a panorama of deep learning techniques, and an introduction to protein sequences and structures. The other days will deal with the prediction of protein structures, conformations and interactions, and protein design.

Audience
The school is open to PhD students and post-doctoral fellows in Biology or Bioinformatics who wish to integrate artificial intelligence techniques into their research. Candidates should have some (possibly light) background in programming and some basic knowledge on proteins. A maximum of 20 participants will be selected.

Venue
The school will take place at the Marine Biological Station of Banyuls-sur-Mer: https://www.obs-banyuls.fr/en/. Information on how to get there can be found at: https://www.obs-banyuls.fr/en/host/how-to-get-here.html.

Registration
Please fill this form to apply: https://forms.gle/UEastjG6Jsr2WDuo9.
Application deadline April 15, 2022.

The registration fees are 50 euros, and cover the housing and food expenses. Depending on the budget, we may also be able to provide financial support for travel expenses to some of the participants. 

Organization
The school is co-organized by i-Bio and SCAI.
Organizers: Elodie Laine (executive chair, IBPS), Clément Carré (IBPS), Xavier Fresquet (SCAI), Valérie Goguel (i-Bio, IBPS), and Gilles Fischer (i-Bio, IBPS)

Sponsors
The school is sponsored by the GDR BIM (http://www.gdr-bim.cnrs.fr) and the Life Sciences Department of Sorbonne University. 

For questions about the school, please contact: elodie.laine@sorbonne-universite.fr.