Coupling CP with Deep Learning for Molecular Design and SARS-CoV2 Variants Exploration (Invited Talk)

Author Thomas Schiex

Thumbnail PDF


  • Filesize: 448 kB
  • 3 pages

Document Identifiers

Author Details

Thomas Schiex
  • Universite Fédérale de Toulouse, ANITI, INRAE, UR 875, 31326 Toulouse, France

Cite AsGet BibTex

Thomas Schiex. Coupling CP with Deep Learning for Molecular Design and SARS-CoV2 Variants Exploration (Invited Talk). In 29th International Conference on Principles and Practice of Constraint Programming (CP 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 280, pp. 4:1-4:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


The use of discrete optimization, including Constraint Programming, for designing objects that we completely understand is quite usual. In this talk, I'll show how designing specific biomolecules (proteins) raises new challenges, requiring solving problems that combine precise design targets, approximate laws, and design rules that can be deep-learned from data.

Subject Classification

ACM Subject Classification
  • Computing methodologies → Artificial intelligence
  • Computing methodologies → Machine learning
  • Theory of computation → Constraint and logic programming
  • Computing methodologies → Learning in probabilistic graphical models
  • graphical models
  • deep learning
  • constraint programming
  • cost function networks
  • random Markov fields
  • decision-focused learning
  • protein design


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads


  1. David Allouche, Isabelle André, Sophie Barbe, Jessica Davies, Simon de Givry, George Katsirelos, Barry O'Sullivan, Steve Prestwich, Thomas Schiex, and Seydou Traoré. Computational protein design as an optimization problem. Artificial Intelligence, 212:59-79, 2014. Google Scholar
  2. David Allouche, Simon De Givry, George Katsirelos, Thomas Schiex, and Matthias Zytnicki. Anytime hybrid best-first search with tree decomposition for weighted CSP. In Principles and Practice of Constraint Programming: 21st International Conference, CP 2015, Cork, Ireland, August 31-September 4, 2015, Proceedings 21, pages 12-29. Springer, 2015. Google Scholar
  3. Mireia Solà Colom, Jelena Vucinic, Jared Adolf-Bryfogle, James W Bowman, Sébastien Verel, Isabelle Moczygemba, Thomas Schiex, David Simoncini, and Christopher D Bahl. Deep evolutionary forecasting identifies highly-mutated SARS-CoV-2 variants via functional sequence-landscape enumeration. Research Square, pages rs-3, 2022. Google Scholar
  4. M. Defresne, S. Barbe, and T. Schiex. Scalable coupling of deep learning with logical reasoning. In Proc. of the 32^nd IJCAI, Macau, A.S.R., China, 2023. Google Scholar
  5. Valentin Durante, George Katsirelos, and Thomas Schiex. Efficient low rank convex bounds for pairwise discrete graphical models. In International Conference on Machine Learning, pages 5726-5741. PMLR, 2022. Google Scholar
  6. Mark A Hallen and Bruce R Donald. Protein design by provable algorithms. Communications of the ACM, 62(10):76-84, 2019. Google Scholar
  7. John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, et al. Highly accurate protein structure prediction with alphafold. Nature, 596(7873):583-589, 2021. Google Scholar
  8. Hiroki Noguchi, Christine Addy, David Simoncini, Staf Wouters, Bram Mylemans, Luc Van Meervelt, Thomas Schiex, Kam YJ Zhang, Jeremy RH Tame, and Arnout RD Voet. Computational design of symmetrical eight-bladed β-propeller proteins. IUCrJ, 6(1):46-55, 2019. Google Scholar
  9. Ilan Samish, editor. Computational Protein Design. Humana New York, NY, 2017. URL: