Interplay between AI and mathematical modelling in the post-structural genomics era

Interaction entre l’IA et la modélisation mathématique à l’ère post-génomique structurale

20 – 24 March, 2023

Scientific Committee 
Comité scientifique 

Jessica Andreani (CEA Paris-Saclay)
Arne Elofsson (Stockholm University)
Krzysztof Fidelis (University of California, Davis)
Serge Grudinin (LJK, CNRS, Université Grenoble Alpes)
Risi Kondor (University of Chicago)
Elodie Laine (Sorbonne Université)

Organizing Committee
Comité d’organisation

Krzysztof Fidelis (University of California, Davis)
Sergei Grudinin (LJK, CNRS, Université Grenoble Alpes)
Elodie Laine (Sorbonne Université)

The goal of the conference is twofold. First, we aim at highlighting recent developments at the interface between machine learning, mathematical modelling, and biological data. More specifically, protein and nucleic acid sequence and structure data. Second, we aim at fostering exchanges and new collaborations toward a better vision of future challenges, and their practical implications for society. In particular, for medicine and protein engineering. These challenges include the reconstruction of interactomes at large scale at the residue resolution with the ability to sense the impact of sequence variations such as point mutations, and the accurate prediction of protein conformational states and continuous heterogeneity. The combination of machine learning and formal methods holds great promise in addressing these challenges, and we welcome contributions pushing the field forward in these directions.  

L’objectif de la conférence est double. Tout d’abord, nous visons à mettre en évidence les développements récents à l’interface entre l’apprentissage automatique, la modélisation mathématique et les données biologiques. Plus précisément, les données de séquence et de structure des protéines. Deuxièmement, nous visons à favoriser les échanges et les nouvelles collaborations vers une meilleure vision des défis futurs et leurs implications
pratiques pour la société. En particulier, pour la médecine et l’ingénierie des protéines. Ces défis incluent la reconstruction d’interactomes à grande échelle avec une résolution au niveau des résidus, et avec la capacité de détecter l’impact des variations de séquence telles que les mutations ponctuelles, et la prédiction précise des états conformationnels des protéines et de leur hétérogénéité. La combinaison de l’apprentissage automatique et des méthodes formelles est très prometteuse pour relever ces défis, et nous encouragerons les contributions faisant avancer le domaine dans ces directions.


Maciej Antczak (Poznan University of Technology)   RNA 3D structure prediction using generative adversarial networks
Minkyung Baek (Seoul National University)   Deep learning-based protein structure modeling and design
Wouter Boomsma (University of Copenhagen)   Internal-Coordinate Density Modelling of Protein Structure: Covariance Matters
Matteo Cagiada (University of Copenhagen)   Discover functional sites in proteins using evolution and structural information
Miguel Correa Marrero (ETH Zürich)   How phosphorylation controls protein structure
Juan Cortés (CNRS – LAAS Toulouse)   WASCO: A Wasserstein-based statistical tool to compare conformational ensembles of intrinsically disordered proteins
Lenore Cowen (Tufts University)   Topsy-Turvy: Integrating a Global View into Sequence-Based Protein-Protein Interaction Prediction
François Coste (INRIA Rennes)   Transformers for enzyme classification
Justas Dapkunas (Vilnius University)   PPI3D-clusters: non-redundant datasets of protein-protein, protein-peptide and protein- nucleic acid complexes, interaction interfaces and binding sites
Simon Dürr (École Polytechnique Fédérale de Lausanne)   Design of metalloproteins
Roland Dunbrack (Fox Chase Cancer Center)   Integration of structural bioinformatics and deep-learning protein structure prediction: application to human protein kinases
Michael Dunne (Protera Biosciences)   ExpressUrself: A spatial model for predicting recombinant expression from mRNA sequence
Krzysztof Fidelis (University of California, Davis)   Introduction
Xinqi Gong (Renmin University of China)   Geometry and deep learning enhanced multi body protein interaction complex prediction
Emna Harigua (Institut Pasteur de Tunis)   Benchmarking machine learning approaches for computer-aided drug discovery
Ilia Igashov (École Polytechnique Fédérale de Lausanne)   Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design
Tomasz Kosciolek (Jagiellonian University)   Leveraging protein structure information and deep learning to functionally annotate the microbiome
Valentin Lombard (Sorbonne Université)   Description/learning of protein conformational diversity
Chitaranjan Mahapatra (Université Paris-Saclay)   Machine Learning Techniques to Predict Cardiovascular Ion Channels Genes and Their Types
Vincent Mallet (École polytechnique)   DNA reverse complement equivariant networks
Céline Marquet (Technical University of Munich)   TBA
Barthelemy Meynard (Sorbonne University)   Generating Interacting Protein Sequences using Domain-to-Domain Translation and modeling the TCR-peptide binding
Yasser Mohseni Behbahani (Sorbonne Université)   New computational frameworks to break down the complexity of protein-protein interactions: from geometrical arrangement of interface to interaction networks
John Moult (University of Maryland)   Deep Learning in Computational Structural Biology – the CASP View
Luca Nesterenko (Université Claude Bernard Lyon 1)   Phyloformer: towards fast and accurate phylogeny estimation with self-attention networks.
Pascal Notin (University of Oxford)   Protein fitness prediction and iterative protein redesign
Carlos-Andres Peña-Reyes (University of Applied Sciences Western Switzerland)   XAI and ML to predict and understand phage-bacteria interactions from genomic data
Tomáš Pluskal (IOCB Prague)   Interpretation of tandem mass spectra of small molecules with self-supervised deep learning
Gabriele Pozzati (Stockholm University)   Usina AlphaFold for studying protein-protein interactions
Nathalie Reuter (University of Bergen)   Dissecting peripheral protein-membrane interfaces
Elena Rivas (Harvard University)   Evolutionary conservation of RNA structure
Burkhard Rost (Technical University of Munich)   Artificial Intelligence captures language of life written in proteins
Thomas Schiex (INRAE Occitanie-Toulouse)   Learning how to design proteins with a Deep Learning and Automated Reasoning architecture
Dina Schneidman (The Hebrew University of Jerusalem)   Integrative Structure Modeling in the Age of Deep Learning: Overcoming Challenges in Modeling Antibody-Antigen Complexes and Large Complex Assemblies
Tobias Senoner (Technical University of Munich)   ProtSpace: a python library to visualize and analyze protein embeddings
Johannes Söding (Max Planck Institute Göttingen)   Fast structure and positional ortholog searching and viral metagenome assembly
Jian Tang (MILA-Québec AI Institute & HEC Montréal)   Generative Biology: Towards Building the “ChatGPT” in Biology
Jeanne Trinquier (Sorbonne Université)   Differentiable structural alignment
Susan Tsutakawa (Lawrence Berkeley National Laboratory)

CASP-SAXS: Comparison of protein structure predictions and crystal structures to experimental Small Angle X-ray Scattering data
Konstantin Volzhenin (Sorbonne Université)   Protein-protein interaction prediction from protein Language Models
Maurice Weiler (University of Amsterdam)   Equivariant and coordinate independent convolutional networks
Andrew White (University of Rochester)   Explaining molecular properties with natural language
Kevin Yang (Microsoft Research)   Multimodal deep learning for protein engineering
François Yvon (Université Paris-Saclay)   Multi-lingual translation
Diego Javier Zea (Université Paris-Saclay)   Impact of protein conformational diversity on AlphaFold predictions
Dmitrii Zhemchuzhnikov (Université Grenoble Alpes)   6DCNN with roto-translational convolution filters for volumetric data processing
Craig Zirbel (Bowling Green State University)   Features of RNA 3D structures that constrain sequence variability