Mots-Clés
Deep learning
Graph Neural Networks
Molecular Dynamics Simulations
Macromolecular complexes
Description
Context. This postdoc position is funded for two years by the grant from Programme Inria Quadrant (PIQ). The main goal is to develop a graph neural network architecture to investigate conformational dynamics of macromolecular complexes. The Postdoc researcher will be in connection with Yasaman Karami (Chargee de recherche, Inria) with expertise in proteins conformational dynamics and allostery, and will be hosted in the Delta team within the Inria center at the Universite de Lorraine. Our team consists of two permanent researchers with several PhD and postdoc members, and is expected to grow by hiring new members. It provides a multidisciplinary and international environment, and benefits from experts in structural bioinformatics, as well as in computer science and deep learning. Our main goal is to develop deep learning models, to study, and predict protein structure, interactions, function and to further design synthetic molecules. The team has access to computational resources, including efficient GPUs and CPUs, from different cluster centers including Grid5000, Jean Zay, etc.
Assignment. Biomolecules such as proteins and nucleic acids are at the heart of virtually all fundamental cellular processes. They adopt complex dynamic behavior and their functions are directly linked to the arrangement of atoms in 3D and dynamics. Therefore, characterizing the structure, dynamics and conformational changes of biomolecules can help understand the molecular mechanisms of underlying diseases. We recently developed ComPASS, a large-scale computational method designed to study communication networks in protein-protein and protein-nucleic acid complexes [1]. ComPASS has been applied to different biological systems, facilitating the interpretation of the conformational dynamics. In a recent study, we highlighted the role of cysteine hyperoxidation in Nucleosome [2,3]. Moreover, we took major steps in learning conformational dynamics by proposing DynamicGT, a novel architecture that combines cooperative graph neural networks with a graph transformer, to predict binding sites [4].
The main goal of this Postdoc is to elucidate the conformational dynamics of macromolecular complexes and to develop a method for understanding their communications. The main idea is to take another major step, taking advantage of the recent developments of AI and propose a novel approach to uncover distinct mechanisms in macromolecular systems. The post-doctoral researcher will also help supervise the team’s students working on computational biology problems.
[1] Bheemireddy S, Gonzalez-Aleman R, Bignon E, Karami Y. Communication pathway analysis within proteinnucleic acid complexes. bioRxiv, 2025.
[2] Karami Y, Bignon E. Cysteine hyperoxidation rewires communication pathways in the nucleosome and destabilizes the dyad. Computational and Structural Biotechnology Journal, 2024, 23, 1387-1396.
[3] Karami Y, Gonzalez-Aleman R, Duch M, Qiu Y, Kedjar Y, Bignon E. Histone H3 as a redox switch in the nucleosome core particle: insights from molecular modeling. bioRxiv, 2024.
[4] Mokhtari O, Grudinin S, Karami Y, Khakzad H. DynamicGT: a dynamic-aware geometric transformer model to predict protein binding interfaces in flexible and disordered regions. bioRxiv, 2025.
Skills.
* PhD degree in Computer Science, or Bioinformatics
* Proficiency in Python and good coding practices is mandatory
* Experience in deep learning (PyTorch) is mandatory+
* Knowledge in protein biochemistry
* Ability to work independently and also to work in a team
* Excellent oral and written English skills
+Applications with no computer science/deep learning background will not be considered.