About us
Espace utilisateur
Education
INSTN offers more than 40 diplomas from operator level to post-graduate degree level. 30% of our students are international students.
Professionnal development
Professionnal development
Find a training course
INSTN delivers off-the-self or tailor-made training courses to support the operational excellence of your talents.
Human capital solutions
At INSTN, we are committed to providing our partners with the best human capital solutions to develop and deliver safe & sustainable projects.
Thesis
Home   /   Thesis   /   DeepDockScan: Modeling protein complexes by coupling deep learning to high-throughput interactions experiments

DeepDockScan: Modeling protein complexes by coupling deep learning to high-throughput interactions experiments

Abstract

Studying Protein-protein interactions remains of great interest in pharmaceutical research and drug design development.

Google’s AlphaFold 2 (AF2) pushed significantly forward the current limits of protein structure prediction. Despite the undeniable accuracy improvement associated with this approach, some complex modeling targets concerning partners that have not co-evolved in different species (such as antigen / antibody) remain largely unsuccessful.

DeepDockScan aims at predicting the precise structures of complexes. It combines quantitative protein-protein interaction (PPI) assays with machine learning or a novel deep learning scoring method for structural docking. The expected outcomes include a generalized method for rapid and cost-efficient modeling of complexes.

Concerning the quantitative protein-protein assays, two approaches coupled to Deep Mutational Scanning (DMS) will be evaluated and compared: a quantitative Bacterial two-Hybrid (DMS-qB2H) and a new quantitative protein-fragment complementation assay (DMS-PCA). This project will use 3D resolved antigen/antibody structures. We will try to investigate and find rules to better predict structure complexes using experimental constraints given by DMS studies and deep learning.

The PhD student will join our Molecular Engineering for Health (SIMoS) team, led by Dr Loïc Martin at Frederic Joliot Institute for life sciences at CEA-Saclay (Nuclear Reserach Center) in the South suburbs of Paris, France. He/She will work in collaboration with Dr Oscar Ramos and Raphaël Guerois. Dr Klervi Desrumeaux and Dr Emmanuelle Vigne, from Large Molecule Research unit of Sanofi in Vitry, will also supervise the work.

Laboratory

Institut des sciences du vivant Frédéric JOLIOT
Service d’Ingénierie Moléculaire des Protéines
Laboratoire d’Immunologie Cellulaire et Biotechnologie
Paris-Saclay
Top pencilenvelopegraduation-hatlicensebookuserusersmap-markercalendar-fullbubblecrossmenuarrow-down