Integrating novel data, artificial intelligence and molecular behaviour to expand functional characterization of intrinsically disordered proteins

Nearly two decades ago, the unveiling of intrinsically disordered proteins/regions (IDPs/IDRs) disrupted the longstanding structure-function paradigm, challenging the notion that well-defined native protein structures are indispensable for function.

IDPs possess the unique ability to sample ensembles of different three dimensional conformations, leading to transition pathways that have a crucial role in various unique molecular functions.

However, despite their importance, our understanding of IDPs is limited due to the challenges of studying such dynamic and large molecular systems experimentally, relegating their characterization to computational methods.Although the recent breakthrough in artificial intelligence (AI)-based protein structure prediction methods has raised the awareness of the scientific community about the IDR prevalence in proteomes (up to 50% of residues in higher organisms), their ability to predict reliable IDP ensembles and explain their function remains completely unexplored.Building upon the IDPfun Consortium and in collaboration with the ELIXIR IDP Community and the ML4NGP COST Action, the proposed IDPfun2 Consortium brings together 7 European and 5 Argentinian leading institutions with complementary expertise in data management, machine learning and structural biology.

IDPfun2 will combine state-of-the-art AI-based computational technology and novel data to advance the characterization of IDPs and their molecular behaviour also taking into account alternative molecular and evolutionary contexts.

The Consortium will establish new standards and formats to better grasp the complexity of IDPs and provide training ground for a new generation of scientists.

The ultimate goal of IDPfun2 is to translate the acquired knowledge into major international protein databases, benefiting the broader scientific community and accelerating biomedical applications with a direct impact on health and diseases.