Grant: Alliance Grants
Université d'Ottawa
$94,880.00
Development and validation of a machine learning framework for identifying protein-protein interaction disruptors
FY 2024-25
Summary
Physical interactions between protein partners are key determinants in modulating central pathways and mechanisms both in healthy and disease-affected cells. While the number of protein-protein interactions (PPIs) encoded by the human genome is much larger than the one of receptors and enzymes, the development of PPI-directed chemical compounds lags significantly behind due to intrinsic challenges related to the complex physicochemical nature of such interfaces compared with conventional binding sites. Computational methods, especially AI-augmented computational chemistry, have recently demonstrated tremendous potential for the discovery of compounds binding to previously intractable sites. Unfortunately, modeling PPI interfaces remains a pivotal challenge even for these methods, hindering the discovery of novel biological tools for interrogating under-characterized PPIs, as well as drugs with innovative mechanisms of actions leading to higher selectivity and potency. Hence, there is a pressing need to develop new methodologies that can alleviate these challenges.
In this project, we aim at developing a computational platform for streamlining the discovery of PPI small molecule disruptors from vast chemical libraries, by adapting general computational chemistry methods to the specific physical chemistry required to bind PPI interfaces using machine learning. This hybrid platform will be thoroughly validated for the discovery of bioactive PPI disruptors against the ERCC1-XPF PPI interaction, which plays a central role in DNA repair and chemoresistance in tumors. We envision that the platform will enable for the first time the efficient computational discovery of PPI modulators, opening the doors to investigate hundreds of PPI complexes whose biological function and pharmacological relevance are currently unknown. Ultimately, our research will reinforce the role of Canada as a global leader in computer-aided chemical discovery, benefitting the national biotech sector as well as to advance the development of innovative therapeutics.
Program
Alliance Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
598402-2024
Name nom
Gentile, Francesco F
Department département
Chemistry
Organization id
28
Institution établissement
Université d'Ottawa
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
94880
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
504
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Human pharmaceuticals
Area of application fr
Produits pharmaceutiques administrables à l'homme
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Development and validation of a machine learning framework for identifying protein-protein interaction disruptors
Keywords
deep learning; molecular docking; protein-protein interactions; structure-based molecular discovery; virtual screening
Application summary
Physical interactions between protein partners are key determinants in modulating central pathways and mechanisms both in healthy and disease-affected cells. While the number of protein-protein interactions (PPIs) encoded by the human genome is much larger than the one of receptors and enzymes, the development of PPI-directed chemical compounds lags significantly behind due to intrinsic challenges related to the complex physicochemical nature of such interfaces compared with conventional binding sites. Computational methods, especially AI-augmented computational chemistry, have recently demonstrated tremendous potential for the discovery of compounds binding to previously intractable sites. Unfortunately, modeling PPI interfaces remains a pivotal challenge even for these methods, hindering the discovery of novel biological tools for interrogating under-characterized PPIs, as well as drugs with innovative mechanisms of actions leading to higher selectivity and potency. Hence, there is a pressing need to develop new methodologies that can alleviate these challenges.
In this project, we aim at developing a computational platform for streamlining the discovery of PPI small molecule disruptors from vast chemical libraries, by adapting general computational chemistry methods to the specific physical chemistry required to bind PPI interfaces using machine learning. This hybrid platform will be thoroughly validated for the discovery of bioactive PPI disruptors against the ERCC1-XPF PPI interaction, which plays a central role in DNA repair and chemoresistance in tumors. We envision that the platform will enable for the first time the efficient computational discovery of PPI modulators, opening the doors to investigate hundreds of PPI complexes whose biological function and pharmacological relevance are currently unknown. Ultimately, our research will reinforce the role of Canada as a global leader in computer-aided chemical discovery, benefitting the national biotech sector as well as to advance the development of innovative therapeutics.
