Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design
Abstract Generative chemical language models (CLMs) have demonstrated success in learning language-based molecular representations for de novo drug design. Here, we integrate structure-based drug design (SBDD) principles with CLMs to go from protein structure to novel small-molecule ligands, without...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-60629-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849402005569667072 |
|---|---|
| author | Morgan Thomas Pierre G. Matricon Robert J. Gillespie Maja Napiórkowska Hannah Neale Jonathan S. Mason Jason Brown Kaan Harwood Charlotte Fieldhouse Nigel A. Swain Tian Geng Noel M. O’Boyle Francesca Deflorian Andreas Bender Chris de Graaf |
| author_facet | Morgan Thomas Pierre G. Matricon Robert J. Gillespie Maja Napiórkowska Hannah Neale Jonathan S. Mason Jason Brown Kaan Harwood Charlotte Fieldhouse Nigel A. Swain Tian Geng Noel M. O’Boyle Francesca Deflorian Andreas Bender Chris de Graaf |
| author_sort | Morgan Thomas |
| collection | DOAJ |
| description | Abstract Generative chemical language models (CLMs) have demonstrated success in learning language-based molecular representations for de novo drug design. Here, we integrate structure-based drug design (SBDD) principles with CLMs to go from protein structure to novel small-molecule ligands, without a priori knowledge of ligand chemistry. Using Augmented Hill-Climb, we successfully optimise multiple objectives within a practical timeframe, including protein-ligand complementarity. Resulting de novo molecules contain known or promising adenosine A2A receptor ligand chemistry that is not available in commercial vendor libraries, accessing commercially novel areas of chemical space. Experimental validation demonstrates a binding hit rate of 88%, with 50% having confirmed functional activity, including three nanomolar ligands and two novel chemotypes. The two strongest binders are co-crystallised with the A2A receptor, revealing their binding mechanisms that can be used to inform future iterations of structure-based de novo design, closing the AI SBDD loop. |
| format | Article |
| id | doaj-art-98a2709b77be4faba2ce3784ca8bc399 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-98a2709b77be4faba2ce3784ca8bc3992025-08-20T03:37:38ZengNature PortfolioNature Communications2041-17232025-07-0116111410.1038/s41467-025-60629-0Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug designMorgan Thomas0Pierre G. Matricon1Robert J. Gillespie2Maja Napiórkowska3Hannah Neale4Jonathan S. Mason5Jason Brown6Kaan Harwood7Charlotte Fieldhouse8Nigel A. Swain9Tian Geng10Noel M. O’Boyle11Francesca Deflorian12Andreas Bender13Chris de Graaf14Centre for Molecular Informatics, Department of Chemistry, University of CambridgeNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonCentre for Molecular Informatics, Department of Chemistry, University of CambridgeNxera Pharma, Steinmetz Building, Granta Park, Great AbingtonAbstract Generative chemical language models (CLMs) have demonstrated success in learning language-based molecular representations for de novo drug design. Here, we integrate structure-based drug design (SBDD) principles with CLMs to go from protein structure to novel small-molecule ligands, without a priori knowledge of ligand chemistry. Using Augmented Hill-Climb, we successfully optimise multiple objectives within a practical timeframe, including protein-ligand complementarity. Resulting de novo molecules contain known or promising adenosine A2A receptor ligand chemistry that is not available in commercial vendor libraries, accessing commercially novel areas of chemical space. Experimental validation demonstrates a binding hit rate of 88%, with 50% having confirmed functional activity, including three nanomolar ligands and two novel chemotypes. The two strongest binders are co-crystallised with the A2A receptor, revealing their binding mechanisms that can be used to inform future iterations of structure-based de novo design, closing the AI SBDD loop.https://doi.org/10.1038/s41467-025-60629-0 |
| spellingShingle | Morgan Thomas Pierre G. Matricon Robert J. Gillespie Maja Napiórkowska Hannah Neale Jonathan S. Mason Jason Brown Kaan Harwood Charlotte Fieldhouse Nigel A. Swain Tian Geng Noel M. O’Boyle Francesca Deflorian Andreas Bender Chris de Graaf Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design Nature Communications |
| title | Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design |
| title_full | Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design |
| title_fullStr | Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design |
| title_full_unstemmed | Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design |
| title_short | Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design |
| title_sort | identification of nanomolar adenosine a2a receptor ligands using reinforcement learning and structure based drug design |
| url | https://doi.org/10.1038/s41467-025-60629-0 |
| work_keys_str_mv | AT morganthomas identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT pierregmatricon identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT robertjgillespie identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT majanapiorkowska identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT hannahneale identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT jonathansmason identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT jasonbrown identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT kaanharwood identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT charlottefieldhouse identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT nigelaswain identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT tiangeng identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT noelmoboyle identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT francescadeflorian identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT andreasbender identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign AT chrisdegraaf identificationofnanomolaradenosinea2areceptorligandsusingreinforcementlearningandstructurebaseddrugdesign |