Prospective de novo drug design with deep interactome learning
Abstract De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-47613-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594654641520640 |
|---|---|
| author | Kenneth Atz Leandro Cotos Clemens Isert Maria Håkansson Dorota Focht Mattis Hilleke David F. Nippa Michael Iff Jann Ledergerber Carl C. G. Schiebroek Valentina Romeo Jan A. Hiss Daniel Merk Petra Schneider Bernd Kuhn Uwe Grether Gisbert Schneider |
| author_facet | Kenneth Atz Leandro Cotos Clemens Isert Maria Håkansson Dorota Focht Mattis Hilleke David F. Nippa Michael Iff Jann Ledergerber Carl C. G. Schiebroek Valentina Romeo Jan A. Hiss Daniel Merk Petra Schneider Bernd Kuhn Uwe Grether Gisbert Schneider |
| author_sort | Kenneth Atz |
| collection | DOAJ |
| description | Abstract De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the “zero-shot" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the human peroxisome proliferator-activated receptor (PPAR) subtype gamma are generated. The top-ranking designs are chemically synthesized and computationally, biophysically, and biochemically characterized. Potent PPAR partial agonists are identified, demonstrating favorable activity and the desired selectivity profiles for both nuclear receptors and off-target interactions. Crystal structure determination of the ligand-receptor complex confirms the anticipated binding mode. This successful outcome positively advocates interactome-based de novo design for application in bioorganic and medicinal chemistry, enabling the creation of innovative bioactive molecules. |
| format | Article |
| id | doaj-art-d7bb743be1dc457aa2795efb9109d361 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-d7bb743be1dc457aa2795efb9109d3612025-01-19T12:29:36ZengNature PortfolioNature Communications2041-17232024-04-0115111810.1038/s41467-024-47613-wProspective de novo drug design with deep interactome learningKenneth Atz0Leandro Cotos1Clemens Isert2Maria Håkansson3Dorota Focht4Mattis Hilleke5David F. Nippa6Michael Iff7Jann Ledergerber8Carl C. G. Schiebroek9Valentina Romeo10Jan A. Hiss11Daniel Merk12Petra Schneider13Bernd Kuhn14Uwe Grether15Gisbert Schneider16ETH Zurich, Department of Chemistry and Applied BiosciencesETH Zurich, Department of Chemistry and Applied BiosciencesETH Zurich, Department of Chemistry and Applied BiosciencesSARomics Biostructures ABSARomics Biostructures ABETH Zurich, Department of Chemistry and Applied BiosciencesRoche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd.ETH Zurich, Department of Chemistry and Applied BiosciencesETH Zurich, Department of Chemistry and Applied BiosciencesETH Zurich, Department of Chemistry and Applied BiosciencesRoche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd.ETH Zurich, Department of Chemistry and Applied BiosciencesDepartment of Pharmacy, Ludwig-Maximilians-Universität MünchenETH Zurich, Department of Chemistry and Applied BiosciencesRoche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd.Roche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd.ETH Zurich, Department of Chemistry and Applied BiosciencesAbstract De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the “zero-shot" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the human peroxisome proliferator-activated receptor (PPAR) subtype gamma are generated. The top-ranking designs are chemically synthesized and computationally, biophysically, and biochemically characterized. Potent PPAR partial agonists are identified, demonstrating favorable activity and the desired selectivity profiles for both nuclear receptors and off-target interactions. Crystal structure determination of the ligand-receptor complex confirms the anticipated binding mode. This successful outcome positively advocates interactome-based de novo design for application in bioorganic and medicinal chemistry, enabling the creation of innovative bioactive molecules.https://doi.org/10.1038/s41467-024-47613-w |
| spellingShingle | Kenneth Atz Leandro Cotos Clemens Isert Maria Håkansson Dorota Focht Mattis Hilleke David F. Nippa Michael Iff Jann Ledergerber Carl C. G. Schiebroek Valentina Romeo Jan A. Hiss Daniel Merk Petra Schneider Bernd Kuhn Uwe Grether Gisbert Schneider Prospective de novo drug design with deep interactome learning Nature Communications |
| title | Prospective de novo drug design with deep interactome learning |
| title_full | Prospective de novo drug design with deep interactome learning |
| title_fullStr | Prospective de novo drug design with deep interactome learning |
| title_full_unstemmed | Prospective de novo drug design with deep interactome learning |
| title_short | Prospective de novo drug design with deep interactome learning |
| title_sort | prospective de novo drug design with deep interactome learning |
| url | https://doi.org/10.1038/s41467-024-47613-w |
| work_keys_str_mv | AT kennethatz prospectivedenovodrugdesignwithdeepinteractomelearning AT leandrocotos prospectivedenovodrugdesignwithdeepinteractomelearning AT clemensisert prospectivedenovodrugdesignwithdeepinteractomelearning AT mariahakansson prospectivedenovodrugdesignwithdeepinteractomelearning AT dorotafocht prospectivedenovodrugdesignwithdeepinteractomelearning AT mattishilleke prospectivedenovodrugdesignwithdeepinteractomelearning AT davidfnippa prospectivedenovodrugdesignwithdeepinteractomelearning AT michaeliff prospectivedenovodrugdesignwithdeepinteractomelearning AT jannledergerber prospectivedenovodrugdesignwithdeepinteractomelearning AT carlcgschiebroek prospectivedenovodrugdesignwithdeepinteractomelearning AT valentinaromeo prospectivedenovodrugdesignwithdeepinteractomelearning AT janahiss prospectivedenovodrugdesignwithdeepinteractomelearning AT danielmerk prospectivedenovodrugdesignwithdeepinteractomelearning AT petraschneider prospectivedenovodrugdesignwithdeepinteractomelearning AT berndkuhn prospectivedenovodrugdesignwithdeepinteractomelearning AT uwegrether prospectivedenovodrugdesignwithdeepinteractomelearning AT gisbertschneider prospectivedenovodrugdesignwithdeepinteractomelearning |