Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks
Discovering novel drug candidate molecules is a fundamental step in drug development. Generative deep learning models can sample new molecular structures from learned probability distributions; however, their practical use in drug discovery hinges on generating compounds tailored to a specific targe...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
15 September 2025
|
| In: |
Nature machine intelligence
Year: 2025, Jahrgang: 7, Heft: 9, Pages: 1524-1540 |
| ISSN: | 2522-5839 |
| DOI: | 10.1038/s42256-025-01082-y |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s42256-025-01082-y Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s42256-025-01082-y 
|
| Verfasserangaben: | Atabey Ünlü, Elif Çevrim, Melih Gökay Yiğit, Ahmet Sarıgün, Hayriye Çelikbilek, Osman Bayram, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Sureyya Rifaioglu, Erden Banoğlu & Tunca Doğan |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1950203611 | ||
| 003 | DE-627 | ||
| 005 | 20260126124555.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 260126s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s42256-025-01082-y |2 doi | |
| 035 | |a (DE-627)1950203611 | ||
| 035 | |a (DE-599)KXP1950203611 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 32 |2 sdnb | ||
| 100 | 1 | |a Ünlü, Atabey |e VerfasserIn |0 (DE-588)1387983903 |0 (DE-627)1950204340 |4 aut | |
| 245 | 1 | 0 | |a Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks |c Atabey Ünlü, Elif Çevrim, Melih Gökay Yiğit, Ahmet Sarıgün, Hayriye Çelikbilek, Osman Bayram, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Sureyya Rifaioglu, Erden Banoğlu & Tunca Doğan |
| 264 | 1 | |c 15 September 2025 | |
| 300 | |b Illustrationen, Diagramme | ||
| 300 | |a 23 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 26.01.2026 | ||
| 520 | |a Discovering novel drug candidate molecules is a fundamental step in drug development. Generative deep learning models can sample new molecular structures from learned probability distributions; however, their practical use in drug discovery hinges on generating compounds tailored to a specific target molecule. Here we introduce DrugGEN, an end-to-end generative system for the de novo design of drug candidate molecules that interact with a selected protein. The proposed method represents molecules as graphs and processes them using a generative adversarial network that comprises graph transformer layers. Trained on large datasets of drug-like compounds and target-specific bioactive molecules, DrugGEN designed candidate inhibitors for AKT1, a kinase crucial in many cancers. Docking and molecular dynamics simulations suggest that the generated compounds effectively bind to AKT1, and attention maps provide insights into the model’s reasoning. Furthermore, selected de novo molecules were synthesized and shown to inhibit AKT1 at low micromolar concentrations in the context of in vitro enzymatic assays. These results demonstrate the potential of DrugGEN for designing target-specific molecules. Using the open-access DrugGEN codebase, researchers can retrain the model for other druggable proteins, provided a dataset of known bioactive molecules is available. | ||
| 650 | 4 | |a Computational science | |
| 650 | 4 | |a Machine learning | |
| 700 | 1 | |a Çevrim, Elif |e VerfasserIn |4 aut | |
| 700 | 1 | |a Yiğit, Melih Gökay |e VerfasserIn |4 aut | |
| 700 | 1 | |a Sarıgün, Ahmet |e VerfasserIn |4 aut | |
| 700 | 1 | |a Çelikbilek, Hayriye |e VerfasserIn |4 aut | |
| 700 | 1 | |a Bayram, Osman |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kahraman, Deniz Cansen |e VerfasserIn |4 aut | |
| 700 | 1 | |a Olğaç, Abdurrahman |e VerfasserIn |4 aut | |
| 700 | 1 | |a Rifaioglu, Ahmet |e VerfasserIn |0 (DE-588)1300369957 |0 (DE-627)1858156408 |4 aut | |
| 700 | 1 | |a Banoğlu, Erden |e VerfasserIn |4 aut | |
| 700 | 1 | |a Doğan, Tunca |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Nature machine intelligence |d [London] : Springer Nature Publishing, 2019 |g 7(2025), 9 vom: Sept., Seite 1524-1540 |h Online-Ressource |w (DE-627)1025147669 |w (DE-600)2933875-X |w (DE-576)506804771 |x 2522-5839 |7 nnas |a Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks |
| 773 | 1 | 8 | |g volume:7 |g year:2025 |g number:9 |g month:09 |g pages:1524-1540 |g extent:23 |a Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s42256-025-01082-y |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |7 1 |
| 856 | 4 | 0 | |u https://www.nature.com/articles/s42256-025-01082-y |x Verlag |z lizenzpflichtig |3 Volltext |7 1 |
| 951 | |a AR | ||
| 992 | |a 20260126 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1300369957 |a Rifaioğlu, Ahmet |m 1300369957:Rifaioğlu, Ahmet |d 910000 |d 912900 |e 910000PR1300369957 |e 912900PR1300369957 |k 0/910000/ |k 1/910000/912900/ |p 9 | ||
| 999 | |a KXP-PPN1950203611 |e 4860746740 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"note":["Gesehen am 26.01.2026"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"15 September 2025"}],"title":[{"title_sort":"Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks","title":"Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks"}],"language":["eng"],"person":[{"role":"aut","given":"Atabey","display":"Ünlü, Atabey","family":"Ünlü"},{"display":"Çevrim, Elif","family":"Çevrim","given":"Elif","role":"aut"},{"role":"aut","given":"Melih Gökay","display":"Yiğit, Melih Gökay","family":"Yiğit"},{"given":"Ahmet","role":"aut","family":"Sarıgün","display":"Sarıgün, Ahmet"},{"given":"Hayriye","role":"aut","display":"Çelikbilek, Hayriye","family":"Çelikbilek"},{"given":"Osman","role":"aut","display":"Bayram, Osman","family":"Bayram"},{"display":"Kahraman, Deniz Cansen","family":"Kahraman","role":"aut","given":"Deniz Cansen"},{"display":"Olğaç, Abdurrahman","family":"Olğaç","role":"aut","given":"Abdurrahman"},{"given":"Ahmet","role":"aut","display":"Rifaioglu, Ahmet","family":"Rifaioglu"},{"display":"Banoğlu, Erden","family":"Banoğlu","given":"Erden","role":"aut"},{"family":"Doğan","display":"Doğan, Tunca","role":"aut","given":"Tunca"}],"id":{"eki":["1950203611"],"doi":["10.1038/s42256-025-01082-y"]},"relHost":[{"id":{"zdb":["2933875-X"],"issn":["2522-5839"],"eki":["1025147669"]},"physDesc":[{"extent":"Online-Ressource"}],"recId":"1025147669","pubHistory":["Volume 1, no. 1 (January 2019)-"],"part":{"text":"7(2025), 9 vom: Sept., Seite 1524-1540","pages":"1524-1540","year":"2025","volume":"7","extent":"23","issue":"9"},"note":["Gesehen am 30.04.25"],"origin":[{"dateIssuedDisp":"[2019]-","publisherPlace":"[London]","publisher":"Springer Nature Publishing"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"title":[{"title_sort":"Nature machine intelligence","title":"Nature machine intelligence"}],"language":["eng"],"disp":"Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networksNature machine intelligence"}],"physDesc":[{"extent":"23 S.","noteIll":"Illustrationen, Diagramme"}],"name":{"displayForm":["Atabey Ünlü, Elif Çevrim, Melih Gökay Yiğit, Ahmet Sarıgün, Hayriye Çelikbilek, Osman Bayram, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Sureyya Rifaioglu, Erden Banoğlu & Tunca Doğan"]},"recId":"1950203611"} | ||
| SRT | |a UENLUEATABTARGETSPEC1520 | ||