Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations
Abstract We introduce a computational approach for the design of target-specific peptides. Our method integrates a Gated Recurrent Unit-based Variational Autoencoder with Rosetta FlexPepDock for peptide sequence generation and binding affinity assessment. Subsequently, molecular dynamics simulations...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-45766-2 |
| _version_ | 1827326876148826112 |
|---|---|
| author | Sijie Chen Tong Lin Ruchira Basu Jeremy Ritchey Shen Wang Yichuan Luo Xingcan Li Dehua Pei Levent Burak Kara Xiaolin Cheng |
| author_facet | Sijie Chen Tong Lin Ruchira Basu Jeremy Ritchey Shen Wang Yichuan Luo Xingcan Li Dehua Pei Levent Burak Kara Xiaolin Cheng |
| author_sort | Sijie Chen |
| collection | DOAJ |
| description | Abstract We introduce a computational approach for the design of target-specific peptides. Our method integrates a Gated Recurrent Unit-based Variational Autoencoder with Rosetta FlexPepDock for peptide sequence generation and binding affinity assessment. Subsequently, molecular dynamics simulations are employed to narrow down the selection of peptides for experimental assays. We apply this computational strategy to design peptide inhibitors that specifically target β-catenin and NF-κB essential modulator. Among the twelve β-catenin inhibitors, six exhibit improved binding affinity compared to the parent peptide. Notably, the best C-terminal peptide binds β-catenin with an IC50 of 0.010 ± 0.06 μM, which is 15-fold better than the parent peptide. For NF-κB essential modulator, two of the four tested peptides display substantially enhanced binding compared to the parent peptide. Collectively, this study underscores the successful integration of deep learning and structure-based modeling and simulation for target specific peptide design. |
| first_indexed | 2024-03-07T14:51:46Z |
| format | Article |
| id | doaj.art-9abaf5b6631f4e708716d36d49b36a97 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-07T14:51:46Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-9abaf5b6631f4e708716d36d49b36a972024-03-05T19:39:42ZengNature PortfolioNature Communications2041-17232024-02-0115112010.1038/s41467-024-45766-2Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulationsSijie Chen0Tong Lin1Ruchira Basu2Jeremy Ritchey3Shen Wang4Yichuan Luo5Xingcan Li6Dehua Pei7Levent Burak Kara8Xiaolin Cheng9College of Pharmacy, The Ohio State UniversityMechanical Engineering Department, Carnegie Mellon UniversityDepartment of Chemistry and Biochemistry, The Ohio State UniversityDepartment of Chemistry and Biochemistry, The Ohio State UniversityCollege of Pharmacy, The Ohio State UniversityElectrical and Computer Engineering Department, Carnegie Mellon UniversityDepartment of Radiology, Affiliated Hospital and Medical School of Nantong UniversityDepartment of Chemistry and Biochemistry, The Ohio State UniversityMechanical Engineering Department, Carnegie Mellon UniversityCollege of Pharmacy, The Ohio State UniversityAbstract We introduce a computational approach for the design of target-specific peptides. Our method integrates a Gated Recurrent Unit-based Variational Autoencoder with Rosetta FlexPepDock for peptide sequence generation and binding affinity assessment. Subsequently, molecular dynamics simulations are employed to narrow down the selection of peptides for experimental assays. We apply this computational strategy to design peptide inhibitors that specifically target β-catenin and NF-κB essential modulator. Among the twelve β-catenin inhibitors, six exhibit improved binding affinity compared to the parent peptide. Notably, the best C-terminal peptide binds β-catenin with an IC50 of 0.010 ± 0.06 μM, which is 15-fold better than the parent peptide. For NF-κB essential modulator, two of the four tested peptides display substantially enhanced binding compared to the parent peptide. Collectively, this study underscores the successful integration of deep learning and structure-based modeling and simulation for target specific peptide design.https://doi.org/10.1038/s41467-024-45766-2 |
| spellingShingle | Sijie Chen Tong Lin Ruchira Basu Jeremy Ritchey Shen Wang Yichuan Luo Xingcan Li Dehua Pei Levent Burak Kara Xiaolin Cheng Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations Nature Communications |
| title | Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations |
| title_full | Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations |
| title_fullStr | Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations |
| title_full_unstemmed | Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations |
| title_short | Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations |
| title_sort | design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations |
| url | https://doi.org/10.1038/s41467-024-45766-2 |
| work_keys_str_mv | AT sijiechen designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT tonglin designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT ruchirabasu designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT jeremyritchey designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT shenwang designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT yichuanluo designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT xingcanli designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT dehuapei designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT leventburakkara designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations AT xiaolincheng designoftargetspecificpeptideinhibitorsusinggenerativedeeplearningandmoleculardynamicssimulations |