AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors
Abstract The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identi...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-06-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-37456-8 |
_version_ | 1797795630336180224 |
---|---|
author | Hyejin Park Sujeong Hong Myeonghun Lee Sungil Kang Rahul Brahma Kwang-Hwi Cho Jae-Min Shin |
author_facet | Hyejin Park Sujeong Hong Myeonghun Lee Sungil Kang Rahul Brahma Kwang-Hwi Cho Jae-Min Shin |
author_sort | Hyejin Park |
collection | DOAJ |
description | Abstract The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson’s correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design. |
first_indexed | 2024-03-13T03:21:56Z |
format | Article |
id | doaj.art-29714be7d49a438a98da01b7b1ac9bd9 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-13T03:21:56Z |
publishDate | 2023-06-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-29714be7d49a438a98da01b7b1ac9bd92023-06-25T11:17:26ZengNature PortfolioScientific Reports2045-23222023-06-0113111210.1038/s41598-023-37456-8AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptorsHyejin Park0Sujeong Hong1Myeonghun Lee2Sungil Kang3Rahul Brahma4Kwang-Hwi Cho5Jae-Min Shin6AZothBio Inc., Rm. DA724 Hyundai Knowledge Industry CenterAZothBio Inc., Rm. DA724 Hyundai Knowledge Industry CenterAZothBio Inc., Rm. DA724 Hyundai Knowledge Industry CenterAZothBio Inc., Rm. DA724 Hyundai Knowledge Industry CenterSchool of Systems Biomedical Science, Soongsil UniversitySchool of Systems Biomedical Science, Soongsil UniversityAZothBio Inc., Rm. DA724 Hyundai Knowledge Industry CenterAbstract The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson’s correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.https://doi.org/10.1038/s41598-023-37456-8 |
spellingShingle | Hyejin Park Sujeong Hong Myeonghun Lee Sungil Kang Rahul Brahma Kwang-Hwi Cho Jae-Min Shin AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors Scientific Reports |
title | AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors |
title_full | AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors |
title_fullStr | AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors |
title_full_unstemmed | AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors |
title_short | AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors |
title_sort | aikpro deep learning model for kinome wide bioactivity profiling using structure based sequence alignments and molecular 3d conformer ensemble descriptors |
url | https://doi.org/10.1038/s41598-023-37456-8 |
work_keys_str_mv | AT hyejinpark aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors AT sujeonghong aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors AT myeonghunlee aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors AT sungilkang aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors AT rahulbrahma aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors AT kwanghwicho aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors AT jaeminshin aikprodeeplearningmodelforkinomewidebioactivityprofilingusingstructurebasedsequencealignmentsandmolecular3dconformerensembledescriptors |