Cargando…
Graph deep learning locates magnesium ions in RNA
Magnesium ions (Mg(2+)) are vital for RNA structure and cellular functions. Present efforts in RNA structure determination and understanding of RNA functions are hampered by the inability to accurately locate Mg(2+) ions in an RNA. Here we present a machine-learning method, originally developed for...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Cambridge University Press
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10249658/ https://www.ncbi.nlm.nih.gov/pubmed/37292390 http://dx.doi.org/10.1017/qrd.2022.17 |
_version_ | 1785055604846362624 |
---|---|
author | Zhou, Yuanzhe Chen, Shi-Jie |
author_facet | Zhou, Yuanzhe Chen, Shi-Jie |
author_sort | Zhou, Yuanzhe |
collection | PubMed |
description | Magnesium ions (Mg(2+)) are vital for RNA structure and cellular functions. Present efforts in RNA structure determination and understanding of RNA functions are hampered by the inability to accurately locate Mg(2+) ions in an RNA. Here we present a machine-learning method, originally developed for computer visual recognition, to predict Mg(2+) binding sites in RNA molecules. By incorporating geometrical and electrostatic features of RNA, we capture the key ingredients of Mg(2+)-RNA interactions, and from deep learning, predict the Mg(2+) density distribution. Five-fold cross-validation on a dataset of 177 selected Mg(2+)-containing structures and comparisons with different methods validate the approach. This new approach predicts Mg(2+) binding sites with notably higher accuracy and efficiency. More importantly, saliency analysis for eight different Mg(2+) binding motifs indicates that the model can reveal critical coordinating atoms for Mg(2+) ions and ion-RNA inner/outer-sphere coordination. Furthermore, implementation of the model uncovers new Mg(2+) binding motifs. This new approach may be combined with X-ray crystallography structure determination to pinpoint the metal ion binding sites. |
format | Online Article Text |
id | pubmed-10249658 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Cambridge University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-102496582023-06-08 Graph deep learning locates magnesium ions in RNA Zhou, Yuanzhe Chen, Shi-Jie QRB Discov Research Article Magnesium ions (Mg(2+)) are vital for RNA structure and cellular functions. Present efforts in RNA structure determination and understanding of RNA functions are hampered by the inability to accurately locate Mg(2+) ions in an RNA. Here we present a machine-learning method, originally developed for computer visual recognition, to predict Mg(2+) binding sites in RNA molecules. By incorporating geometrical and electrostatic features of RNA, we capture the key ingredients of Mg(2+)-RNA interactions, and from deep learning, predict the Mg(2+) density distribution. Five-fold cross-validation on a dataset of 177 selected Mg(2+)-containing structures and comparisons with different methods validate the approach. This new approach predicts Mg(2+) binding sites with notably higher accuracy and efficiency. More importantly, saliency analysis for eight different Mg(2+) binding motifs indicates that the model can reveal critical coordinating atoms for Mg(2+) ions and ion-RNA inner/outer-sphere coordination. Furthermore, implementation of the model uncovers new Mg(2+) binding motifs. This new approach may be combined with X-ray crystallography structure determination to pinpoint the metal ion binding sites. Cambridge University Press 2022-10-06 /pmc/articles/PMC10249658/ /pubmed/37292390 http://dx.doi.org/10.1017/qrd.2022.17 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited. |
spellingShingle | Research Article Zhou, Yuanzhe Chen, Shi-Jie Graph deep learning locates magnesium ions in RNA |
title | Graph deep learning locates magnesium ions in RNA |
title_full | Graph deep learning locates magnesium ions in RNA |
title_fullStr | Graph deep learning locates magnesium ions in RNA |
title_full_unstemmed | Graph deep learning locates magnesium ions in RNA |
title_short | Graph deep learning locates magnesium ions in RNA |
title_sort | graph deep learning locates magnesium ions in rna |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10249658/ https://www.ncbi.nlm.nih.gov/pubmed/37292390 http://dx.doi.org/10.1017/qrd.2022.17 |
work_keys_str_mv | AT zhouyuanzhe graphdeeplearninglocatesmagnesiumionsinrna AT chenshijie graphdeeplearninglocatesmagnesiumionsinrna |