File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.xcrp.2022.101046
- Scopus: eid_2-s2.0-85138187995
- WOS: WOS:000874915400002
Supplementary
- Citations:
- Appears in Collections:
Article: An ensemble 3D deep-learning model to predict protein metal-binding site
Title | An ensemble 3D deep-learning model to predict protein metal-binding site |
---|---|
Authors | |
Keywords | 3D voxels ensemble 3D deep learning metal-binding sites metalloprotein spatial features |
Issue Date | 2022 |
Citation | Cell Reports Physical Science, 2022, v. 3, n. 9, article no. 101046 How to Cite? |
Abstract | Predicting metal-binding sites in proteins is critical for understanding the protein's biological function. Here, we develop an ensemble deep convolutional neural network (CNN) method for predicting metal-binding sites based on their three-dimensional (3D) structure. We build multi-channel 3D voxels based on biophysical characteristics obtained from raw atom coordinates of each protein-binding pocket. Then, we use these 3D voxels as the input of an ensemble 3D CNN model. We train and evaluate the model using a curated dataset of 3D protein structures. Our proposed model shows high performance in predicting metal-binding sites for Zn, Fe, Mg, Mn, Ca, and Na. Our approach offers a framework to use 3D spatial features to train 3D-CNN, which may be used to predict complicated metal-binding sites directly from their biophysical characteristics. The source code and webserver of the model are publicly available. |
Persistent Identifier | http://hdl.handle.net/10722/324515 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Mohamadi, Ahmad | - |
dc.contributor.author | Cheng, Tianfan | - |
dc.contributor.author | Jin, Lijian | - |
dc.contributor.author | Wang, Junwen | - |
dc.contributor.author | Sun, Hongzhe | - |
dc.contributor.author | Koohi-Moghadam, Mohamad | - |
dc.date.accessioned | 2023-02-03T07:03:41Z | - |
dc.date.available | 2023-02-03T07:03:41Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Cell Reports Physical Science, 2022, v. 3, n. 9, article no. 101046 | - |
dc.identifier.uri | http://hdl.handle.net/10722/324515 | - |
dc.description.abstract | Predicting metal-binding sites in proteins is critical for understanding the protein's biological function. Here, we develop an ensemble deep convolutional neural network (CNN) method for predicting metal-binding sites based on their three-dimensional (3D) structure. We build multi-channel 3D voxels based on biophysical characteristics obtained from raw atom coordinates of each protein-binding pocket. Then, we use these 3D voxels as the input of an ensemble 3D CNN model. We train and evaluate the model using a curated dataset of 3D protein structures. Our proposed model shows high performance in predicting metal-binding sites for Zn, Fe, Mg, Mn, Ca, and Na. Our approach offers a framework to use 3D spatial features to train 3D-CNN, which may be used to predict complicated metal-binding sites directly from their biophysical characteristics. The source code and webserver of the model are publicly available. | - |
dc.language | eng | - |
dc.relation.ispartof | Cell Reports Physical Science | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | 3D voxels | - |
dc.subject | ensemble 3D deep learning | - |
dc.subject | metal-binding sites | - |
dc.subject | metalloprotein | - |
dc.subject | spatial features | - |
dc.title | An ensemble 3D deep-learning model to predict protein metal-binding site | - |
dc.type | Article | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1016/j.xcrp.2022.101046 | - |
dc.identifier.scopus | eid_2-s2.0-85138187995 | - |
dc.identifier.hkuros | 340022 | - |
dc.identifier.volume | 3 | - |
dc.identifier.issue | 9 | - |
dc.identifier.spage | article no. 101046 | - |
dc.identifier.epage | article no. 101046 | - |
dc.identifier.eissn | 2666-3864 | - |
dc.identifier.isi | WOS:000874915400002 | - |