LncRNA-Top: Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms

Weidun Xie; Xingjian Chen; Zetian Zheng; Fuzhou Wang; Xiaowei Zhu; Qiuzhen Lin; Yanni Sun; Ka-Chun Wong

doi:10.1016/j.isci.2023.108197

LncRNA-Top: Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms

Weidun Xie, Xingjian Chen, Zetian Zheng, Fuzhou Wang, Xiaowei Zhu, Qiuzhen Lin, Yanni Sun, Ka-Chun Wong^*

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

69 Downloads (CityUHK Scholars)

Abstract

By soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to regulate gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power. Our additional software can annotate the scores with target candidates. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs. © 2023 The Author(s).

Original language	English
Article number	108197
Journal	iScience
Volume	26
Issue number	11
Online published	12 Oct 2023
DOIs	https://doi.org/10.1016/j.isci.2023.108197
Publication status	Published - 17 Nov 2023

Bibliographical note

Information for this record is supplemented by the author(s) concerned.

Research Keywords

lncRNA
lncRNA-Gene
Controlled Deep-Learning
ensemble methods

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-ND 4.0. https://creativecommons.org/licenses/by-nc-nd/4.0/

Access Output

10.1016/j.isci.2023.108197

170348838.pdfFinal Published version, 4.67 MBLicence: CC BY-NC-ND

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{8f8fad32331246ae8331631c01d7667b,

title = "LncRNA-Top: Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms",

abstract = "By soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to regulate gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power. Our additional software can annotate the scores with target candidates. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs. {\textcopyright} 2023 The Author(s).",

keywords = "lncRNA, lncRNA-Gene, Controlled Deep-Learning, ensemble methods",

author = "Weidun Xie and Xingjian Chen and Zetian Zheng and Fuzhou Wang and Xiaowei Zhu and Qiuzhen Lin and Yanni Sun and Ka-Chun Wong",

note = "Information for this record is supplemented by the author(s) concerned.",

year = "2023",

month = nov,

day = "17",

doi = "10.1016/j.isci.2023.108197",

language = "English",

volume = "26",

number = "11",

}

TY - JOUR

T1 - LncRNA-Top

T2 - Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms

AU - Xie, Weidun

AU - Chen, Xingjian

AU - Zheng, Zetian

AU - Wang, Fuzhou

AU - Zhu, Xiaowei

AU - Lin, Qiuzhen

AU - Sun, Yanni

AU - Wong, Ka-Chun

N1 - Information for this record is supplemented by the author(s) concerned.

PY - 2023/11/17

Y1 - 2023/11/17

N2 - By soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to regulate gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power. Our additional software can annotate the scores with target candidates. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs. © 2023 The Author(s).

AB - By soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to regulate gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power. Our additional software can annotate the scores with target candidates. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs. © 2023 The Author(s).

KW - lncRNA

KW - lncRNA-Gene

KW - Controlled Deep-Learning

KW - ensemble methods

UR - http://www.scopus.com/inward/record.url?scp=85175652282&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85175652282&origin=recordpage

U2 - 10.1016/j.isci.2023.108197

DO - 10.1016/j.isci.2023.108197

M3 - RGC 21 - Publication in refereed journal

C2 - 37965148

SN - 2589-0042

VL - 26

JO - iScience

JF - iScience

IS - 11

M1 - 108197

ER -

LncRNA-Top: Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms

Abstract

Bibliographical note

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: DNA Motif Knowledge Extraction and Distillation from Big Deep Learning Models in Regulatory Genomics

Cite this

LncRNA-Top: Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms

Abstract

Bibliographical note

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: DNA Motif Knowledge Extraction and Distillation from Big Deep Learning Models in Regulatory Genomics

Cite this