See the published version of this preprint at BMC Bioinformatics.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research article
Jingpu Zhang
Henan University of Urban Construction
Corresponding Author
ORCiD: https://orcid.org/0000-0002-8006-747X
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Circular RNAs (circRNAs) are special noncoding RNA molecules with closed loop structures. Compared with the traditional linear RNA, circRNA is more stable and not easily degraded. Many studies have shown that circRNAs are involved in the regulation of various diseases and cancers. Determining the functions of circRNAs in mammalian cells is of great significance for revealing their mechanism of action in physiological and pathological processes, diagnosis and treatment of diseases. However, determining the functions of circRNAs on a large scale is a challenging task because of the high experimental costs.
In this paper, we present a hierarchical deep learning model, DeepciRGO, which can effectively predict gene ontology functions of circRNAs. We build a heterogeneous network containing circRNA co-expressions, protein-protein interactions (PPIs) and protein-circRNA interactions. The topology features of proteins and circRNAs are calculated using a novel representation learning approach Hin2vec across the heterogeneous network. Then, a deep multi-label hierarchical classification model is trained with the topology features to predict the biological process (BP) function in the Gene Ontology (GO) for each circRNA. In particular, we manually curated a benchmark dataset containing 185 GO annotations for 62 circRNAs, namely, circRNA2GO-62. The DeepciRGO achieves promising performance on the circRNA2GO-62 dataset with a maximum F-measure of 0.412, a recall score of 0.4, and an accuracy of 0.4, which are significantly better than other state-of-the-art RNA function prediction methods. In addition, we demonstrate the considerable potential of integrating multiple interactions and association networks.
Keywords
Gene ontology, Representation learning, Hin2vec, Multi-label hierarchical classi cation
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
This preprint is available for download as a PDF.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at BMC Bioinformatics.
Version (no preprint)
Posted 27 Aug, 2020
Editorial decision: Minor revision
On 25 Aug, 2020
Editor assigned
On 24 Aug, 2020
Submission checks complete
On 23 Aug, 2020
Editor invited
On 23 Aug, 2020
This version was not preprinted
Version 1
Posted 10 Jan, 2020
Community comments: 2
Editorial decision: Major revision
On 25 Apr, 2020
Review #4 received
Received 20 Apr, 2020
Review #2 received
Received 17 Apr, 2020
Review #3 received
Received 17 Apr, 2020
Reviewer #4 agreed
On 28 Mar, 2020
Reviewer #3 agreed
On 25 Mar, 2020
Review #1 received
Received 24 Feb, 2020
Reviewer #1 agreed
On 12 Feb, 2020
Reviewer #2 agreed
On 12 Feb, 2020
Editor assigned
On 17 Jan, 2020
Reviewers invited
Invitations sent on 17 Jan, 2020
Submission checks complete
On 07 Jan, 2020
Editor invited
On 06 Jan, 2020
First submitted
On 23 Dec, 2019
Version (no preprint)
Posted 10 Jan, 2020
Editorial decision: Minor revision
On 14 Aug, 2020
Review #2 received
Received 11 Aug, 2020
Editor assigned
On 23 Jun, 2020
Reviewers invited
Invitations sent on 23 Jun, 2020
Reviewer #1 agreed
On 23 Jun, 2020
Reviewer #2 agreed
On 23 Jun, 2020
Review #1 received
Received 23 Jun, 2020
Submission checks complete
On 22 Jun, 2020
Editor invited
On 22 Jun, 2020
This version was not preprinted
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Bioinformatics
Learn more about our company.
See the published version of this preprint at BMC Bioinformatics.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research article
Jingpu Zhang
Henan University of Urban Construction
Corresponding Author
ORCiD: https://orcid.org/0000-0002-8006-747X
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at BMC Bioinformatics.
Version (no preprint)
Posted 27 Aug, 2020
Editorial decision: Minor revision
On 25 Aug, 2020
Editor assigned
On 24 Aug, 2020
Submission checks complete
On 23 Aug, 2020
Editor invited
On 23 Aug, 2020
This version was not preprinted
Version 1
Posted 10 Jan, 2020
Community comments: 2
Editorial decision: Major revision
On 25 Apr, 2020
Review #4 received
Received 20 Apr, 2020
Review #2 received
Received 17 Apr, 2020
Review #3 received
Received 17 Apr, 2020
Reviewer #4 agreed
On 28 Mar, 2020
Reviewer #3 agreed
On 25 Mar, 2020
Review #1 received
Received 24 Feb, 2020
Reviewer #1 agreed
On 12 Feb, 2020
Reviewer #2 agreed
On 12 Feb, 2020
Editor assigned
On 17 Jan, 2020
Reviewers invited
Invitations sent on 17 Jan, 2020
Submission checks complete
On 07 Jan, 2020
Editor invited
On 06 Jan, 2020
First submitted
On 23 Dec, 2019
Version (no preprint)
Posted 10 Jan, 2020
Editorial decision: Minor revision
On 14 Aug, 2020
Review #2 received
Received 11 Aug, 2020
Editor assigned
On 23 Jun, 2020
Reviewers invited
Invitations sent on 23 Jun, 2020
Reviewer #1 agreed
On 23 Jun, 2020
Reviewer #2 agreed
On 23 Jun, 2020
Review #1 received
Received 23 Jun, 2020
Submission checks complete
On 22 Jun, 2020
Editor invited
On 22 Jun, 2020
This version was not preprinted
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Bioinformatics
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at BMC Bioinformatics.
Circular RNAs (circRNAs) are special noncoding RNA molecules with closed loop structures. Compared with the traditional linear RNA, circRNA is more stable and not easily degraded. Many studies have shown that circRNAs are involved in the regulation of various diseases and cancers. Determining the functions of circRNAs in mammalian cells is of great significance for revealing their mechanism of action in physiological and pathological processes, diagnosis and treatment of diseases. However, determining the functions of circRNAs on a large scale is a challenging task because of the high experimental costs.
In this paper, we present a hierarchical deep learning model, DeepciRGO, which can effectively predict gene ontology functions of circRNAs. We build a heterogeneous network containing circRNA co-expressions, protein-protein interactions (PPIs) and protein-circRNA interactions. The topology features of proteins and circRNAs are calculated using a novel representation learning approach Hin2vec across the heterogeneous network. Then, a deep multi-label hierarchical classification model is trained with the topology features to predict the biological process (BP) function in the Gene Ontology (GO) for each circRNA. In particular, we manually curated a benchmark dataset containing 185 GO annotations for 62 circRNAs, namely, circRNA2GO-62. The DeepciRGO achieves promising performance on the circRNA2GO-62 dataset with a maximum F-measure of 0.412, a recall score of 0.4, and an accuracy of 0.4, which are significantly better than other state-of-the-art RNA function prediction methods. In addition, we demonstrate the considerable potential of integrating multiple interactions and association networks.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
This preprint is available for download as a PDF.
Loading...