File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/IHMSC.2013.276
- Scopus: eid_2-s2.0-84891881941
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Synthetic time series resembling human (HeLa) cell-cycle gene expression data and application to gene regulatory network discovery
Title | Synthetic time series resembling human (HeLa) cell-cycle gene expression data and application to gene regulatory network discovery |
---|---|
Authors | |
Keywords | Gene regulatory network Synthetic data Cellcycle Time series Vector autoregressive mode Pearson correlation coefficient Granger causality |
Issue Date | 2013 |
Publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1002959 |
Citation | The 5th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC 2013), Hangzhou, Zhejiang, China, 26-27 August 2013. In Conference Proceedings, 2013, v. 2, p. 538-541 How to Cite? |
Abstract | Evaluation of gene regulatory network (GRN) discovery methods relies heavily on synthetic time series. However, synthetic data generated by traditional method deviate a lot from real data, making such evaluation questionable. Guiding by decaying sinusoids, we propose a new method that generates synthetic data resembling human (HeLa) cell-cycle gene expression data. Using the new synthetic data, a simple comparison between four GRN discovery methods reveals that Granger causality (GC) methods substantially outperform Pearson correlation coefficient (PCC), while time-shifted PCC can give comparable performance as GC methods. The new synthetic data generation would also be useful for generating other kinds of cell-cycle time series. Using data generated by our proposed method, evaluation of GRN discovery methods should be more trustworthy for real-data applications. |
Persistent Identifier | http://hdl.handle.net/10722/186742 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tam, GHF | en_US |
dc.contributor.author | Hung, YS | en_US |
dc.contributor.author | Chang, C | en_US |
dc.date.accessioned | 2013-08-20T12:19:21Z | - |
dc.date.available | 2013-08-20T12:19:21Z | - |
dc.date.issued | 2013 | en_US |
dc.identifier.citation | The 5th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC 2013), Hangzhou, Zhejiang, China, 26-27 August 2013. In Conference Proceedings, 2013, v. 2, p. 538-541 | en_US |
dc.identifier.isbn | 978-0-7695-5011-4 | - |
dc.identifier.uri | http://hdl.handle.net/10722/186742 | - |
dc.description.abstract | Evaluation of gene regulatory network (GRN) discovery methods relies heavily on synthetic time series. However, synthetic data generated by traditional method deviate a lot from real data, making such evaluation questionable. Guiding by decaying sinusoids, we propose a new method that generates synthetic data resembling human (HeLa) cell-cycle gene expression data. Using the new synthetic data, a simple comparison between four GRN discovery methods reveals that Granger causality (GC) methods substantially outperform Pearson correlation coefficient (PCC), while time-shifted PCC can give comparable performance as GC methods. The new synthetic data generation would also be useful for generating other kinds of cell-cycle time series. Using data generated by our proposed method, evaluation of GRN discovery methods should be more trustworthy for real-data applications. | - |
dc.language | eng | en_US |
dc.publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1002959 | - |
dc.relation.ispartof | International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) Proceedings | en_US |
dc.subject | Gene regulatory network | - |
dc.subject | Synthetic data | - |
dc.subject | Cellcycle | - |
dc.subject | Time series | - |
dc.subject | Vector autoregressive mode | - |
dc.subject | Pearson correlation coefficient | - |
dc.subject | Granger causality | - |
dc.title | Synthetic time series resembling human (HeLa) cell-cycle gene expression data and application to gene regulatory network discovery | en_US |
dc.type | Conference_Paper | en_US |
dc.identifier.email | Tam, GHF: hftam@eee.hku.hk | en_US |
dc.identifier.email | Hung, YS: yshung@eee.hku.hk | en_US |
dc.identifier.email | Chang, C: cqchang@eee.hku.hk | - |
dc.identifier.authority | Hung, YS=rp00220 | en_US |
dc.identifier.authority | Chang, C=rp00095 | en_US |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/IHMSC.2013.276 | - |
dc.identifier.scopus | eid_2-s2.0-84891881941 | - |
dc.identifier.hkuros | 220050 | en_US |
dc.identifier.volume | 2 | - |
dc.identifier.spage | 538 | - |
dc.identifier.epage | 541 | - |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 140102 | - |