File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: MetaProm: A neural network based meta-predictor for alternative human promoter prediction

TitleMetaProm: A neural network based meta-predictor for alternative human promoter prediction
Authors
Issue Date2007
PublisherBioMed Central Ltd. The Journal's web site is located at http://www.biomedcentral.com/bmcgenomics/
Citation
BMC Genomics, 2007, v. 8 n. 374, p. 1-13 How to Cite?
AbstractBackground: De novo eukaryotic promoter prediction is important for discovering novel genes and understanding gene regulation. In spite of the great advances made in the past decade, recent studies revealed that the overall performances of the current promoter prediction programs (PPPs) are still poor, and predictions made by individual PPPs do not overlap each other. Furthermore, most PPPs are trained and tested on the most-upstream promoters; their performances on alternative promoters have not been assessed. Results: In this paper, we evaluate the performances of current major promoter prediction programs (i.e., PSPA, FirstEF, McPromoter, DragonGSF, DragonPF, and FProm) using 42,536 distinct human gene promoters on a genome-wide scale, and with emphasis on alternative promoters. We describe an artificial neural network (ANN) based meta-predictor program that integrates predictions from the current PPPs and the predicted promoters' relation to CpG islands. Our specific analysis of recently discovered alternative promoters reveals that although only 41% of the 3′ most promoters overlap a CpG island, 74% of 5′ most promoters overlap a CpG island. Conclusion: Our assessment of six PPPs on 1.06 × 109 bps of human genome sequence reveals the specific strengths and weaknesses of individual PPPs. Our meta-predictor outperforms any individual PPP in sensitivity and specificity. Furthermore, we discovered that the 5′ alternative promoters are more likely to be associated with a CpG island. © 2007 Wang et al; licensee BioMed Central Ltd.
Persistent Identifierhttp://hdl.handle.net/10722/61601
ISSN
2023 Impact Factor: 3.5
2023 SCImago Journal Rankings: 1.047
PubMed Central ID
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorWang, Jen_HK
dc.contributor.authorUngar, LHen_HK
dc.contributor.authorTseng, Hen_HK
dc.contributor.authorHannenhalli, Sen_HK
dc.date.accessioned2010-07-13T03:43:15Z-
dc.date.available2010-07-13T03:43:15Z-
dc.date.issued2007en_HK
dc.identifier.citationBMC Genomics, 2007, v. 8 n. 374, p. 1-13en_HK
dc.identifier.issn1471-2164en_HK
dc.identifier.urihttp://hdl.handle.net/10722/61601-
dc.description.abstractBackground: De novo eukaryotic promoter prediction is important for discovering novel genes and understanding gene regulation. In spite of the great advances made in the past decade, recent studies revealed that the overall performances of the current promoter prediction programs (PPPs) are still poor, and predictions made by individual PPPs do not overlap each other. Furthermore, most PPPs are trained and tested on the most-upstream promoters; their performances on alternative promoters have not been assessed. Results: In this paper, we evaluate the performances of current major promoter prediction programs (i.e., PSPA, FirstEF, McPromoter, DragonGSF, DragonPF, and FProm) using 42,536 distinct human gene promoters on a genome-wide scale, and with emphasis on alternative promoters. We describe an artificial neural network (ANN) based meta-predictor program that integrates predictions from the current PPPs and the predicted promoters' relation to CpG islands. Our specific analysis of recently discovered alternative promoters reveals that although only 41% of the 3′ most promoters overlap a CpG island, 74% of 5′ most promoters overlap a CpG island. Conclusion: Our assessment of six PPPs on 1.06 × 109 bps of human genome sequence reveals the specific strengths and weaknesses of individual PPPs. Our meta-predictor outperforms any individual PPP in sensitivity and specificity. Furthermore, we discovered that the 5′ alternative promoters are more likely to be associated with a CpG island. © 2007 Wang et al; licensee BioMed Central Ltd.en_HK
dc.languageengen_HK
dc.publisherBioMed Central Ltd. The Journal's web site is located at http://www.biomedcentral.com/bmcgenomics/en_HK
dc.relation.ispartofBMC Genomicsen_HK
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.rightsBMC Genomics. Copyright © BioMed Central Ltd.-
dc.subject.meshCpG Islands-
dc.subject.meshGenome, Human-
dc.subject.meshHumans-
dc.subject.meshNeural Networks (Computer)-
dc.subject.meshPromoter Regions, Genetic-
dc.titleMetaProm: A neural network based meta-predictor for alternative human promoter predictionen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1471-2164&volume=8&issue=374&spage=1&epage=13&date=2007&atitle=MetaProm:+a+neural+network+based+meta-predictor+for+alternative+human+promoter+prediction-
dc.identifier.emailWang, J:junwen@hkucc.hku.hken_HK
dc.identifier.authorityWang, J=rp00280en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1186/1471-2164-8-374en_HK
dc.identifier.pmid17941982-
dc.identifier.pmcidPMC2194789-
dc.identifier.scopuseid_2-s2.0-38049156077en_HK
dc.identifier.hkuros156647en_HK
dc.identifier.hkuros166789-
dc.identifier.hkuros213293-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-38049156077&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume8en_HK
dc.identifier.issue374-
dc.identifier.spage1-
dc.identifier.epage13-
dc.identifier.isiWOS:000252439000001-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridWang, J=8950599500en_HK
dc.identifier.scopusauthoridUngar, LH=7006123330en_HK
dc.identifier.scopusauthoridTseng, H=19637691100en_HK
dc.identifier.scopusauthoridHannenhalli, S=6603889650en_HK
dc.identifier.citeulike1798440-
dc.identifier.issnl1471-2164-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats