File(s) under permanent embargo
IPA: Integrated predictive gene signature from gene expression based breast cancer patient samples
conference contribution
posted on 2014-05-03, 00:00 authored by Ashish Saini, Jingyu HouJingyu Hou, Wanlei ZhouBackground: Novel predictive markers are needed to accurately diagnose the breast cancer patients so they do not need to undergo any unnecessary aggressive therapies. Various gene expression studies based predictive gene signatures
have generated in the recent past to predict the binary estrogen-receptor subclass or to predict the therapy response subclass. However, the existing algorithms comes with many limitations, including low predictive performances over multiple cohorts of patients and non-significant or limited biological roles associated with the
predictive gene signatures. Therefore, the aim of this study is to develop novel predictive markers with improved performances.
Methods: We propose a novel prediction algorithm called IPA to construct a predictive gene signature for performing multiple prediction tasks of predicting estrogen-receptor based binary subclass and predicting chemotherapy response (neoadjuvantly) based binary subclass. The constructed gene signature with considering multiple classification techniques was used to evaluate the algorithm performance on multiple cohorts of breast cancer patients.
Results: The evaluation on multiple validation cohorts demonstrated that proposed algorithm achieved stable and high performance to perform prediction tasks, with consideration given to any classification techniques. We show that the predictive gene signature of our proposed algorithm reflects the mechanisms underlying the estrogen-receptors or response to therapy with significant greater biological interpretations, compared with the other existing algorithm.
have generated in the recent past to predict the binary estrogen-receptor subclass or to predict the therapy response subclass. However, the existing algorithms comes with many limitations, including low predictive performances over multiple cohorts of patients and non-significant or limited biological roles associated with the
predictive gene signatures. Therefore, the aim of this study is to develop novel predictive markers with improved performances.
Methods: We propose a novel prediction algorithm called IPA to construct a predictive gene signature for performing multiple prediction tasks of predicting estrogen-receptor based binary subclass and predicting chemotherapy response (neoadjuvantly) based binary subclass. The constructed gene signature with considering multiple classification techniques was used to evaluate the algorithm performance on multiple cohorts of breast cancer patients.
Results: The evaluation on multiple validation cohorts demonstrated that proposed algorithm achieved stable and high performance to perform prediction tasks, with consideration given to any classification techniques. We show that the predictive gene signature of our proposed algorithm reflects the mechanisms underlying the estrogen-receptors or response to therapy with significant greater biological interpretations, compared with the other existing algorithm.
History
Event
Stem Cell Research, Cancer Biology and Applied Biotechnology. World Congress (2014 : New Delhi, India)Source
Innovative Approach in Stem Cell Research, Cancer Biology and Applied BiotechnologyPagination
13 - 30Publisher
Excellent Publishing HouseLocation
New Delhi, IndiaPlace of publication
Kishangarh, New DelhiStart date
2014-05-03End date
2014-05-03ISBN-13
9789383083794Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2014, Excellent Publishing HouseEditor/Contributor(s)
A Johri, G MishraTitle of proceedings
Biotech 2014 : Innovative Approach in Stem Cell Research, Cancer Biology and Applied BiotechnologyUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC