Adaptive Lasso Logistic Regression Applied on Gene Expression of Prostate Cancer

Amir Hossein Hashemian; Maryam Ghobadi Asl; Soodeh Shahsavari; Mansour Rezaei; Hadi Raeisi Shahraki

doi:10.5742/MEWFM.2017.93028

Article Details

Adaptive Lasso Logistic Regression Applied on Gene Expression of Prostate Cancer

Authors:

Amir Hossein Hashemian | Maryam Ghobadi Asl | Soodeh Shahsavari | Mansour Rezaei | Hadi Raeisi Shahraki

Publisher:

medi+WORLD International

Main Topics:

Medicine

Journal:

World Family Medicine Journal: Incorporating the Middle East Journal of Family Medicine 2017 Vol.15 Issue 7, pp.136-141

Document Type:

Article

Publication Date:

9/2017

Document Language:

English

Document ID (Org No.):

109685

Frequency:

Monthly

eISSN:

18390196

pISSN:

18390188

DOI:

10.5742/MEWFM.2017.93028

Descriptors:

Keywords:

Abstract:

 Introduction: The high number of prostate cancer patients has signified the importance of identifying its risk factors. The aim of the present study was to employ stratification method and penalized logistic regression with the adaptive LASSO for selecting appropriate and important genes in prostate cancer.
Materials and Methods: Microarray data used in this study include a prostate cancer gene expression dataset with [HG_U95B] Affymetrix Human Genome U95B Array platform which consisted of 12,620 genes and 167 subjects, among whom 76 subjects were unaffected and the rest were affected with cancer. Using adaptive Lasso regression, important genes in prostate cancer were stratified and the results were analyzed using ROC analysis and gene ontology annotation. To modify and conduct primary measures on the dataset, SPSS software version 22 was used. To fit the models and draw the diagrams, R software version 3.3.1 and penalty specific packages were used.
Findings: According to this research, the obtained adaptive Lasso regression accuracy and confidence interval (CI) were 0.99 and 0.97-0.99, respectively. Considering criteria such as area under the curve and gene ontology annotation, it can be argued that adaptive Lasso regression was fairly effective in stratification and selection of appropriate genes in prostate cancer.
Conclusion: Based on the results of this study, it can be said that in gene expression data, where there are both linear and large scale data, techniques such as adaptive Lasso can be useful in diagnosis of effective genes.

Article Details

Adaptive Lasso Logistic Regression Applied on Gene Expression of Prostate Cancer

Authors:

Amir Hossein Hashemian | Maryam Ghobadi Asl | Soodeh Shahsavari | Mansour Rezaei | Hadi Raeisi Shahraki

Publisher:

medi+WORLD International

Main Topics:

Medicine

Journal:

World Family Medicine Journal: Incorporating the Middle East Journal of Family Medicine 2017 Vol.15 Issue 7, pp.136-141

Document Type:

Article

Publication Date:

9/2017

Document Language:

English

Document ID (Org No.):

109685

Frequency:

Monthly

eISSN:

18390196

pISSN:

18390188

DOI:

10.5742/MEWFM.2017.93028

Descriptors:

PROSTATE

PROSTATITIS

CANCER

GENE EXPRESSION

STRATIFICATION

ALACHLOR

PATIENTS

Regression with Adaptive Lasso

Prostate Cancer

Gene Expression

Stratification

Gene Ontology Annotation

Issues

Article Details

Authors: Amir Hossein Hashemian | Maryam Ghobadi Asl | Soodeh Shahsavari | Mansour Rezaei | Hadi Raeisi Shahraki

Publisher: medi+WORLD International

Main Topics: Medicine

Journal: World Family Medicine Journal: Incorporating the Middle East Journal of Family Medicine 2017 Vol.15 Issue 7, pp.136-141

Document Type: Article

Publication Date: 9/2017

Document Language: English

Document ID (Org No.): 109685

Frequency: Monthly

eISSN: 18390196

pISSN: 18390188

DOI: 10.5742/MEWFM.2017.93028

Descriptors:

Issues

Authors:

Amir Hossein Hashemian | Maryam Ghobadi Asl | Soodeh Shahsavari | Mansour Rezaei | Hadi Raeisi Shahraki

Publisher:

medi+WORLD International

Main Topics:

Medicine

Journal:

World Family Medicine Journal: Incorporating the Middle East Journal of Family Medicine 2017 Vol.15 Issue 7, pp.136-141

Document Type:

Article

Publication Date:

9/2017

Document Language:

English

Document ID (Org No.):

109685

Frequency:

Monthly

eISSN:

18390196

pISSN:

18390188

DOI:

10.5742/MEWFM.2017.93028