A Stacking-Based Classification Approach: Case Study in Volatility Prediction of HIV-1

Mohammad Fili, Guiping Hu (), Changze Han, Alexa Kort and Hillel Haim ()
Additional contact information
Mohammad Fili: Iowa State University
Guiping Hu: Iowa State University
Changze Han: Carver College of Medicine, University of Iowa
Alexa Kort: Carver College of Medicine, University of Iowa
Hillel Haim: Carver College of Medicine, University of Iowa

A chapter in AI and Analytics for Public Health, 2022, pp 355-365 from Springer

Abstract: Abstract Human immunodeficiency virus type 1 (HIV-1) is eminent among chronic viruses for the vast number of therapeutics that exist for it. However, a hurdle to a promising long-term antiviral therapy is the error-prone replication of the viruses. The occurrence of mutations in some patients may result in resistance against medications. As a result, this can lead to increased morbidity and the likelihood of transmission to other individuals. Thus, the dissemination of such impervious mutants is of deep concern. In this study, we proposed a stacking-based classification technique to predict the absence or presence of variance in amino acid sequence of the envelope glycoprotein (Env) of HIV-1 based on the sequence variance of the positions within a specific neighborhood. For this purpose, we used sequence data from HIV-1-infected patients that describe the in-host variance in amino acid sequence (volatility) at each position of the Env protein. We tested the method on 4 different datasets, each corresponding to a specific position on Env. We compared the method with the performance of individual classifiers that have been incorporated into the algorithm as the base learners. We utilized a multi-layer perceptron model as the meta-learner in the second stage. Using the proposed method, we observed improvement in the classification metrics for all cases.

Keywords: Ensemble network algorithm; HIV-1 in-host variance; Multi-layer perceptron (MLP); Stacking (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-3-030-75166-1_26

Ordering information: This item can be ordered from
http://www.springer.com/9783030751661

DOI: 10.1007/978-3-030-75166-1_26

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().