Can We Convert Genotype Sequences Into Images for Cases/Controls Classification?
Converting genotype sequences into images offers advantages, such as genotype data visualization, classification, and comparison of genotype sequences. This study converted genotype sequences into images, applied two-dimensional convolutional neural networks for case/control classification, and comp...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-06-01
|
Series: | Frontiers in Bioinformatics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fbinf.2022.914435/full |
_version_ | 1811344389933367296 |
---|---|
author | Muhammad Muneeb Muhammad Muneeb Samuel F. Feng Samuel F. Feng Andreas Henschel Andreas Henschel |
author_facet | Muhammad Muneeb Muhammad Muneeb Samuel F. Feng Samuel F. Feng Andreas Henschel Andreas Henschel |
author_sort | Muhammad Muneeb |
collection | DOAJ |
description | Converting genotype sequences into images offers advantages, such as genotype data visualization, classification, and comparison of genotype sequences. This study converted genotype sequences into images, applied two-dimensional convolutional neural networks for case/control classification, and compared the results with the one-dimensional convolutional neural network. Surprisingly, the average accuracy of multiple runs of 2DCNN was 0.86, and that of 1DCNN was 0.89, yielding a difference of 0.03, which suggests that even the 2DCNN algorithm works on genotype sequences. Moreover, the results generated by the 2DCNN exhibited less variation than those generated by the 1DCNN, thereby offering greater stability. The purpose of this study is to draw the research community’s attention to explore encoding schemes for genotype data and machine learning algorithms that can be used on genotype data by changing the representation of the genotype data for case/control classification. |
first_indexed | 2024-04-13T19:46:35Z |
format | Article |
id | doaj.art-b03d93d31399480285d24ad6c2a5c392 |
institution | Directory Open Access Journal |
issn | 2673-7647 |
language | English |
last_indexed | 2024-04-13T19:46:35Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Bioinformatics |
spelling | doaj.art-b03d93d31399480285d24ad6c2a5c3922022-12-22T02:32:43ZengFrontiers Media S.A.Frontiers in Bioinformatics2673-76472022-06-01210.3389/fbinf.2022.914435914435Can We Convert Genotype Sequences Into Images for Cases/Controls Classification?Muhammad Muneeb0Muhammad Muneeb1Samuel F. Feng2Samuel F. Feng3Andreas Henschel4Andreas Henschel5Department of Mathematics, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesDepartment of Electrical Engineering and Computer Science, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesDepartment of Mathematics, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesResearch and Data Intelligence Support Center R-DISC, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesDepartment of Electrical Engineering and Computer Science, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesResearch and Data Intelligence Support Center R-DISC, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesConverting genotype sequences into images offers advantages, such as genotype data visualization, classification, and comparison of genotype sequences. This study converted genotype sequences into images, applied two-dimensional convolutional neural networks for case/control classification, and compared the results with the one-dimensional convolutional neural network. Surprisingly, the average accuracy of multiple runs of 2DCNN was 0.86, and that of 1DCNN was 0.89, yielding a difference of 0.03, which suggests that even the 2DCNN algorithm works on genotype sequences. Moreover, the results generated by the 2DCNN exhibited less variation than those generated by the 1DCNN, thereby offering greater stability. The purpose of this study is to draw the research community’s attention to explore encoding schemes for genotype data and machine learning algorithms that can be used on genotype data by changing the representation of the genotype data for case/control classification.https://www.frontiersin.org/articles/10.3389/fbinf.2022.914435/fullgenotype-phenotype predictiongeneticsbioinformaticsapplied machine learningimage classification |
spellingShingle | Muhammad Muneeb Muhammad Muneeb Samuel F. Feng Samuel F. Feng Andreas Henschel Andreas Henschel Can We Convert Genotype Sequences Into Images for Cases/Controls Classification? Frontiers in Bioinformatics genotype-phenotype prediction genetics bioinformatics applied machine learning image classification |
title | Can We Convert Genotype Sequences Into Images for Cases/Controls Classification? |
title_full | Can We Convert Genotype Sequences Into Images for Cases/Controls Classification? |
title_fullStr | Can We Convert Genotype Sequences Into Images for Cases/Controls Classification? |
title_full_unstemmed | Can We Convert Genotype Sequences Into Images for Cases/Controls Classification? |
title_short | Can We Convert Genotype Sequences Into Images for Cases/Controls Classification? |
title_sort | can we convert genotype sequences into images for cases controls classification |
topic | genotype-phenotype prediction genetics bioinformatics applied machine learning image classification |
url | https://www.frontiersin.org/articles/10.3389/fbinf.2022.914435/full |
work_keys_str_mv | AT muhammadmuneeb canweconvertgenotypesequencesintoimagesforcasescontrolsclassification AT muhammadmuneeb canweconvertgenotypesequencesintoimagesforcasescontrolsclassification AT samuelffeng canweconvertgenotypesequencesintoimagesforcasescontrolsclassification AT samuelffeng canweconvertgenotypesequencesintoimagesforcasescontrolsclassification AT andreashenschel canweconvertgenotypesequencesintoimagesforcasescontrolsclassification AT andreashenschel canweconvertgenotypesequencesintoimagesforcasescontrolsclassification |