Home > Research > Publications & Outputs > Machine learning approach to single nucleotide ...

Links

Text available via DOI:

View graph of relations

Machine learning approach to single nucleotide polymorphism-based asthma prediction

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Machine learning approach to single nucleotide polymorphism-based asthma prediction. / Gaudillo, Joverlyn; Hernandez-Lemus, Enrique (Editor); Rodriguez, Jae Joseph Russell et al.
In: PLoS ONE, Vol. 14, No. 12, e0225574, 04.12.2019.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Gaudillo, J, Hernandez-Lemus, E (ed.), Rodriguez, JJR, Nazareno, A, Baltazar, LR, Vilela, J, Bulalacao, R, Domingo, M & Albia, J 2019, 'Machine learning approach to single nucleotide polymorphism-based asthma prediction', PLoS ONE, vol. 14, no. 12, e0225574. https://doi.org/10.1371/journal.pone.0225574

APA

Gaudillo, J., Hernandez-Lemus, E. (Ed.), Rodriguez, J. J. R., Nazareno, A., Baltazar, L. R., Vilela, J., Bulalacao, R., Domingo, M., & Albia, J. (2019). Machine learning approach to single nucleotide polymorphism-based asthma prediction. PLoS ONE, 14(12), Article e0225574. https://doi.org/10.1371/journal.pone.0225574

Vancouver

Gaudillo J, Hernandez-Lemus E, (ed.), Rodriguez JJR, Nazareno A, Baltazar LR, Vilela J et al. Machine learning approach to single nucleotide polymorphism-based asthma prediction. PLoS ONE. 2019 Dec 4;14(12):e0225574. doi: 10.1371/journal.pone.0225574

Author

Gaudillo, Joverlyn ; Hernandez-Lemus, Enrique (Editor) ; Rodriguez, Jae Joseph Russell et al. / Machine learning approach to single nucleotide polymorphism-based asthma prediction. In: PLoS ONE. 2019 ; Vol. 14, No. 12.

Bibtex

@article{b8a0ca2fafa34c55a3e258b7dbf9975b,
title = "Machine learning approach to single nucleotide polymorphism-based asthma prediction",
abstract = "Machine learning (ML) is poised as a transformational approach uniquely positioned to discover the hidden biological interactions for better prediction and diagnosis of complex diseases. In this work, we integrated ML-based models for feature selection and classification to quantify the risk of individual susceptibility to asthma using single nucleotide polymorphism (SNP). Random forest (RF) and recursive feature elimination (RFE) algorithm were implemented to identify the SNPs with high implication to asthma. K-nearest neighbor (kNN) and support vector machine (SVM) algorithms were trained to classify the identified SNPs whether associated with non-asthmatic or asthmatic samples. Feature selection step showed that RF outperformed RFE and the feature importance score derived from RF was consistently high for a subset of SNPs, indicating the robustness of RF in selecting relevant features associated with asthma. Model comparison showed that the integration of RF-SVM obtained the highest model performance with an accuracy, precision, and sensitivity of 62.5%, 65.3%, and 69%, respectively, when compared to the baseline, RF-kNN, and an external MeanDiff-kNN models. Furthermore, results show that the occurrence of asthma can be predicted with an Area under the Curve (AUC) of 0.62 and 0.64 for RF-SVM and RF-kNN models, respectively. This study demonstrates the integration of ML models to augment traditional methods in predicting genetic predisposition to multifactorial diseases such as asthma.",
author = "Joverlyn Gaudillo and Enrique Hernandez-Lemus and Rodriguez, {Jae Joseph Russell} and Allen Nazareno and Baltazar, {Lei Rigi} and Julianne Vilela and Rommel Bulalacao and Mario Domingo and Jason Albia",
year = "2019",
month = dec,
day = "4",
doi = "10.1371/journal.pone.0225574",
language = "English",
volume = "14",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "12",

}

RIS

TY - JOUR

T1 - Machine learning approach to single nucleotide polymorphism-based asthma prediction

AU - Gaudillo, Joverlyn

AU - Rodriguez, Jae Joseph Russell

AU - Nazareno, Allen

AU - Baltazar, Lei Rigi

AU - Vilela, Julianne

AU - Bulalacao, Rommel

AU - Domingo, Mario

AU - Albia, Jason

A2 - Hernandez-Lemus, Enrique

PY - 2019/12/4

Y1 - 2019/12/4

N2 - Machine learning (ML) is poised as a transformational approach uniquely positioned to discover the hidden biological interactions for better prediction and diagnosis of complex diseases. In this work, we integrated ML-based models for feature selection and classification to quantify the risk of individual susceptibility to asthma using single nucleotide polymorphism (SNP). Random forest (RF) and recursive feature elimination (RFE) algorithm were implemented to identify the SNPs with high implication to asthma. K-nearest neighbor (kNN) and support vector machine (SVM) algorithms were trained to classify the identified SNPs whether associated with non-asthmatic or asthmatic samples. Feature selection step showed that RF outperformed RFE and the feature importance score derived from RF was consistently high for a subset of SNPs, indicating the robustness of RF in selecting relevant features associated with asthma. Model comparison showed that the integration of RF-SVM obtained the highest model performance with an accuracy, precision, and sensitivity of 62.5%, 65.3%, and 69%, respectively, when compared to the baseline, RF-kNN, and an external MeanDiff-kNN models. Furthermore, results show that the occurrence of asthma can be predicted with an Area under the Curve (AUC) of 0.62 and 0.64 for RF-SVM and RF-kNN models, respectively. This study demonstrates the integration of ML models to augment traditional methods in predicting genetic predisposition to multifactorial diseases such as asthma.

AB - Machine learning (ML) is poised as a transformational approach uniquely positioned to discover the hidden biological interactions for better prediction and diagnosis of complex diseases. In this work, we integrated ML-based models for feature selection and classification to quantify the risk of individual susceptibility to asthma using single nucleotide polymorphism (SNP). Random forest (RF) and recursive feature elimination (RFE) algorithm were implemented to identify the SNPs with high implication to asthma. K-nearest neighbor (kNN) and support vector machine (SVM) algorithms were trained to classify the identified SNPs whether associated with non-asthmatic or asthmatic samples. Feature selection step showed that RF outperformed RFE and the feature importance score derived from RF was consistently high for a subset of SNPs, indicating the robustness of RF in selecting relevant features associated with asthma. Model comparison showed that the integration of RF-SVM obtained the highest model performance with an accuracy, precision, and sensitivity of 62.5%, 65.3%, and 69%, respectively, when compared to the baseline, RF-kNN, and an external MeanDiff-kNN models. Furthermore, results show that the occurrence of asthma can be predicted with an Area under the Curve (AUC) of 0.62 and 0.64 for RF-SVM and RF-kNN models, respectively. This study demonstrates the integration of ML models to augment traditional methods in predicting genetic predisposition to multifactorial diseases such as asthma.

U2 - 10.1371/journal.pone.0225574

DO - 10.1371/journal.pone.0225574

M3 - Journal article

VL - 14

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 12

M1 - e0225574

ER -