TY - GEN
T1 - Using Gene-level to Generalize Transcript-level Classification Performance on Multiple Colorectal Cancer Microarray Studies
AU - Lim, Hendrick Gao Min
AU - Lee, Yuan Chii Gladys
N1 - Publisher Copyright:
© 2020 ACM.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/1/19
Y1 - 2020/1/19
N2 - Several classification algorithms have been applied into microarray studies for colorectal cancer identification. Algorithms such as naïve bayes, random forest, logistic regression, support vector machine, and deep learning have been successfully used in previous studies. The accuracy of these algorithms shown promising result through n-fold validation. However, most of studies are limited to transcript-level that will implicate to biased interpretation of classification result due to different microarray platform entanglement. Therefore, we applied gene-level classification to generalize transcript-level classification result on multiple colorectal cancer microarray studies through different classification algorithms including: naïve Bayes, random forest, logistic regression, support vector machine, and deep learning. We evaluated classification performance using several parameters including: accuracy, area under ROC curve, recall and precision. As the result, we found biased classification result in transcript-level from multiple microarray studies can be solved through gene-level classification by applying annotation and merging. In addition, applying batch effect removal method can make gene-level classification performance slightly improved. Furthermore, annotation and merging also can be used to solve another biased result of feature selection in transcript-level.
AB - Several classification algorithms have been applied into microarray studies for colorectal cancer identification. Algorithms such as naïve bayes, random forest, logistic regression, support vector machine, and deep learning have been successfully used in previous studies. The accuracy of these algorithms shown promising result through n-fold validation. However, most of studies are limited to transcript-level that will implicate to biased interpretation of classification result due to different microarray platform entanglement. Therefore, we applied gene-level classification to generalize transcript-level classification result on multiple colorectal cancer microarray studies through different classification algorithms including: naïve Bayes, random forest, logistic regression, support vector machine, and deep learning. We evaluated classification performance using several parameters including: accuracy, area under ROC curve, recall and precision. As the result, we found biased classification result in transcript-level from multiple microarray studies can be solved through gene-level classification by applying annotation and merging. In addition, applying batch effect removal method can make gene-level classification performance slightly improved. Furthermore, annotation and merging also can be used to solve another biased result of feature selection in transcript-level.
KW - Classification
KW - Colorectal cancer
KW - Gene-level
KW - Microarray
KW - Transcript-level
UR - http://www.scopus.com/inward/record.url?scp=85089136621&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089136621&partnerID=8YFLogxK
U2 - 10.1145/3386052.3386064
DO - 10.1145/3386052.3386064
M3 - Conference contribution
AN - SCOPUS:85089136621
T3 - ACM International Conference Proceeding Series
SP - 64
EP - 68
BT - ICBBB 2020 - Proceedings of 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics
PB - Association for Computing Machinery, Inc
T2 - 10th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2020
Y2 - 19 January 2020 through 22 January 2020
ER -