In:
PLOS Computational Biology, Public Library of Science (PLoS), Vol. 17, No. 10 ( 2021-10-11), p. e1009433-
Abstract:
Most predictive models based on gene expression data do not leverage information related to gene splicing, despite the fact that splicing is a fundamental feature of eukaryotic gene expression. Cigarette smoking is an important environmental risk factor for many diseases, and it has profound effects on gene expression. Using smoking status as a prediction target, we developed deep neural network predictive models using gene, exon, and isoform level quantifications from RNA sequencing data in 2,557 subjects in the COPDGene Study. We observed that models using exon and isoform quantifications clearly outperformed gene-level models when using data from 5 genes from a previously published prediction model. Whereas the test set performance of the previously published model was 0.82 in the original publication, our exon-based models including an exon-to-isoform mapping layer achieved a test set AUC (area under the receiver operating characteristic) of 0.88, which improved to an AUC of 0.94 using exon quantifications from a larger set of genes. Isoform variability is an important source of latent information in RNA-seq data that can be used to improve clinical prediction models.
Type of Medium:
Online Resource
ISSN:
1553-7358
DOI:
10.1371/journal.pcbi.1009433
DOI:
10.1371/journal.pcbi.1009433.g001
DOI:
10.1371/journal.pcbi.1009433.g002
DOI:
10.1371/journal.pcbi.1009433.g003
DOI:
10.1371/journal.pcbi.1009433.g004
DOI:
10.1371/journal.pcbi.1009433.g005
DOI:
10.1371/journal.pcbi.1009433.t001
DOI:
10.1371/journal.pcbi.1009433.t002
DOI:
10.1371/journal.pcbi.1009433.t003
DOI:
10.1371/journal.pcbi.1009433.t004
DOI:
10.1371/journal.pcbi.1009433.s001
DOI:
10.1371/journal.pcbi.1009433.s002
DOI:
10.1371/journal.pcbi.1009433.s003
DOI:
10.1371/journal.pcbi.1009433.s004
DOI:
10.1371/journal.pcbi.1009433.s005
DOI:
10.1371/journal.pcbi.1009433.s006
DOI:
10.1371/journal.pcbi.1009433.s007
DOI:
10.1371/journal.pcbi.1009433.s008
DOI:
10.1371/journal.pcbi.1009433.s009
DOI:
10.1371/journal.pcbi.1009433.s010
DOI:
10.1371/journal.pcbi.1009433.s011
DOI:
10.1371/journal.pcbi.1009433.r001
DOI:
10.1371/journal.pcbi.1009433.r002
DOI:
10.1371/journal.pcbi.1009433.r003
DOI:
10.1371/journal.pcbi.1009433.r004
DOI:
10.1371/journal.pcbi.1009433.r005
DOI:
10.1371/journal.pcbi.1009433.r006
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2021
detail.hit.zdb_id:
2193340-6
Bookmarklink