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.
Highlights
Smoking is the most important environmental risk factor for a wide range of diseases including cardiovascular disease, lung cancer, and chronic obstructive pulmonary disease (COPD)
While gene expression microarrays were first used for genomewide transcriptomics profiling, massively parallel high-throughput RNA sequencing (RNA-seq) is the standard, and one of the benefits of RNA-seq is that it can directly measure exon expression and detect junctional reads (i.e. RNA-seq reads spanning exons) which allows for estimation of transcript isoforms
Using blood RNA-seq data from 2,557 subjects in the COPDGene Study, we explored the relative utility of expression measures at the gene, exon, and isoform level using deep learning models [13] tailored to account for patterns of alternative splicing induced by smoking
Summary
Smoking is the most important environmental risk factor for a wide range of diseases including cardiovascular disease, lung cancer, and chronic obstructive pulmonary disease (COPD). Using RNA-seq combined with novel isoform reconstruction algorithms, we have shown that smoking causes widespread differential isoform and exon usage in addition to overall gene-level expression changes [3]. High throughput measurements of gene expression in biological samples have been shown to capture information relevant to complex biological processes such as cell cycle [5], stress response [6], and medical disease states [7]. It has been shown that the additional information that RNA-seq provides on alternative splicing allows for more sensitive detection of transcriptomic differences between cancer subtypes, but this information did not necessarily lead to improved prediction of clinical outcomes [12], suggesting that there may be latent information in RNA-seq data related to splicing that may require novel modeling approaches to better utilize this information
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
