Deep Learning Techniques to Characterize the RPS28P7 Pseudogene and the Metazoa- SRP Gene as Drug Potential Targets in Pancreatic Cancer Patients

Abstract

The molecular explanation about why some pancreatic cancer (PaCa) patients die early and others die later is poorly understood. This study aimed to discover potential novel markers and drug targets that could be useful to stratify and extend expected survival in prospective early-death patients. We deployed a deep learning algorithm and analyzed the gene copy number, gene expression, and protein expression data of death versus alive PaCa patients from the GDC cohort. The genes with higher relative amplification (copy number >4 times in the dead compared with the alive group) were EWSR1, FLT3, GPC3, HIF1A, HLF, and MEN1. The most highly up-regulated genes (>8.5-fold change) in the death group were RPL30, RPL37, RPS28P7, RPS11, Metazoa_SRP, CAPNS1, FN1, H3-3B, LCN2, and OAZ1. None of their corresponding proteins were up or down-regulated in the death group. The mRNA of the RPS28P7 pseudogene could act as ceRNA sponging the miRNA that was originally directed to the parental gene RPS28. We propose RPS28P7 mRNA as the most druggable target that can be modulated with small molecules or the RNA technology approach. These markers could be added as criteria to patient stratification in future PaCa drug trials, but further validation in the target populations is encouraged.

Keywords: biomarkers; deep learning; gene copy number; gene expression; lethality; pancreatic cancer.

Figure 1

General methodology. Procedure to identify the survival expectation in patients with pancreatic cancer based on Deep Learning aiming to detect possible markers or drug targets.

Figure 2

ANN Topology. The ANN has an input layer based on LSTM, a dropout layer, a feedforward neural network, and a softmax layer as the output layer.

Figure 3

Classification performance. Receiver operating characteristic curve of the classification process of the multiomics information.

Figure 4

Metazoa_SRP RNA representation. Representation of the secondary structure of the non-coding Metazoa_SRP RNA (signal recognition particle RNA; RF00017) part of the signal recognition particle (SRP) ribonucleoprotein complex. The representation was depicted by Rscape [28], using the alignment of 91 metazoan species from the Rfam database [14].