A Hierarchical Machine Learning Model to Discover Gleason Grade-Specific Biomarkers in Prostate Cancer

Abstract

1) Background:One of the most common cancers that affect North American men and men worldwide is prostate cancer. The Gleason score is a pathological grading system to examine the potential aggressiveness of the disease in the prostate tissue. Advancements in computing and next-generation sequencing technology now allow us to study the genomic profiles of patients in association with their different Gleason scores more accurately and effectively. (2) Methods: In this study, we used a novel machine learning method to analyse gene expression of prostate tumours with different Gleason scores, and identify potential genetic biomarkers for each Gleason group. We obtained a publicly-available RNA-Seq dataset of a cohort of 104 prostate cancer patients from the National Center for Biotechnology Information's (NCBI) Gene Expression Omnibus (GEO) repository, and categorised patients based on their Gleason scores to create a hierarchy of disease progression. A hierarchical model with standard classifiers in different Gleason groups, also known as nodes, was developed to identify and predict nodes based on their mRNA or gene expression. In each node, patient samples were analysed via class imbalance and hybrid feature selection techniques to build the prediction model. The outcome from analysis of each node was a set of genes that could differentiate each Gleason group from the remaining groups. To validate the proposed method, the set of identified genes were used to classify a second dataset of 499 prostate cancer patients collected from cBioportal. (3) Results: The overall accuracy of applying this novel method to the first dataset was 93.3%; the method was further validated to have 87% accuracy using the second dataset. This method also identified genes that were not previously reported as potential biomarkers for specific Gleason groups. In particular, PIAS3 was identified as a potential biomarker for Gleason score 4 + 3 = 7, and UBE2V2 for Gleason score 6. (4) Insight: Previous reports show that the genes predicted by this newly proposed method strongly correlate with prostate cancer development and progression. Furthermore, pathway analysis shows that both PIAS3 and UBE2V2 share similar protein interaction pathways, the JAK/STAT signaling process.

An integrated approach to biomarker discovery reveals gene signatures highly predictive of cancer progression

“…In addition, the emergence of machine learning applications to RNA-seq data analysis has further augmented the discovery of cancer progression signatures. For example, Rueda et al developed supervised machine learning models to identify multiple novel transcriptomic biomarkers predictive of prostate cancer progression 33 , 34 . However, most current prospective signatures have been found to be poorly reproducible 35 – 37 , likely due to the diverse clinical and technical factors across independent patient cohorts.…”

An Update on the Prognostic and Predictive Serum Biomarkers in Metastatic Prostate Cancer

“…Machine learning is a field that has developed with advances in computing and artificial intelligence. Machine learning models can rapidly analyse large data sets, and their use in identifying biomarkers from genomic data in prostate cancer is promising and attracting much research [ 54 , 55 ].…”

Validating METCAM/MUC18 as a Novel Biomarker to Predict the Malignant Potential of Prostate Cancer at an Early Stage by Using a Modified Gold Nanoparticles-Based Lateral Flow Immunoassay

“…However, the elevated level of PSA in the serum is not always prognostic of the correct pathologic stage of the cancer or the presence of an indolent or a metastatic disease; thus, it results in at least 20–25% of false diagnosis [ 4 ]. Many potential biomarkers for predicting prostate cancer progression have been published [ 5 , 6 , 7 , 8 ] and some of them are even Gleason grade-specific biomarkers [ 8 ]. However, only PSA, Prostate Health Index, and PCA3 have been approved by Food and Drug Administration for the diagnosis of prostate cancer [ 5 ].…”