Small Patient Datasets Reveal Genetic Drivers of Non-Small Cell Lung Cancer Subtypes using a Novel Machine Learning Approach

Abstract

AbstractThere are many small datasets of significant value in the medical space that are being underutilized. Due to the heterogeneity of complex disorders found in oncology, systems capable of discovering patient subpopulations while elucidating etiologies is of great value as it can indicate leads for innovative drug discovery and development. Here, we report on a machine intelligence-based study that utilized a combination of two small non-small cell lung cancer (NSCLC) datasets consisting of 58 samples of adenocarcinoma (ADC) and squamous cell carcinoma (SCC) and 45 samples from the gene expression analysis of human lung cancer and control samples series (GSE18842). Utilizing a novel machine learning approach, we were able to uncover subpopulations of ADC and SCC while simultaneously extracting which genes, in combination, were significantly involved in defining the subpopulations. An interactive hypothesis-generating interface designed to work with machine learning methods allowed us to explore the hypotheses generated by the unsupervised components of the system. Using these methods, we were able to uncover genes implicated by other methods and accurately discover known subpopulations without being asked, such as different levels of aggressiveness within the SCC and ADC subtypes. Furthermore, PIGX was a novel gene implicated in this study that warrants further study due to its role in breast cancer proliferation. Here we demonstrate the ability to learn from small datasets and reveal well-established properties of NSCLC. These machine learning techniques can reveal the driving factors behind subpopulations of patients altering the approach to drug discovery and development by making precision medicine a reality.