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

BackgroundThere 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. Materials and MethodsHere, 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 (GSE18842). Utilizing a set of standard machine learning (ML) methods which are described in this paper, we were able to uncover subpopulations of ADC and SCC while simultaneously extracting which genes, in combination, were significantly involved in defining the subpopulations. We also utilized a proprietary interactive hypothesis-generating method designed to work with machine learning methods, which provided us with an alternative way of pinpointing the most important combination of variables. The discovered gene expression variables were used to train ML models. This allowed us to create methods using standard methods and to also validate our in-house methods for heterogeneous patient populations, as is often found in oncology. ResultsUsing 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. ConclusionHere we demonstrate the ability to learn from small datasets and reveal well-established properties of NSCLC. This demonstrates the utility for machine learning techniques to reveal potential genes of interest, even from small data sets, and thus the driving factors behind subpopulations of patients.