Background: Host immune response is coordinated by a variety of different specialized cell types that vary in time and location. While host immune response can be studied using conventional low-dimensional approaches, advances in transcriptomics analysis may provide a less biased view. Yet, leveraging transcriptomics data to identify immune cell subtypes presents challenges for extracting informative gene signatures hidden within a high dimensional transcriptomics space characterized by low sample numbers with noisy and missing values. To address these challenges, we explore using machine learning methods to select gene subsets and estimate gene coefficients simultaneously.Results: Elastic-net logistic regression, a type of machine learning, was used to construct separate classifiers for ten different types of immune cell and for five T helper cell subsets. The resulting classifiers were then used to develop gene signatures that best discriminate among immune cell types and T helper cell subsets using RNA-seq datasets. We validated the approach using single-cell RNA-seq (scRNA-seq) datasets, which gave consistent results. In addition, we classified cell types that were previously unannotated. Finally, we benchmarked the proposed gene signatures against other existing gene signatures. Conclusions: Developed classifiers can be used as priors in predicting the extent and functional orientation of the host immune response in diseases, such as cancer, where transcriptomic profiling of bulk tissue samples and single cells are routinely employed. Information that can provide insight into the mechanistic basis of disease and therapeutic response. The source code and documentation are available through GitHub: https://github.com/KlinkeLab/ImmClass2019.
Abstract:The return on investment within the pharmaceutical industry has exhibited an exponential decline over the last several decades. Contemporary analysis suggests that the rate-limiting step associated with the drug discovery and development process is our limited understanding of the disease pathophysiology in humans that is targeted by a drug. Similar to other industries, mechanistic modeling and simulation has been proposed as an enabling quantitative tool to help address this problem. Moreover, immunotherapies are transforming the clinical treatment of cure cancer and are becoming a major segment of the pharmaceutical research and development pipeline. As the clinical benefit of these immunotherapies seems to be limited to subset of the patient population, identifying the specific defect in the complex network of interactions associated with host immunity to a malignancy is a major challenge for expanding the clinical benefit. Understanding the interaction between malignant and immune cells is inherently a systems problem, where an engineering perspective may be helpful. The objective of this manuscript is to summarize this quantitative systems perspective, particularly with respect to developing immunotherapies for the treatment of cancer.
OPEN ACCESSProcesses 2015, 3 236
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.