RTI uses cookies to offer you the best experience online. By clicking “accept” on this website, you opt in and you agree to the use of cookies. If you would like to know more about how RTI uses cookies and how to manage them please view our Privacy Policy here. You can “opt out” or change your mind by visiting: http://optout.aboutads.info/. Click “accept” to agree.
Statistical methods for supervised learning in high-dimensional omics data
Sedaghat, N., Stanway, I. B., Zangeneh, S., WA, U. O. W., & Shojaie, A. (2017). Bioinformatics in toxicology: Statistical methods for supervised learning in high-dimensional omics data. In C. McQueen (Ed.), Comprehensive Toxicology (3rd ed., Vol. 1, pp. 447-472) https://doi.org/10.1016/B978-0-12-801238-3.64209-5
Toxicology plays a key role in public and environmental health. Traditionally, animals exposing to toxicants were used in toxicity tests. Fueled by rapid technologies advances, the majority of animal tests have recently been replaced by tests based on high-throughput data. In this regard, toxicogenomics helps discover the relationship between toxicant exposure and its impacts on genomics. Bioinformatics tools and statistical machine learning are the primary tools in drawing scientific conclusions in this endeavor. This chapter briefly describes various types of high-throughput data applicable to toxicogenomic studies and required preprocessing steps. Further, two main categories of statistical analyses, namely univariate and multivariate analysis are discussed with an emphasis on discrete, continuous, and survival outcomes. Reproducibility and generalizability considerations are emphasized throughout the chapter.
