ABSTRACT
In this article, we provide an introduction to machine learning tools in theranostics, which address important problems in genomic medicine. The term “theranostics” was probably first used in 2000 to describe the business model of developing diagnostic tests directly linked to the application of specific therapies. It deals with the combination of predictive biomarkers with an effective therapeutic agent. Selection of patients who are most likely responding, or most likely not responding from this specific treatment; “genomic medicine”. One of the objectives of genomic medicine is to analyze the variations in the DNA of individuals, which do affect the risk of different diseases in order to find out the targeted therapies. Here, we focus on how machine learning can help to model the relationship between DNA and the quantities of key molecules in the cell, with the premise that these quantities, which we refer to as cell variables, may be associated with disease risks. Modern biotechnology allows cutting edge research in measuring live atmosphere variables, including gene expression, splicing, and proteins binding to nucleic acids. These variables can be treated as training targets for predictive models in order to treat diseases. With the availability of large-scale data sets, and advanced computational techniques such as deep learning, researchers can help to improve knowledge in theranostics.
