Emergence of Drug Discovery in Machine Learning
Studies in Computational Intelligence
The discovery of drugs and its pipelines formulation is tough, long, and depend on various factors. Machine Learning comes as a savior to this field and supplies different tools and techniques that are used to drastically improve the discovery as well as the decision-making capabilities for questions that have been well specified and already have an abundant amount of high quality data. There are several possibilities in each and every stage of drug discovery to apply Machine Learning tools and techniques. The applications of Machine Learning have proved from time to time that with some of its approaches generating accurate predictions and insights are very easy. Thus its application has not only been limited to the theoretical part of drug discovery, but has also proven that it can be used in practical conditions too. But there are certain challenges that we need to face that come with Machine Learning. Its inadequacy in terms of interpreting and repeating in its results may sometimes pose as a hindrance to their application in some areas. It also requires consistent and comprehensive high-quality data in almost all areas. There are continuous efforts being put to find a solution for such problems and also growing the reach of machine learning to new fields. Machine Learning can boost data-driven decision-making in this field and has the capability to accelerate the whole process and lessen the failure rates in drug discovery and development.
Open Access Status
This publication is not available as open access