Читать книгу Data Analytics in Bioinformatics - Группа авторов - Страница 10

Preface

Machine learning has become increasingly popular in recent decades due to its well-defined algorithms and techniques that enable computers to learn and solve real-life problems which are difficult, time-consuming, and tedious to solve traditionally. Regarded as a subdomain of artificial intelligence, it has a gamut of applications in the field of healthcare, medical diagnosis, bioinformatics, natural language processing, stock market analysis and many more. Recently, there has been an explosion of heterogeneous biological data requiring analysis, retrieval of useful patterns, management and proper storage. Moreover, there is the additional challenge of developing automated tools and techniques that can deal with these different kinds of outsized data in order to translate and transform computational modelling of biological systems and its correlated disciplinary data for further classification, clustering, prediction and decision-making.

Machine learning has justified its potential with its application in extracting relevant information in various biological domains like bioinformatics. It has been successful in dealing with and finding efficient solutions for complex biomedical problems. Prior to the application of machine learning, traditional mathematical as well as statistical models were used along with the domain of expert intelligence to carry out investigations and experiments manually, using instruments, hands and eyes, etc. But such conventional methods alone are not enough to deal with large volumes of different types of biological data. Hence, the application of machine learning techniques has become the need of the hour in research in order to find a solution to complex bioinformatics applications for both the disciplines of computer science and biology. With this in mind, this book has been designed with a number of chapters from eminent researchers who relate and explain the machine learning techniques and their application to various bioinformatics problems such as classification and prediction of disease, feature selection, dimensionality reduction, gene selection, etc. Since the chapters are based on progressive collaborative research work on a broad range of topics and implementations, it will be of interest to both students and researchers from the computer science as well as biological domains.

This edited book is compiled using four sections, with the first section rationalizing the applications of machine learning techniques in bioinformatics with introductory chapters. The subsequent chapters in the second section flows with machine learning technological applications for dimensionality reduction, feature & gene selection, plant disease analysis & prediction as well as cluster analysis. Further, the third section of the book brings together a variety of machine learning research applications to healthcare domain. Then the book dives into the concluding remarks of machine learning applications to stock market behavioural analysis and prediction.

The Editors

December 2020