Computational Systems Biology Methods and Protocols.7z

Chapter 11

Revisit of Machine Learning Supported Biological

and Biomedical Studies

Xiang-tian Yu, Lu Wang, and Tao Zeng

Abstract

Generally, machine learning includes many in silico methods to transform the principles underlying natural
phenomenon to human understanding information, which aim to save human labor, to assist human judge,
and to create human knowledge. It should have wide application potential in biological and biomedical
studies, especially in the era of big biological data. To look through the application of machine learning
along with biological development, this review provides wide cases to introduce the selection of machine
learning methods in different practice scenarios involved in the whole biological and biomedical study cycle
and further discusses the machine learning strategies for analyzing omics data in some cutting-edge
biological studies. Finally, the notes on new challenges for machine learning due to small-sample high-
dimension are summarized from the key points of sample unbalance, white box, and causality.

Key wordsMachine learning, Feature selection, Clustering, Classification, Omics big data, Associa-

tion, Causality, Gut metagenomics, Precision medicine

1 Introduction

Machine learning includes many in silico methods to transform or

abstract the natural principles to human knowledge. The main tasks

have feature engineering or dimension reduction to extract the

object-relevant elements in the study problem [1], clustering to

determine the type or class of object observed in the study field [2],

and classification/regression to predict the type or class for an

unknown object [3].

The general purpose of machine learning is to save human

labor, to assist human judge, and to create human knowledge.

Thus, it should have wide application potential in biological and

biomedical researches [4]. Actually, machine learning has an impor-

tant branch involved in bioinformatics, which try to learn the data

from biological technologies and transform such data to biological

insights [5].

Tao Huang (ed.),Computational Systems Biology: Methods and Protocols, Methods in Molecular Biology, vol. 1754,
https://doi.org/10.1007/978-1-4939-7717-8_11,©Springer Science+Business Media, LLC, part of Springer Nature 2018

183