be the best approach to model about 59,000 sequences to discover

ic differentiation of this virus across countries. Therefore, this

will introduce the alignment-free sequence comparison

es which play a key role for a large-scale multiple sequence

on problem.

er 8 will focus on the global optimisation pattern discovery

A typical problem is how to find the optimal and intelligent rules

ase cleavage pattern discovery. This chapter will introduce the

rogramming algorithm and introduce the novel min-max function

iscovery of the optimised decision-making rules for a protease

data. How the genetic programming algorithm works for

kind of data will be introduced in this chapter.

er 9 will outline several recent developments or future research

s in the area of biological pattern discovery using machine

approaches. It covers some cutting-edge studies including the

how to generate sparse neural networks to make models more

r the interpretation, the quantum computing for developing novel

powerful machine learning algorithms, the advanced issues of

ating the evolutionary computation approaches with the deep

approaches to further promote the pattern discovery power as well

vanced protease cleavage problems.

hapters of this book can be read separately because each of them

written for addressing a specific biological pattern discovery

associated with different machine learning algorithms.

y, all introductions and discussions in this book are based on the

mming language, which is a good platform for statistical learning

hine learning. This provides a good opportunity to integrate the

learning theory and algorithms with the workable environment

rchers, especially for the new researchers.