Engineering thermostable enzymes; application of unsupervised clustering algorithms
Date
2011
Authors
Lakizadeh, A.
Agha-Golzadeh, P.
Ebrahimi, M.
Ebrahimie, E.
Ebrahimi, M.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Advanced Studies in Biology, 2011; 3(2):63-78
Statement of Responsibility
Amir Lakizadeh, Parisa Agha-Golzadeh, Mansour Ebrahimi, Esmaeil Ebrahimie and Mahdi Ebrahimi
Conference Name
Abstract
There is a high demand for engineering thermostable enzymes in some industries; especially in paper industries to use environmental friendly enzymes instead of toxic chlorine chemicals. Hence, understanding protein attributes involved in enzyme thermostability is important. Herein, the most important protein features contributing to enzyme thermostability was searched by using data mining algorithms. Combination of attribute weighting and unsupervised clustering algorithms were used to explore protein attributes which play major roles in thermostability. The results showed that expectation maximization clustering with uncertainly and correlation attribute weighting algorithms can effectively (100%) classify thermo- and meso-stable proteins. Gln content and frequency of hydrophilic residues were the most important protein features selected by 70% of weighing methods. The findings of this research provide the required knowledge for engineering thermostable enzymes in laboratory.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright status unknown