Analysis of Genetic Disease Haemophilia A by Using Machine Learning

Authors
Kenji Aoki, Makoto Sakamoto, Hiroshi Furutani
Corresponding Author
Kenji Aoki
Available Online 1 September 2015.
DOI
https://doi.org/10.2991/jrnal.2015.2.2.11How to use a DOI?
Keywords
Haemophilia A, Machine Learning, Factor VIII, Amino-acid, Mutation
Abstract
Haemophilia A is a genetic disease resulting from deficiency of factor VIII. The database of mutations causing haemophilia A has been developed by the world wide collaboration. In this study, we examined the relation between activity of factor VIII and the missense mutation by using machine learning. As parameters, we used four physical-chemical parameters of amino acids. We predicted the severity of haemophilia A by using machine learning in factor VIII. As the result, logistic regression is not better than other methods in the prediction of haemophilia A severity. The result of the prediction improved in order to SVM, bagging, boosting and random forest. These results suggested that we can predict the haemophilia A severity by using these methods, and random forest was the best method in these five methods to predict the haemophilia A severity.

Copyright
© 2013, the Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).