Prediction of Protein Secondary Structures of All Types Using New Hypersphere Machine Learning Method

Authors:
Markku Siermala
Affiliations:
-
Venue:
AIME '01 Proceedings of the 8th Conference on AI in Medicine in Europe: Artificial Intelligence Medicine
Year:
2001

Citing 2
Cited 1

Bioinformatics: the machine learning approach

Bioinformatics: the machine learning approach
Machine Learning

Machine Learning

Behaviour of protein secondary structure types in the sequence space of a certain length

Intelligent Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new hypersphere machine learning method and use it to predict all protein secondary structures. It finds sequences with sufficiently high homology. Prediction accuracy of the new method with protein secondary structures was good (average 89.3%). However, the method could not classify all test cases.