A preliminary study on the prediction of human protein functions

Authors:
Guido Bologna;Anne-Lise Veuthey;Marco Pagni;Lydie Lane;Amos Bairoch
Affiliations:
CALIPHO Group, Swiss Institute of Bioinformartics, Geneva, Switzerland;Swiss-Prot Group, Swiss Institute of Bioinformartics, Geneva, Switzerland;Vital-IT Group, Swiss Institute of Bioinformartics, Switzerland;CALIPHO Group, Swiss Institute of Bioinformartics, Geneva, Switzerland and Department of Structural Biology and Bioinformatics, University of Geneva, Geneva, Switzerland;CALIPHO Group, Swiss Institute of Bioinformartics, Geneva, Switzerland and Department of Structural Biology and Bioinformatics, University of Geneva, Geneva, Switzerland
Venue:
IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation - Volume Part I
Year:
2011

Citing 4
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization

IEEE Transactions on Knowledge and Data Engineering
Hierarchical multi-label prediction of gene function

Bioinformatics
Decision trees for hierarchical multi-label classification

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the human proteome, about 5'000 proteins lack experimentally validated functional information. In this work we propose to tackle the problem of human protein function prediction by three distinct supervised learning schemes: one-versus-all classification; tournament learning; multi-label learning. Target values of supervised learning models are represented by the nodes of a subset of the Gene Ontology, which is widely used as a benchmark for functional prediction. With an independent dataset including very difficult cases the recall measure reached a reasonable performance for the first 50 ranked predictions, on average; however, average precision was quite low.