Deep Neural Architectures for Highly Imbalanced Data in Bioinformatics.
IEEE Trans Neural Netw Learn Syst
; 31(8): 2857-2867, 2020 08.
Article
de En
| MEDLINE
| ID: mdl-31170082
ABSTRACT
In the postgenome era, many problems in bioinformatics have arisen due to the generation of large amounts of imbalanced data. In particular, the computational classification of precursor microRNA (pre-miRNA) involves a high imbalance in the classes. For this task, a classifier is trained to identify RNA sequences having the highest chance of being miRNA precursors. The big issue is that well-known pre-miRNAs are usually just a few in comparison to the hundreds of thousands of candidate sequences in a genome, which results in highly imbalanced data. This imbalance has a strong influence on most standard classifiers and, if not properly addressed, the classifier is not able to work properly in a real-life scenario. This work provides a comparative assessment of recent deep neural architectures for dealing with the large imbalanced data issue in the classification of pre-miRNAs. We present and analyze recent architectures in a benchmark framework with genomes of animals and plants, with increasing imbalance ratios up to 12000. We also propose a new graphical way for comparing classifiers performance in the context of high-class imbalance. The comparative results obtained show that, at a very high imbalance, deep belief neural networks can provide the best performance.
Texte intégral:
1
Collection:
01-internacional
Base de données:
MEDLINE
Sujet principal:
Plantes
/
Bases de données factuelles
/
/
Biologie informatique
/
Apprentissage profond
Limites:
Animals
/
Humans
Langue:
En
Journal:
IEEE Trans Neural Netw Learn Syst
Année:
2020
Type de document:
Article