DNA Barcode Classification Using General Regression Neural Network with Different Distance Models

Massimo La Rosa (), Antonino Fiannaca (), Riccardo Rizzo () and Alfonso Urso ()
Additional contact information
Massimo La Rosa: ICAR-CNR
Antonino Fiannaca: ICAR-CNR
Riccardo Rizzo: ICAR-CNR
Alfonso Urso: ICAR-CNR

A chapter in Mathematical Models in Biology, 2015, pp 119-132 from Springer

Abstract: Abstract The “cythosome c oxidase subunits 1” (COI) gene is used for identification of species, and it is one of the so-called DNA barcode genes. Identification of species, even using DNA barcoding can be difficult if the biological examples are degraded. Spectral representation of sequences and the General Regression Neural Network (GRNN) can give some interesting results in these difficult cases. The GRNN is based on the distance between the memorized examples of sequence and the input unknown sequence, both represented using a vector space spectral representation. In this paper we will analyse the effectiveness of different distance models in the GRNN implementation and will compare the obtained results in the classification of full length sequences and degraded samples.

Keywords: Barcode classification; Alignment-free; GRNN (search for similar items in EconPapers)
Date: 2015
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-23497-7_9

Ordering information: This item can be ordered from
http://www.springer.com/9783319234977

DOI: 10.1007/978-3-319-23497-7_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().