Towards BacterioPhage genetic edition : deep learning prediction of phage-bacterium interactions

Ataee, Shabnam (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland) ; Rodriguez, Oscar (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland) ; Brochet, Xavier (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland) ; Pena, Carlos Andrés (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland)

In this paper, a novel approach is proposed for genetically engineering bacteriophages. It is formed of two main modules: a predictor and a genome sequence generator. Convolutional Neural Networks are used to build the predictor while the generator is constructed based on Deep Generative Models. This paper concentrates in the architecture and the results for the predictor module. The evaluation results suggest that the proposed model has the potential to be further used to guide genetic edition of phages so as to improve phage therapy against bacterial infections.


Keywords:
Conference Type:
short paper
Faculty:
Ingénierie et Architecture
School:
HEIG-VD
Institute:
IICT - Institut des Technologies de l'Information et de la Communication
Publisher:
Seoul, South Korea, 16-19 December 2020
Date:
2020-12
Seoul, South Korea
16-19 December 2020
Pagination:
3 p.
Published in:
Proceedings of 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 16-19 December 2020, Seoul, South Korea
DOI:
ISBN:
978-1-7281-6215-7
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2021-02-23, last modified 2021-02-25

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)