Banca de QUALIFICAÇÃO: KAROLAYNE SANTOS DE AZEVEDO

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : KAROLAYNE SANTOS DE AZEVEDO
DATE: 17/12/2021
TIME: 16:30
LOCAL: meet.google.com/cnd-rthb-usi
TITLE:

Deep Learning Applied to Classification and behavior analysis SARS-CoV-2 virus

KEY WORDS:

SARS-CoV-2, Viral Classification, Deep Learning, Worry Variants, Convolutional Neural Network.

PAGES: 45
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUMMARY:

The new Beta Coronavirus, officially named SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus - 2 - SARS-CoV-2) is the virus causing COVID-19 disease. A member of the Coronaviridae family of viruses, SARS-CoV-2 is a positive-sense, single-stranded RNA enveloped virus that contains nearly 30,000 base-pair pairs - bp).RNA viruses tend to undergo more modifications than DNA viruses. Thus, when a virus is circulating widely in a population and causing many infections, the probability of its genome undergoing modifications increases, which may negatively affect some of its properties, becoming more transmissible and/or even more lethal. Within this context, this work proposes a tool, based on machine learning, which makes use of a deep one-dimensional (1D) convolutional neural network (CNN), intended for the classification and comparison of viral genomes of the new SARS-CoV - 2. As input, complete genomic cDNA samples (complementary DNA) were used, whose size varies between 26342 and 31029 base pairs (base-pair - bp) in length. Contrary to most approaches presented in the literature, the results obtained by this tool involving the classification of viruses, from the same family, reveal high values for the performance metrics, proving to be more reliable when compared to the works discussed in the state of the art. The proposed model was also used to verify possible changes in the genomic sequences of the main concern variants (alpha, beta, gamma), over a period of time, through their accuracy values, obtained through the classification between the variants.For this experiment, genomic samples from GISAID (Global Initiative on Sharing All Influenza Data - GISAID) were used, which also hosts epidemiological and clinical data referring to all variants related to SARS-CoV-2. The results obtained in this experiment indicate that the model can be used not only for classifying the virus of the Coronaviridae family, but also for predicting the behavior of SARS-CoV-2 variants over time.

BANKING MEMBERS:
Presidente - 1837240 - MARCELO AUGUSTO COSTA FERNANDES
Interno - 1153006 - LUIZ AFFONSO HENDERSON GUEDES DE OLIVEIRA
Externo ao Programa - 2170415 - JORGE ESTEFANO SANTANA DE SOUZA