Banca de QUALIFICAÇÃO: GABRIEL BEZERRA MOTTA CÂMARA

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : GABRIEL BEZERRA MOTTA CÂMARA
DATE: 25/02/2022
TIME: 10:00
LOCAL: meet.google.com/usy-ucui-gys
TITLE:

Convolutional Neural Network applied to SARS-CoV-2 sequence classification

KEY WORDS:

SARS-CoV-2, COVID-19, Deep Learning, CNN

PAGES: 24
BIG AREA: Ciências Biológicas
AREA: Genética
SUMMARY:

COVID-19, the illness caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, that belongs to the Coronaviridade family, a single-strand positive-sense RNA genome, has been spreading around the world and has been declared a pandemic by the World Health Organization. On January 17, 2022, there were more than 329 million cases, with more than 5.5 million deaths. Although COVID-19 has a low mortality rate, its high capacity for contamination, spread, and mutation, worries the authorities, especially after the emergence of the omicron variant, which has a high transmission capacity and can more easily contaminate even vaccinated people. Such outbreaks require the elucidation of the taxonomic classification and the origin of the virus (SARS-CoV-2) from the genomic sequence for strategic planning, containment, and treatment of the disease. Thus, this work proposes a high accuracy technique to classify viruses and other organisms from genome sequence using a deep learning Convolutional Neural Network (CNN). Unlike other literature, the proposed approach does not limit the genome sequence length. Results show that the novel proposal accurately distinguishes the SARS-CoV-2 of the other viruses sequence. The results were obtained with 1557 instances of SARS-CoV-2 from the National Center for Biotechnology Information (NCBI) and 14684 different viruses from the Virus-Host DB. As CNN has several changeable parameters, tests were performed with forty-eight different architectures, with the best of them having an accuracy of 91.94±2.62% in classifying viruses into their realms correctly, in addition to 100% in classifying SARS-CoV-2 into their respective realm, Riboviria. For the subsequent classifications (Family, genera, and subgenus), this accuracy increased, showing that the proposed architecture may be viable in the classification of the virus that causes COVID-19.

BANKING MEMBERS:
Interno - 347628 - ADRIAO DUARTE DORIA NETO
Interno - 1837240 - MARCELO AUGUSTO COSTA FERNANDES
Externo ao Programa - 2885532 - IVANOVITCH MEDEIROS DANTAS DA SILVA