Banca de QUALIFICAÇÃO: ALESSANDRO SOARES DA SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : ALESSANDRO SOARES DA SILVA
DATE: 09/05/2025
TIME: 14:00
LOCAL: meet.google.com/qbp-egqx-ntg
TITLE:

Embedding and Transformer-based Approach for Genomic Surveillance of SARS-CoV-2

KEY WORDS:

SARS-CoV-2; Artificial Intelligence; Natural Language Processing; Deep Learning; Transformers; Embeddings; Genomic Surveillance; Viral Variants;

PAGES: 50
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUMMARY:

The rapid evolution of SARS-CoV-2 has accelerated the adoption of advanced artificial intelligence techniques to understand and monitor viral mutations. This work proposes a methodology based on Natural Language Processing (NLP) and deep learning to analyze amino acid substitutions found in virus variants, utilizing data from the GISAID database. The strategy employs embeddings generated by Transformer models to semantically represent genetic mutations, allowing the identification of relevant patterns and structural organization of samples in a latent space. Results demonstrate coherent clusters associated with specific viral variants, suggesting sensitivity of these representations to structural differences within the viral genome. Furthermore, the integration with epidemiological variables, such as continent of origin and patient age group, was explored to provide context to the identified clusters. The proposed approach shows potential to aid viral evolutionary tracking and to contribute to the development of computational tools applicable in genomic surveillance systems and personalized medicine.

COMMITTEE MEMBERS:
Presidente - 1837240 - MARCELO AUGUSTO COSTA FERNANDES
Interna - ***.350.054-** - LUCILEIDE MEDEIROS DANTAS DA SILVA - UFRN
Externo à Instituição - GABRIEL BEZERRA MOTTA CÂMARA - UFRN