INTELIGÊNCIA ARTIFICIAL E BIOINFORMÁTICA APLICADA À PESQUISA CIENTÍFICA: UMA REVISÃO SOBRE A DESCOBERTA DE NOVOS FÁRMACOS
INTELIGÊNCIA ARTIFICIAL E BIOINFORMÁTICA APLICADA À PESQUISA CIENTÍFICA: UMA REVISÃO SOBRE A DESCOBERTA DE NOVOS FÁRMACOS
-
DOI: https://doi.org/10.22533/at.ed.1661125170313
-
Palavras-chave: Machine learning; Deep learning; Bioinformática; Inteligência artificial; Pesquisa científica.
-
Keywords: Machine learning; Deep learning; Bioinformatic; Artificial intelligence; Scientific research.
-
Abstract: The discovery of new drugs is a complex, time-consuming, and high-cost process, often exceeding a decade of research and billions in investment. In this context, Artificial Intelligence (AI) and Bioinformatics are being incorporated as key technologies to optimize the early stages of bioactive compound prospecting and screening. This chapter presents a narrative review of the scientific literature published between 2015 and 2025, aiming to identify the main advances, challenges, and applications of these tools in drug discovery. The literature search was conducted in the PubMed, Web of Science, and Google Scholar databases using the descriptors "Artificial Intelligence", "Drug Discovery", and "Bioinformatics". After applying eligibility criteria, eight peer-reviewed articles were selected. The results show that approaches based on machine learning (ML), deep learning (DL), convolutional neural networks (CNN), graph neural networks (GNN), molecular docking, and generative models (GANs) have been successfully used for predicting biological activity, identifying molecular targets, reducing false positives, and generating novel compounds with desired properties. The analyzed tools demonstrate improvements in precision and speed of virtual screening, especially when integrated with large structural databases. Despite the advances, limitations remain regarding the need for experimental validation in vitro and in vivo, as well as the lack of methodological standardization and high- quality data. It is concluded that AI and bioinformatics represent a promising technological convergence, but still require technical and regulatory maturation for full integration into translational research.
- Pâmela Gomes Santos
- Vanessa da Silva Lima
- Gabriela Cristina Baccaro
- Isadora Mara Cunha Bezerra
- Lailda Brito Soares
- Marcela Bacchetti Vicentini
- Ayron Abraão César Xavier
- Brunela Pimentel de Oliveira
- Celine Mano Andrade
- Isadora Nascimento
- Raquel Paes dos Santos
- Paloma Gomes Santos