O impacto da inteligência artificial nas ciências da vida através da bioinformática

Autores

DOI:

https://doi.org/10.35699/2965-6931.2023.47996

Palavras-chave:

bioinformática, inteligência artificial, aprendizagem de máquina

Resumo

Nos últimos anos, as técnicas de inteligência artificial (IA) têm revolucionado a pesquisa nas ciências da vida. Isto tornou-se possível graças ao surgimento de novos métodos e tecnologias que permitiram a geração de dados biológicos de alta qualidade e em larga escala. Aliado a isso, as técnicas de bioinformática têm permitido a modelagem e a resolução de problemas biológicos de forma que as aplicações de modelos de aprendizagem de máquina têm levantado novas perspectivas. Neste artigo, abordaremos os impactos da IA nas ciências da vida, com particular ênfase naqueles mediados pela bioinformática, dos avanços nos modelos e algoritmos de IA e das consequências para a pesquisas nas ciências da vida.

Biografia do Autor

  • Lucas Moraes dos Santos, Universidade Federal de Minas Gerais (UFMG)

    Possui mestrado em Bioinformática pela Universidade Federal de Minas Gerais (2022) e graduação em Engenharia de Computação pela Universidade de Caxias do Sul (2019). Seus principais interesses de pesquisa estão relacionados à Inteligência Artificial e Biologia Estrutural. Atualmente, é doutorando do Programa de Pós-Graduação em Bioinformática da UFMG.

  • Diego Mariano, Universidade Federal de Minas Gerais (UFMG)

    Residente pós-doutoral no Laboratório de Bioinformática e Sistemas da UFMG. Editor-in-chief na Revista BIOINFO e Guest Associate Editor na Frontiers in Bioinformatics. Vice coordenador da rede bioinfo.com. Revisor em diversos periódicos internacionais, como PlosOne, Molecules, Oxford Bioinformatics, dentre outros. Mestre e doutor pelo Programa de Pós-graduação em Bioinformática da UFMG. Vencedor do prêmio UFMG de teses e do Prêmio Nacional de Teses da AB3C em 2020. Tem experiência no desenvolvimento de aplicações web, visualização de dados e manipulação de bases de dados biológicas.

  • Raquel Cardoso de Melo-Minardi, Universidade Federal de Minas Gerais (UFMG)

    possui doutorado em Bioinformática pela Universidade Federal de Minas Gerais (2008) e graduação em Ciência da Computação pela mesma instituição (2004). Realizou seu pós-doutorado no Comissariat à l'Energie Atomique et aux Énergies Alternatives / CEA na França (2008/2009). Atualmente é Professora Classe D Nível 03 (antigo Associado 3) da Universidade Federal de Minas Gerais no Departamento de Ciência da Computação. É membro afiliado da Academia Brasileira de Ciências (2019-2023). Atua como docente permanente no Programa de Pós-Graduação em Ciência da Computação (cenceito 7 da CAPES) e no Programa de Pós-Graduação em Bioinformática (conceito 7 da CAPES). É sub-coordenadora do Programa de Pós-Graduação em Bioinformática da UFMG (gestão 2020-2021 e 2022-2024), secretária da regional Centro-Sudeste da Associação Brasileira de Biologia Computacional e Bioinformática (AB3C), coordenadora do Comitê Especial de Biologia Computacional (CE-BioComp) da Sociedade Brasileira de Computação (SBC) (2022) e vice-coordenadora do mesmo comitê em 2022. Seus principais interesses de pesquisa são Bioinformática e Biologia Computacional, Inteligência Artificial e Visualização de Dados.

Referências

ABBASI, Maryam et al. Designing optimized drug candidates with Generative Adversarial Network. Journal of Cheminformatics, 14, n. 1, 2022. 40. DOI: https://doi.org/10.1186/s13321-022-00623-6

ALQURAISHI, Mohammed. AlphaFold at CASP13. Bioinformatics, 35, n. 22, 2019. 4862-4865. DOI: https://doi.org/10.1093/bioinformatics/btz422

ANAND, Namrata; HUANG, Po-Ssu. Generative modeling for protein structures. Proceedings of the 32nd International Conference on Neural Information Processing Systems, 31, 2018. 7505-7516.

ANISHCHENKO, Ivan. et al. De novo protein design by deep network hallucination. Nature, 600, n. 7889, 2021. 547-552. DOI: https://doi.org/10.1038/s41586-021-04184-w

ANSTINE, Dylan M.; ISAYEV, Olexandr. Generative Models as an Emerging Paradigm in the Chemical Sciences. Journal of the American Chemical Society, 145, n. 16, 2023. 8736-8750. DOI: https://doi.org/10.1021/jacs.2c13467

BAI, Qifeng et al. Application advances of deep learning methods for de novo drug design and molecular dynamics simulation. WIREs Computational Molecular Science, 12, n. 3, 2021. e1581. DOI: https://doi.org/10.1002/wcms.1581

BENGIO, Yoshua; COURVILLE, Aaron; VINCENT, Pascal. Representation Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, n. 8, 2013. 1798-1828. DOI: https://doi.org/10.1109/TPAMI.2013.50

BIAN, Yuemin; XIE, Xiang-Qun. Generative chemistry: drug discovery with deep learning generative models. Journal of Molecular Modeling, 27, n. 3, 2021. 71-89. DOI: https://doi.org/10.1007/s00894-021-04674-8

BILODEAU, Camille et al. Generative models for molecular discovery: Recent advances and challenges. WIREs Computational Molecular Science, 12, n. 5, 2022. DOI: https://doi.org/10.1002/wcms.1608

BRANDES, Nadav et al. ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics, 38, n. 8, 2022. 2102-2110. DOI: https://doi.org/10.1093/bioinformatics/btac020

BRANDES, Nadav et al. Genome-wide prediction of disease variant effects with a deep protein language model. Nature Genetics, 2023. DOI: https://doi.org/10.1101/2022.08.25.505311

CALLAWAY, Ewen. AI tools are designing entirely new proteins that could transform medicine. Nature, 619, n. 7969, 2023. 236-238. DOI: https://doi.org/10.1038/d41586-023-02227-y

CHEN, Ziqi et al. Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Models. Preprint, 2023. Disponível em: <https://arxiv.org/abs/2308.11890>. Acesso em: 5 Setembro 2023.

CHENTHAMARAKSHAN, Vijil et al. Accelerating drug target inhibitor discovery with a deep generative foundation model. Science Advances, 9, n. 25, 2023. DOI: https://doi.org/10.1126/sciadv.adg7865

DEFRESNE, Marianne; BARBE, Sophie; SCHIEX, Thomas. Protein Design with Deep Learning. International Journal of Molecular Sciences, 22, n. 21, 2021. 11741. DOI: https://doi.org/10.3390/ijms222111741

DILL, Ken A.; MACCALLUM, Justin L. The Protein-Folding Problem, 50 Years On. Science, 338, n. 6110, 2012. 1042-1046. DOI: https://doi.org/10.1126/science.1219021

DING, Wenze; GONG, Haipeng. Predicting the Real-Valued Inter-Residue Distances for Proteins. Advanced Science, 7, n. 19, 2020. 2001314. DOI: https://doi.org/10.1002/advs.202001314

DU, Zongyang et al. The trRosetta server for fast and accurate protein structure prediction. Nature Protocols, 16, n. 12, 2021. 5634-5651. DOI: https://doi.org/10.1038/s41596-021-00628-9

DUDA, Richard O.; HART, Peter E.; STORK, David G. Pattern Classification. 2ª. ed.

FERRUZ, Noelia; SCHMIDT, Steffen; HÖCKER, Birte. ProtGPT2 is a deep unsupervised language. Nature Communications, 13, n. 1, 2022. 4348. DOI: https://doi.org/10.1038/s41467-022-32007-7

GAO, Wenhao et al. Deep Learning in Protein Structural Modeling and Design. Patterns, 1, n. 9, 2020. 100142. DOI: https://doi.org/10.1016/j.patter.2020.100142

GONZALEZ, Rafael C.; WOODS, Richard E. Digital Image Processing. 4ª. ed.

GOODFELLOW, Ian J. et al. Generative Adversarial Networks. Advances in Neural Information Processing System, 2014. 2672-2680.

GOODFELLOW, Ian; BENGIO, Yoshua; COURVILLE, Aaron. Deep Learning.

HAN, Minwoo et al. Recognition of the ligand-induced spatiotemporal residue pair pattern of β2-adrenergic receptors using 3-D residual networks trained by the time series of protein distance maps. Computational and Structural Biotechnology Journal, 20, 2022. 6360-6374. DOI: https://doi.org/10.1016/j.csbj.2022.10.036

HAYKIN, Simon. Neural Networks: A Comprehensive Foundation. 2ª. ed.

HOLT, Charles A.; ROTH, Alvin E. The Nash equilibrium: A perspective. Proceedings of the National Academy of Sciences, 101, n. 12, 2004. 3999-4002. DOI: https://doi.org/10.1073/pnas.0308738101

HOPFIELD, J. J. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79, n. 8, 1982. 2554-2558. DOI: https://doi.org/10.1073/pnas.79.8.2554

HUANG, Po-Ssu; BOYKEN, Scott E.; BAKER, David. The coming of age of de novo protein design. Nature, 537, n. 7620, 2016. 320-327. DOI: https://doi.org/10.1038/nature19946

JUMPER, John et al. Highly accurate protein structure prediction with AlphaFold. Nature, 596, n. 7873, 2021. 583-589. DOI: https://doi.org/10.1038/s41586-021-03819-2

KINGMA, Diederik P.; WELLING, Max. Auto-Encoding Variational Bayes, 2013.

LECUN, Yan et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1, n. 4, 1989. 541-551. DOI: https://doi.org/10.1162/neco.1989.1.4.541

LI, Chuan et al. An Interpretable Convolutional Neural Network Framework for Analyzing Molecular Dynamics Trajectories: a Case Study on Functional States for G-Protein-Coupled Receptors. Journal of Chemical Information and Modeling, 62, n. 6, 2022. 1399-1410. DOI: https://doi.org/10.1021/acs.jcim.2c00085

LI, Xuanyi et al. Chemical space exploration based on recurrent neural networks: applications in discovering kinase inhibitors. Journal of Cheminformatics, 12, n. 1, 2020. 42. DOI: https://doi.org/10.1186/s13321-020-00446-3

LI, Yuesen et al. DrugGPT: A GPT-based Strategy for Designing Potential Ligands Targeting Specific Proteins. Preprint, 2023. Disponível em: <https://doi.org/10.1101/2023.06.29.543848>. Acesso em: 5 Setembro 2023. DOI: https://doi.org/10.1101/2023.06.29.543848

LI, Zhaoyu et al. Protein Loop Modeling Using Deep Generative Adversarial Network. IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), 2017. 1085-1091. DOI: https://doi.org/10.1109/ICTAI.2017.00166

LIN, Zeming et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science, 379, n. 6637, 2023. 1123-1130. DOI: https://doi.org/10.1126/science.ade2574

MAO, Jiashun et al. Application of a deep generative model produces novel and diverse functional peptides against microbial resistance. Computational and Structural Biotechnology Journal, 21, 2023. 463-471. DOI: https://doi.org/10.1016/j.csbj.2022.12.029

MARIANO, Diego et al. A Brief History of Bioinformatics Told by Data Visualization. Advances in Bioinformatics and Computational Biology. BSB 2020. Lecture Notes in Computer Science. Belo Horizonte: Springer, Cham. 2020. p. 235-246. DOI: https://doi.org/10.1007/978-3-030-65775-8_22

METHOD of the Year 2021: Protein structure prediction. Nature Methods, 19, n. 1, 2022. DOI: https://doi.org/10.1038/s41592-021-01380-4

MIN, Seonwoo; LEE, Byunghan; YOON, Sungroh. Deep learning in bioinformatics. Briefings in Bioinformatics, 18, n. 5, 2017. 851–869.

MISHRA, Sarbani et al. Introduction to the World of Bioinformatics. A Guide to Applied Machine Learning for Biologists, 2023. 105-126. DOI: https://doi.org/10.1007/978-3-031-22206-1_4

MITCHELL, Tom M. Machine learning.

MOLNAR, Christoph. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. 2ª. ed.

NASH, John F. Equilibrium points in n-person games. Proceedings of the National Academy of Sciences, 36, n. 1, 1950. 48-49. DOI: https://doi.org/10.1073/pnas.36.1.48

PLANTE, Ambrose et al. A Machine Learning Approach for the Discovery of Ligand-Specific Functional Mechanisms of GPCRs. Molecules, 24, n. 11, 2019. 2097. DOI: https://doi.org/10.3390/molecules24112097

PRAVALPHRUEKUL, Nutaya et al. De Novo Design of Molecules with Multiaction Potential from Differential Gene Expression using Variational Autoencoder. Journal of Chemical Information and Modeling, 63, n. 13, 2023. 3999-4011. DOI: https://doi.org/10.1021/acs.jcim.3c00355

RAO, Roshan. et al. Transformer protein language models are unsupervised structure learners. International Conference on Learning Representations, 2020. DOI: https://doi.org/10.1101/2020.12.15.422761

RIVES, Alexander. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. PNAS, 118, n. 15, 2019. DOI: https://doi.org/10.1073/pnas.2016239118

ROSSETTO, Allison; ZHOU, Wenjin. GANDALF: Peptide Generation for Drug Design Using Sequential and Structural Generative Adversarial Networks. Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2020. DOI: https://doi.org/10.1145/3388440.3412487

RUMELHART, David E.; HINTON, Geoffrey E.; WILLIAMS, Ronald J. Learning representations by back-propagating errors. Nature, 323, n. 6088, 1986. 533-536. DOI: https://doi.org/10.1038/323533a0

SANCHEZ-LENGELING, Benjamin; ASPURU-GUZIK, Alán. Inverse molecular design using machine learning: Generative models for matter engineering. Science, 361, n. 6400, 2018. 360-365. DOI: https://doi.org/10.1126/science.aat2663

SANTOS, Lucas M. D. et al. Peptide-Protein Interface Classification Using Convolutional Neural Networks. Advances in Bioinformatics and Computational Biology. BSB 2023. Lecture Notes in Computer Science. Curitiba: Springer, Cham. 2023. p. 112-122. DOI: https://doi.org/10.1007/978-3-031-42715-2_11

SANTOS, Lucas M. D.; MELO-MINARDI, Raquel C. D. Identifying Large Scale Conformational Changes in Proteins Through Distance Maps and Convolutional Networks. Advances in Bioinformatics and Computational Biology. BSB 2022. Lecture Notes in Computer Science. Búzios: Springer, Cham. 2022. p. 56-67. DOI: https://doi.org/10.1007/978-3-031-21175-1_7

SENIOR, Andrew W. et al. Improved protein structure prediction using potentials from deep learning. Nature, 577, n. 7792, 2020. 706–710. DOI: https://doi.org/10.1038/s41586-019-1923-7

SOHL-DICKSTEIN, Jascha et al. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille: [s.n.]. 2015. p. 2256–2265.

SOUSA, Tiago et al. Generative Deep Learning for Targeted Compound Design. Journal of Chemical Information and Modeling, 61, n. 11, 2021. 5343-5361. DOI: https://doi.org/10.1021/acs.jcim.0c01496

SURANA, Shraddha. et al. PandoraGAN: Generating antiviral peptides. SN COMPUT. SCI., 4, n. 607, 2023. DOI: https://doi.org/10.1007/s42979-023-02203-3

THOMAS, Morgan; BENDER, Andreas; GRAAF, Chris D. Integrating structure-based approaches in generative molecular design. Current Opinion in Structural Biology, 79, 2023. 102559. DOI: https://doi.org/10.1016/j.sbi.2023.102559

TONG, Xiaochu et al. Generative Models for De Novo Drug Design. Journal of Medicinal Chemistry, 64, n. 19, 2021. 14011-14027. DOI: https://doi.org/10.1021/acs.jmedchem.1c00927

TORRISI, Mirko; POLLASTRI, Gianluca; LE, Quan. Deep learning methods in protein structure prediction. Computational and Structural Biotechnology Journal, 18, 2020. 1301-1310. DOI: https://doi.org/10.1016/j.csbj.2019.12.011

VASWANI, Ashish et al. Attention is All you Need. Advances in Neural Information Processing Systems, 30, 2017. 6000–6010.

VERLI, Hugo. Bioinformática: da biologia à flexibilidade molecular.

VERT, Jean-Philippe. How will generative AI disrupt data science in

drug discovery?. Nature Biotechnology, 41, n. 6, 2023. 750-751. DOI: https://doi.org/10.1038/s41587-023-01789-6

WATSON, Joseph L. et al. De novo design of protein structure and function with RFdiffusion. Nature, 620, n. 7976, 2023. 1089-1100. DOI: https://doi.org/10.1038/s41586-023-06415-8

XIE, Xuezhi; VALIENTE, Pedro A.; KIM, Philip M. HelixGAN a deep-learning methodology for conditional de novo design of α-helix structures. Bioinformatics, 39, n. 1, 2023. DOI: https://doi.org/10.1093/bioinformatics/btad036

ZENG, Xiangxiang et al. Deep generative molecular design reshapes drug discovery. Cell Reports Medicine, 3, n. 12, 2022. 100794. DOI: https://doi.org/10.1016/j.xcrm.2022.100794

ZHANG, Shuang et al. Applications of transformer-based language models in bioinformatics: a survey. Bioinformatics Advances, 3, n. 1, 2023. DOI: https://doi.org/10.1093/bioadv/vbad001

Revista da UFMG escrito na cor preto e fluxo contínuo de publicações na cor azul.

Downloads

Publicado

2023-12-07

Edição

v. 30 (2023): Inteligência e Inteligência Artificial

Seção

Artigos

Categorias

Licença

Copyright (c) 2023 Lucas Moraes dos Santos, Diego Mariano, Raquel Cardoso de Melo-Minardi

Creative Commons License
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.

Como Citar

O impacto da inteligência artificial nas ciências da vida através da bioinformática . Revista da Universidade Federal de Minas Gerais, Belo Horizonte, v. 30, n. fluxo contínuo, 2023. DOI: 10.35699/2965-6931.2023.47996. Disponível em: https://periodicos.ufmg.br/index.php/revistadaufmg/article/view/47996. Acesso em: 4 nov. 2026.