Inferência de Redes de Regulação Gênica Usando Programação Genética Cartesiana Paralela

• Luciana N. S. Prachedes UFJF
• José Eduardo Henriques da Silva UFJF
• Heder Soares Bernardino UFJF
• Itamar Leite de Oliveira UFJF

DOI: https://doi.org/10.5753/sbcas_estendido.2022.222566

Abstract

The inference of gene regulatory networks (GRNs) is important in Systems Biology as it allows for the understanding of patterns of interactions between genes. These findings are useful in providing knowledge regarding diseases and helping to develop drugs. Evolutionary computation techniques, such as Cartesian Genetic Programming (CGP), have been used to infer GRNs with promising results. However, CGP has scalability issues. Here, GRNs are infered efficiently using high-performance computing approaches. Computational experiments show that the method developed in this scientific initiation program can infer GRNs faster than other ones from the literature with symbolic solutions. The gain in processing time of the presented parallel technique in relation to the sequential one is up to 104%.

References

da Silva, J. E. H. et al. (2020). Inferring gene regulatory network models from time-series data using metaheuristics. In 2020 IEEE (CEC), pages 1–8. IEEE.

Delahaye-Duriez, A. et al. (2016). Rare and common epilepsies converge on a shared gene regulatory network providing opportunities for novel antiepileptic drug discovery. Genome biology, 17(1):1–18.

Dumitrescu, D., Lazzerini, B., Jain, L. C., and Dumitrescu, A. (2000). Evolutionary computation. CRC press.

Emmert-Streib, F. et al. (2014a). The gene regulatory network for breast cancer: integrated regulatory landscape of cancer hallmarks. Frontiers in genetics, 5:15.

Emmert-Streib, F. et al. (2014b). Grns and their applications: understanding biological and medical problems in terms of networks. Front. in cell and devel. biology, 2:38.

Khan, M. M., Khan, G. M., and Miller, J. F. (2010). Evolution of neural networks using cartesian genetic programming. In Cong. on Evol. Comput. (CEC), pages 1–8. IEEE.

Koza, J. R. (1992). Genetic programming: on the programming of computers by means of natural selection. Complex adaptive systems. MIT Press.

Ma, B. et al. (2019). Identification of gene regulatory networks by integrating genetic programming with particle filtering. IEEE Access, 7:113760–113770.

McCall, M. N. (2013). Estimation of gene regulatory networks. Postdoc journal: a journal of postdoctoral research and postdoctoral affairs, 1(1):60.

Medeiros, F. et al. (2019). Gene regulatory network inference and analysis of multidrugresistant pseudomonas aeruginosa. Memórias do Instituto Oswaldo Cruz, 114.

Miller, J. F. (2011). Cartesian genetic programming. In Cartesian Genetic Programming, pages 17–34. Springer.

Miller, J. F. et al. (1999). An empirical study of the efficiency of learning boolean functions using a cartesian genetic programming approach. In Proceedings of the genetic and evolutionary computation conference, volume 2, pages 1135–1142.

Noman, N. and Iba, H. (2007). Inferring grns using differential evolution with local search heuristics. IEEE/ACM Trans. on comp. biology and bioinfo., 4(4):634–647.

Palafox, L., Noman, N., and Iba, H. (2013). Reverse engineering of grns using dissipative particle swarm optimization. IEEE Trans. on Evolutionary Comp., 17(4):577–587.

Pratapa, A. et al. (2020). Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data. Nature methods, 17(2):147–154.

Qian, L., Wang, H., and Dougherty, E. R. (2008). Inference of noisy nonlinear differential equation models for gene regulatory networks using genetic programming and kalman filtering. IEEE Transactions on Signal Processing, 56(7):3327–3339.

Silva, B. M., Bernardino, H. S., and Barbosa, H. J. (2021). Human activity recognition using parallel cartesian genetic programming. In CEC, pages 474–481. IEEE.

Streichert, F., Planatscher, H., Spieth, C., Ulmer, H., and Zell, A. (2004). Comparing genetic programming and evolution strategies on inferring gene regulatory networks. In Genetic and Evolutionary Computation Conference, pages 471–480. Springer.

Van Der Wijst, M. G., de Vries, D. H., Brugge, H., Westra, H.-J., and Franke, L. (2018). An integrative approach for building personalized gene regulatory networks for precision medicine. Genome medicine, 10(1):1–15.