High performance computing architectures analysis for gene networks inference
Resumen
Modeling and inference of biological systems are an important field in computer science, presenting strong interdisciplinary aspects. In this context, the inference of gene regulatory networks and the analysis of their dynamics generated by their transition functions are important issues that demand substantial computational power. Because the algorithms that return the optimal solution have an exponential time cost, such algorithms only work for gene networks with only dozens of genes. However realistic gene networks present hundreds to thousands of genes, with some genes being hubs, i.e., their number of predictor genes are usually much higher than average. Therefore there is a need to develop ways to speed up the gene networks inference. This paper presents a benchmark involving GPUs and FPGAs to infer gene networks, analysing processing time, hardware cost acquisition, energy consumption and programming complexity. Overall Titan XP GPU achieved the best performance, but with a large cost regarding acquisition price when compared to R9 Nano GPU and DE1-SOC FPGA. In its turn, R9 Nano GPU presented the best cost-benefit regarding performance, acquisition price, energy consumption, and programming complexity, although DE1-SOC FPGA presented much smaller energy consumption.
Citas
[Borelli et al. 2013] Borelli, F. F., de Camargo, R. Y., Martins-Jr, D. C., and Rozante, L. C. S. (2013). Gene regulatory networks inference using a multi-gpu exhaustive search algorithm. BMC Bioinformatics, 14(S5).
[Carastan-Santos et al. 2017] Carastan-Santos, D., Camargo, R. Y., Martins-Jr, D. C., Song, S. W., and Rozante, L. C. S. (2017). Finding exact hitting set solutions for systems biology applications using heterogeneous gpu clusters. Future Generation Computer Systems, 67:418–429.
[Chickering 1996] Chickering, D. M. (1996). Learning Bayesian Networks is NP-Complete, pages 121–130. Springer New York, New York, NY.
[Cook 2018] Cook, S. (2018). CUDA Programming.
[Dougherty et al. 2009] Dougherty, E. R., Brun, M., Trent, J., and Bittner, M. L. (2009) A conditioning-based model of contextual regulation. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 6(2):310–320.
[Friedman et al. 2000] Friedman, N., Linial, M., Nachman, I., and Pe’er, D. (2000). Using Bayesian Network to Analyze Expression Data. Journal of Computational Biology, 7:601–620.
[Kauffman 1969] Kauffman, S. A. (1969). Metabolic stability and epigenesis in randomly constructed genetic nets. Journal of Theoretical Biology, 22(3):437–467.
[Lopes et al. 2008] Lopes, F. M., Martins-Jr, D. C., and Cesar-Jr, R. M. (2008). Feature selection environment for genomic applications. BMC Bioinformatics, 9(1):451.
[Martins-Jr et al. 2008] Martins-Jr, D. C., Braga-Neto, U., Hashimoto, R. F., Dougherty, E. R., and Bittner, M. L. (2008). Intrinsically multivariate predictive genes. IEEE Journal of Selected Topics in Signal Processing, 2(3):424–439.
[Munshi et al. 2018] Munshi, A., Gaster, B., Mattson, T. G., Fung, J., and Ginsburg, D. (2018). OpenCL Programming Guide.
[Pournara et al. 2005] Pournara, I., s. Bouganis, C., and Constantinides, G. A. (2005). Fpgaaccelerated bayesian learning for reconstruction of gene regulatory networks. In International Conference on Field Programmable Logic and Applications, 2005., pages 323–328.
[Shmulevich et al. 2002] Shmulevich, I., Dougherty, E. R., Kim, S., and Zhang, W. (2002) Probabilistic boolean networks: a rule-based uncertainty model for gene regulatory networks. Bioinformatics, 18(2):261–274.
[Vanderbauwhede and Benkrid 2013] Vanderbauwhede, W. and Benkrid, K. (2013). HighPerformance Computing Using FPGAs. Springer Publishing Company, Incorporated.
