1. Proceedings
  2. I3M
  3. 2019
  4. EMSS
  5. 10.46354/i3m.2019.emss.001

Representation of a convolutional neuronal network as a high level parallel composition applied to the recognition of DNA sequences

  • a M. Rossainz-López  ,
  • b S. Zúñiga-Herrera  ,
  • c M. Capel-Tuñón  ,
  • d I. Pineda-Torres  
  • a,b,d Faculty of Computer Science, Autonomous University of Puebla, San Claudio Avenue and South 14th Street, San Manuel, Puebla, Puebla, 72000, México
  • c Software Engineering Department, College of Informatics and Telecommunications ETSIIT, University of Granada, Daniel Saucedo Aranda s/n, Granada 18071, Spain
Cite as
Rossainz-López M., Zúñiga-Herrera S., Capel-Tuñón M., Pineda-Torres I. (2019). Representation of a Convolutional Neuronal Network as a High Level Parallel Composition Applied to the Recognition of DNA Sequences. Proceedings of the 31st European Modeling & Simulation Symposium (EMSS 2019), pp. 1-8. DOI: 10.46354/i3m.2019.emss.001.

Abstract

This work proposes the use of Structured Parallel Programming using the process communication pattern called Pipeline in its version of High-Level Parallel Composition (HLPC) to implement a process composition that represents a convolutional neuronal network or CNN and that is used to solve a specific problem of DNA sequences. The HLPC Pipeline-CNN is then shown, which represents the implementation of a convolutional neural network making use of the three types of parallel objects that make up an HLPC: A manager object, one or more stage objects and a collector object. The manager object represents the HLPC itself and makes an encapsulated abstraction out of it that hides the internal structure, the stage objects are objects of a specific purpose, in charge of encapsulating an client-server type interface that settles down between the manager and the slave-objects and the collector object that is an object in charge of storing the results received from the stage objects to which is connected. To show the usefulness and performance of the HLPC Pipeline-CNN implemented, it was used in the recognition of DNA sequences from a database with 4 types of hepatitis C virus (type 1, 2, 3 and 6). The results of this classification were obtained in terms of percentages of training precision and validation precision, as well as performance results in terms of speedup from 1000 to 4000 training steps with 2, 4, 8, 16 and 32 exclusive processors in one parallel machine of up to 64 processors with shared-distributed memory.

References

  1. Andrews G.R., 2000. Foundations of Multithreaded, Parallel, and Distributed Programming, Addison-Wesley.
  2. Bacci, Danelutto, Pelagatti, Vaneschi, 1999. SklE: A Heterogeneous Environment for HPC Applications. Parallel Computing 25.
  3. Birrell A., 1989. An Introduction to Programming with Threads, Digital Equipment Corporation, Systems Research Center, Palo Alto California, USA.
  4. Brinch Hansen, 1993. Model Programs for Computational Science: A programming methodology for multicomputers, Concurrency: Practice and Experience, Volume 5, Number 5.
  5. Calvo D. (2015). Red Neuronal Convolucional (CNN). Data Scientist. http://www.diegocalvo.es/redneuronal-convolucional/
  6. Corradi A., Leonardi L., 1991. PO Constraints as tools to synchronize active objects. Journal Object Oriented Programming 10, pp. 42-53.
  7. Corradi A, Leonardo L, Zambonelli F., 1995. Experiences toward an Object-Oriented Approach to Structured Parallel Programming. DEIS technical report no. DEIS-LIA-95-007.
  8. Christos Ouzounis 2012. Rise and demise of bioinformatics? promise and progress. PLoS computational biology, 8(4):e1002487.
  9. Danelutto M. and Torquati M, 2014. Loop parallelism: a new skeleton perspective on data parallel patterns, in Proc. of Intl. Euromicro PDP: Parallel Distributed and Network-based Processing, Torino, Italy.
  10. Darlington et al., 1993, Parallel Programming Using Skeleton Functions. Proceedings PARLE’93, Munich (D).
  11. Genís P, Blanco P. and Guigó R., (2000). Geneid in drosophila. Genome research, 10(4):511–515.
  12. Lavander G.R., Kafura D.G. 1995. A Polimorphic Future and First-class Function Type for Concurrent Object-Oriented Programming. Journal of Object-Oriented Systems.
  13. Liwu Li, 2002. Java Data Structures and Programming. Springer Verlag. Germany. ISBN: 3-540-63763X.
  14. Marcelo A., Apolloni J., Kavka C., et-al. 2000. Entrenamiento de Redes Neuronales. Universidad Nacional de San Luís. WICC 2000. Argentina.
  15. Marturet R., Alferez E.S., 2018. Evaluación de Redes Neuronales Convulcionales para la clasificación de imágenes histológicas de cancer colorrectar mediante transferencia de aprendizaje. Master en Bioinformática y Bioestadística. Universitat Oberta de Catalunya. España.
  16. Mathworks. 2018. Deep learning. https://la.mathworks.com/solutions/deeplearning/convolutional-neural-network.html
  17. Noordewier M, Towell G, and Shavlik Jude, (1991). Training knowledge-based neural networks to recognize genes in DNA sequences. In Advances in neural information processing systems, pages 530–536.
  18. Panduro A, 2009. Biología molecular en la clínica. McGraw-Hill Interamericana.
  19. Roosta, Séller, 1999. Parallel Processing and Parallel Algorithms. Theory and Computation. Springer.
  20. Rossainz, M., 2005. Una Metodología de Programación Basada en Composiciones Paralelas de Alto Nivel (HLPCs). Universidad de Granada, PhD dissertation, 02/25/2005.
  21. Rossainz, M., Capel M., 2008. A Parallel Programming Methodology using Communication Patterns named CPANS or Composition of Parallel Object. 20TH European Modeling & Simulation Symposium.Campora S. Giovanni. Italy.
  22. Rossainz M., Capel M., 2014. Approach class library of high level parallel compositions to implements communication patterns using structured parallel programming. 26TH European Modeling & Simulation Symposium. Campora Bordeaux, France.
  23. Salzberg SL, Searls DB, and Kasif S., 1998. Computational gene prediction using neural networks and similarity search. Computational Methods in Molecular Biology, pp.32-109. Vizcaya R., (2018). Deep Learning para la detección de peatones y vehículos sobre FPGA. Disertación de Master. Universidad Autónoma del Estado de México.
  24. Wilkinson B., Allen M., 1999. Parallel Programming Techniques and Applications Using Networked Workstations and Parallel Computers. Prentice-Hall. USA.