ABSTRACT
We genetically improve BarraCUDA using a BNF grammar incorporating C scoping rules with GP. Barracuda maps next generation DNA sequences to the human genome using the Burrows-Wheeler algorithm (BWA) on nVidia Tesla parallel graphics hardware (GPUs). GI using phenotypic tabu search with manually grown code can graft new features giving more than 100 fold speed up on a performance critical kernel without loss of accuracy.
- Durbin, R. M., et al. A map of human genome variation from population-scale sequencing. Nature 467Google Scholar
- Harding, S. L., et al. Distributed GP on GPUs using CUDA. In Par. Arch. & Bioinspired Alg., 2009.Google Scholar
- Harman, M., Jia, Y., and Langdon, W. B. Babel pidgin: SBSE can grow and graft entirely new functionality into a real world system. In SSBSE 2014, LNCS 8636, pp. 247--252.Google ScholarCross Ref
- Harris, C. An investigation into the Application of Genetic Programming techniques to Signal Analysis and Feature Detection. PhD thesis, UCL, 1997.Google Scholar
- Initial sequencing and analysis of the human genome. Nature 409, 6822, (15 Feb 2001), 860--921.Google Scholar
- Klus, P., et al. BarraCUDA. BMC Res. Notes 5, 27Google Scholar
- Koza, J. R. Genetic Programming. MIT press, 1992. Google ScholarDigital Library
- Langdon, W. B. Genetically improved software. In Handbook of Genetic Programming Applications, A. H. Gandomi et al., Eds. Springer.Google Scholar
- Langdon, W. B. Mycoplasma contamination in the 1000 genomes project. BioData Mining 7, 3 (2014).Google ScholarCross Ref
- Langdon, W. B., and Harman, M. Evolving a CUDA kernel from an nVidia template. In WCCI 2010Google Scholar
- Langdon, W. B., and Harman, M. Genetically improved CUDA C++ software. In EuroGP 2014.Google ScholarDigital Library
- Langdon, W. B., and Harman, M. Optimising existing software with genetic programming. IEEE Trans. on Evo. Comp. 19, 1 (2015), 118--135.Google ScholarDigital Library
- Langdon, W. B., et al. Improving 3D medical image registration CUDA software with genetic programming. In GECCO 2014, ACM, pp. 951--958. Google ScholarDigital Library
- Langdon, W. B., and Nordin, J. P. Seeding GP populations. In EuroGP'2000 pp. 304--315. Google ScholarDigital Library
- Langdon, W. B., and Poli, R. Fitness causes bloat: Mutation. In EuroGP 1998, LNCS 1391, pp. 37--48. Google ScholarDigital Library
- Le Goues, C., et al. GenProg: A generic method for automatic software repair. IEEE Transactions on Software Engineering 38, 1 (2012), 54--72. Google ScholarDigital Library
- Li, H., and Durbin, R. Fast and accurate long-read alignment with Burrows-Wheeler transform. Bioinformatics 26, 5 (2010), 589--595. Google ScholarDigital Library
- Papadakis, M., Jia, Y., Harman, M., and Le Traon, Y. Trivial compiler equivalence. In ICSE 2015Google Scholar
- Petke, J., et al. Using genetic improvement and code transplants to specialise a C++ program to a problem class. In EuroGP 2014, pp. 137--149.Google Scholar
- Poli, R., et al. A field guide to genetic programming. http://www.gp-field-guide.org.uk, 2008. Google ScholarDigital Library
- Price, G. R. Selection and covariance. Nature 227 (1 August 1970), 520--521.Google ScholarCross Ref
- Syswerda, G. Uniform crossover in genetic algorithms. In FOGA 1989, pp. 2--9. Google ScholarDigital Library
Index Terms
- Improving CUDA DNA Analysis Software with Genetic Programming
Recommendations
CUDA-MEME: Accelerating motif discovery in biological sequences using CUDA-enabled graphics processing units
Motif discovery in biological sequences is of prime importance and a major challenge in computational biology. Consequently, numerous motif discovery tools have been developed to date. However, the rapid growth of both genomic sequence and gene ...
Evolving CUDA PTX programs by quantum inspired linear genetic programming
GECCO '11: Proceedings of the 13th annual conference companion on Genetic and evolutionary computationThe tremendous computing power of Graphics Processing Units (GPUs) can be used to accelerate the evolution process in Genetic Programming (GP). The automatic generation of code using the GPU usually follows two different approaches: compiling each ...
Comments