Advertisement

Evaluating Graph Database Systems for Biological Data

  • Minghe YuEmail author
  • Yaxuan Zang
  • Shaopeng Dai
  • Daoyi Zheng
  • Jinheng Li
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 911)

Abstract

The graph database system can express the complex relationships in the real world through the simple and intuitive description of “entities” and“relationships”. Now, the graph database system is used to analyze complex relationship between entities, especially, in the scientific research field. For example, the RDF-based graph database system has been used for biological data processing. Many previous works have proved that the graph database system is very suite for biological researchers to store and analyze biological data. In this paper, we evaluate two graph database systems (Apache Jena and gStore) by the biological RDF data set, the biological RDF data set contains 10 millions pieces of data on the types of Uniport, Enzyme, Taxonomy and Gen. And we design five query workloads, which are “1-step”,“2-steps(p1)”, “2-steps(p2)”,“union” and “filtering” and one data load workload. The metrics which we evaluated including user-observed metrics (workload execution time), system metrics (CPU utilization, I/O wait ratio and memory bandwith) and micro-architecture metrics (IPC, cache miss and branch misprediction ratio). The experiment results show that gStore performs better in complex query workloads, and Jena is more suitable for the simple ones.

Keywords

Graph database systems Performance evaluation Biological data 

Notes

Acknowledgment

This work is supported by the National Key Research and Development Plan of China (Grant No.2016YFB1000600 and 2016YFB1000601).

References

  1. 1.
    De Virgilio, R., Rombo, S.E.: Approximate matching over biological RDF graphs. 1413–1414 (2012)Google Scholar
  2. 2.
    Consortium U P: UniProt: a hub for protein information. Nucleic Acids Res. 43(Database issue), 204–212 (2015)Google Scholar
  3. 3.
    UniProt Consortium: UniProt: the universal protein knowledgebase. Nucleic Acids Res. 45(D1), D158–D169 (2016)CrossRefGoogle Scholar
  4. 4.
    Duan, S., Kementsietsidis, A., Srinivas, K., et al.: Apples and oranges: a comparison of RDF benchmarks and real RDF datasets. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, pp. 145-156. ACM (2011)Google Scholar
  5. 5.
    Prud’Hommeaux, E., Seaborne, A.: SPARQL query language for RDF, W3C Recommendation (2008)Google Scholar
  6. 6.
    Zou, L., Özsu, M.T., Chen, L., et al.: gStore: a graph-based SPARQL query engine. VLDB J. Int. J. Very Large Data Bases 23(4), 565–590 (2014)CrossRefGoogle Scholar
  7. 7.
    Zeng, L., Zou, L.: Redesign of the gStore system. Front. Comput. Sci. 2, 1–19 (2018)Google Scholar
  8. 8.
  9. 9.
    Wang, L., et al.: Bigdatabench: a big data benchmark suite from internet services. In: 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). IEEE (2014)Google Scholar
  10. 10.
    Zheng, C., Zhan, J., Jia, Z., et al.: Characterizing OS behaviors of datacenter and big data workloads. In: 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 1079-1086. IEEE (2016)Google Scholar
  11. 11.
    Jia, Z., Zhan, J., Wang, L., et al.: Characterizing and subsetting big data workloads. In: 2014 IEEE International Symposium on Workload Characterization (IISWC), pp. 191–201. IEEE (2014)Google Scholar
  12. 12.
    Gao, W., Zhan, J., Wang, L., et al.: Data Motifs: A Lens Towards Fully Understanding Big Data and AI Workloads. IEEE Parallel Architectures and Compilation Techniques (2018)Google Scholar
  13. 13.
    Gao, W., Zhan, J., Wang, L., et al.: Data Motif-based Proxy Benchmarks for Big Data and AI Workloads. IISWC (2018)Google Scholar
  14. 14.
    Jia, Z., Zhan, J., Wang, L., et al.: Understanding big data analytics workloads on modern processors. IEEE Trans. Parallel Distrib. Syst. 28(6), 1797–1810 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Minghe Yu
    • 1
    • 2
  • Yaxuan Zang
    • 1
    • 3
  • Shaopeng Dai
    • 1
    • 2
  • Daoyi Zheng
    • 1
    • 2
  • Jinheng Li
    • 1
  1. 1.Institute of Computing TechnologyChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina
  3. 3.University of Electronic Science and Technology of ChinaChengduChina

Personalised recommendations