GTED: Graph traversal edit distance

Ebrahimpour Boroojeny, A ; Sharif University of Technology | 2018

505 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/978-3-319-89929-9_3
  3. Publisher: Springer Verlag , 2018
  4. Abstract:
  5. Many problems in applied machine learning deal with graphs (also called networks), including social networks, security, web data mining, protein function prediction, and genome informatics. The kernel paradigm beautifully decouples the learning algorithm from the underlying geometric space, which renders graph kernels important for the aforementioned applications. In this paper, we give a new graph kernel which we call graph traversal edit distance (GTED). We introduce the GTED problem and give the first polynomial time algorithm for it. Informally, the graph traversal edit distance is the minimum edit distance between two strings formed by the edge labels of respective Eulerian traversals of the two graphs. Also, GTED is motivated by and provides the first mathematical formalism for sequence co-assembly and de novo variation detection in bioinformatics. We demonstrate that GTED admits a polynomial time algorithm using a linear program in the graph product space that is guaranteed to yield an integer solution. To the best of our knowledge, this is the first approach to this problem. We also give a linear programming relaxation algorithm for a lower bound on GTED. We use GTED as a graph kernel and evaluate it by computing the accuracy of an SVM classifier on a few datasets in the literature. Our results suggest that our kernel outperforms many of the common graph kernels in the tested datasets. As a second set of experiments, we successfully cluster viral genomes using GTED on their assembly graphs obtained from de novo assembly of next generation sequencing reads. Our GTED implementation can be downloaded from http://chitsazlab.org/software/gted/. © Springer International Publishing AG, part of Springer Nature 2018
  6. Keywords:
  7. Classification (of information) ; Data mining ; Genes ; Integer programming ; Learning systems ; Linear programming ; Molecular biology ; Polynomial approximation ; Applied machine learning ; De novo assemblies ; Linear programming relaxation ; Mathematical formalism ; Minimum edit distance ; Next-generation sequencing ; Polynomial-time algorithms ; Protein function prediction ; Learning algorithms
  8. Source: 22nd International Conference on Research in Computational Molecular Biology, RECOMB 2018, 21 April 2018 through 24 April 2018 ; Volume 10812 LNBI , 2018 , Pages 37-53 ; 03029743 (ISSN); 9783319899282 (ISBN)
  9. URL: https://link.springer.com/chapter/10.1007/978-3-319-89929-9_3