Modelling and Recognition of Protein Contact Networks by Multiple Kernel Learning and Dissimilarity Representations.

Alessio Martino,Enrico De Santis,Antonello Rizzi,Alessandro Giuliani

doi:10.3390/e22070794

Alessio Martino, Enrico De Santis + Show 2 more

Open Access

https://doi.org/10.3390/e22070794

Copy DOI

Abstract

Multiple kernel learning is a paradigm which employs a properly constructed chain of kernel functions able to simultaneously analyse different data or different representations of the same data. In this paper, we propose an hybrid classification system based on a linear combination of multiple kernels defined over multiple dissimilarity spaces. The core of the training procedure is the joint optimisation of kernel weights and representatives selection in the dissimilarity spaces. This equips the system with a two-fold knowledge discovery phase: by analysing the weights, it is possible to check which representations are more suitable for solving the classification problem, whereas the pivotal patterns selected as representatives can give further insights on the modelled system, possibly with the help of field-experts. The proposed classification system is tested on real proteomic data in order to predict proteins’ functional role starting from their folded structure: specifically, a set of eight representations are drawn from the graph-based protein folded description. The proposed multiple kernel-based system has also been benchmarked against a clustering-based classification system also able to exploit multiple dissimilarities simultaneously. Computational results show remarkable classification capabilities and the knowledge discovery analysis is in line with current biological knowledge, suggesting the reliability of the proposed system.

Highlights

Dealing with structured data is an evergreen challenge in pattern recognition and machine learning
This paper is organised as follows: Section 2 overviews some theory related to kernel methods and dissimilarity spaces; Section 3 presents the proposed methodology; Section 4 shows the results obtained with the proposed approach, along with a comparison against a clustering-based classifier, and we provide some remarks on the two-fold knowledge discovery phase
We proposed a classification system able to explore simultaneously multiple representations following an hybridisation between multiple kernel learning and dissimilarity spaces, exploiting the discriminative power of kernel methods and the customisability of dissimilarity spaces

Summary

Introduction

Dealing with structured data is an evergreen challenge in pattern recognition and machine learning. Feature generation and/or feature engineering, where numerical features are extracted ad-hoc from structured patterns (e.g., using their properties or via measurements) and can be further merged according to different strategies (e.g., in a multi-modal way [11]); Ad-hoc dissimilarities in the input space, where custom dissimilarity measures are designed in order to process structured patterns directly in the input domain without moving towards. Common—possibly parametric—edit distances include the Levenshtein distance [12] for sequence domains and graph edit distances [13] for graphs domains; Embedding via information granulation and granular computing [3,14,15,16,17,18,19,20,21,22,23,24,25]; Dissimilarity representations [26,27,28], where structured patterns are embedded in the Euclidean space according to their pairwise dissimilarities; Kernel methods, where the mapping between the original input space and the Euclidean space exploits positive-definite kernel functions [29,30,31,32,33]

Methods

Results

Conclusion