Submit Manuscript  

Article Details


On the Use of Topological Features of Metabolic Networks for the Classification of Cancer Samples

[ Vol. 22 , Issue. 2 ]

Author(s):

Jeaneth Machicao*, Francesco Craighero, Davide Maspero, Fabrizio Angaroni, Chiara Damiani , Alex Graudenzi *, Marco Antoniotti and Odemir M. Bruno*   Pages 88 - 97 ( 10 )

Abstract:


Background: The increasing availability of omics data collected from patients affected by severe pathologies, such as cancer, is fostering the development of data science methods for their analysis.

Introduction: The combination of data integration and machine learning approaches can provide new powerful instruments to tackle the complexity of cancer development and deliver effective di-agnostic and prognostic strategies.

Methods: We explore the possibility of exploiting the topological properties of sample-specific met-abolic networks as features in a supervised classification task. Such networks are obtained by pro-jecting transcriptomic data from RNA-seq experiments on genome-wide metabolic models to define weighted networks modeling the overall metabolic activity of a given sample.

Results: We show the classification results on a labeled breast cancer dataset from the TCGA data-base, including 210 samples (cancer vs. normal). In particular, we investigate how the performance is affected by a threshold-based pruning of the networks by comparing Artificial Neural Networks, Support Vector Machines and Random Forests. Interestingly, the best classification performance is achieved within a small threshold range for all methods, suggesting that it might represent an effec-tive choice to recover useful information while filtering out noise from data. Overall, the best accu-racy is achieved with SVMs, which exhibit performances similar to those obtained when gene ex-pression profiles are used as features.

Conclusion: These findings demonstrate that the topological properties of sample-specific metabolic networks are effective in classifying cancer and normal samples, suggesting that useful information can be extracted from a relatively limited number of features.

Keywords:

Metabolic networks, cancer sample classification, machine learning, RNA-seq data, topological properties, network pruning.

Affiliation:

São Carlos Institute of Physics, University of São Paulo, São Carlos, Department of Informatics, Systems and Communication, University of Milan-Bicocca, Milan, Department of Informatics, Systems and Communication, University of Milan-Bicocca, Milan, Department of Informatics, Systems and Communication, University of Milan-Bicocca, Milan, Department of Biotechnology and Biosciences, University of Milan-Bicocca, Milan, Institute of Molecular Bioimaging and Physiology, Consiglio Nazionale delle Ricerche (IBFM-CNR), Segrate, Milan, Department of Informatics, Systems and Communication, University of Milan-Bicocca, Milan, Saõ Carlos Institute of Physics, University of Saõ Paulo, Saõ Carlos



Read Full-Text article