Integrating protein networks and machine learning for disease stratification in the Hereditary Spastic Paraplegias

Nikoleta Vavouraki; James E Tomkins; Eleanna Kara; Henry Houlden; John Hardy; Marcus J Tindall; Patrick A Lewis; Claudia Manzoni

doi:10.1016/j.isci.2021.102484

Integrating protein networks and machine learning for disease stratification in the Hereditary Spastic Paraplegias

iScience. 2021 Apr 28;24(5):102484. doi: 10.1016/j.isci.2021.102484. eCollection 2021 May 21.

Authors

Nikoleta Vavouraki^{1

2}, James E Tomkins¹, Eleanna Kara³, Henry Houlden⁴, John Hardy^{3

5

6

7

8

9}, Marcus J Tindall^{2

10}, Patrick A Lewis^{1

3

9

11}, Claudia Manzoni^{1

12}

Affiliations

¹ School of Pharmacy, University of Reading, Reading, RG6 6AX, UK.
² Department of Mathematics and Statistics, University of Reading, Reading, RG6 6AX, UK.
³ Department of Neurodegenerative Disease, UCL Queen Square Institute of Neurology, London, WC1N 3BG, UK.
⁴ Department of Neuromuscular Diseases, UCL Queen Square Institute of Neurology, London, WC1N 3BG, UK.
⁵ UK Dementia Research Institute at UCL and Department of Neurodegenerative Disease, UCL IoN, UCL London, W1T 7NF UK.
⁶ Reta Lila Weston Institute, UCL IoN, 1 Wakefield Street, London, WC1N 1PJ, UK.
⁷ UCL Movement Disorders Centre, Department of Clinical and Movement Neurosciences, UCL Queen Square Institute of Neurology, London, WC1N 3BG, UK.
⁸ Institute for Advanced Study, The Hong Kong University of Science and Technology, Hong Kong SAR, China.
⁹ Aligning Science Across Parkinson's (ASAP) Collaborative Research Network, Chevy Chase, MD 20815, USA.
¹⁰ Institute of Cardiovascular and Metabolic Research, University of Reading, Reading, RG6 6AS, UK.
¹¹ Department of Comparative Biomedical Sciences, Royal Veterinary College, London, NW1 0TU, UK.
¹² School of Pharmacy, University College London, London, WC1N 1AX, UK.

Abstract

The Hereditary Spastic Paraplegias are a group of neurodegenerative diseases characterized by spasticity and weakness in the lower body. Owing to the combination of genetic diversity and variable clinical presentation, the Hereditary Spastic Paraplegias are a strong candidate for protein-protein interaction network analysis as a tool to understand disease mechanism(s) and to aid functional stratification of phenotypes. In this study, experimentally validated human data were used to create a protein-protein interaction network based on the causative genes. Network evaluation as a combination of topological analysis and functional annotation led to the identification of core proteins in putative shared biological processes, such as intracellular transport and vesicle trafficking. The application of machine learning techniques suggested a functional dichotomy linked with distinct sets of clinical presentations, indicating that there is scope to further classify conditions currently described under the same umbrella-term of Hereditary Spastic Paraplegias based on specific molecular mechanisms of disease.

Keywords: Bioinformatics; Biological sciences; Molecular network; Network.

Abstract

Grants and funding