Email updates

Keep up to date with the latest news and content from BMC Musculoskeletal Disorders and BioMed Central.

Open Access Research article

Analysis of mass spectrometry data from the secretome of an explant model of articular cartilage exposed to pro-inflammatory and anti-inflammatory stimuli using machine learning

Anna L Swan1, Kirsty L Hillier2, Julia R Smith3, David Allaway4, Susan Liddell157, Jaume Bacardit678 and Ali Mobasheri101112131415279*

Author Affiliations

1 School of Biosciences, Faculty of Science, University of Nottingham, Sutton Bonington Campus, Leicestershire, LE12 5RD, UK

2 Musculoskeletal Research Group, School of Veterinary Medicine and Science, Faculty of Medicine and Health Science, University of Nottingham, Sutton Bonington Campus, Leicestershire, LE12 5RD, UK

3 Bruker UK Limited, Coventry, CV4 9GH, UK

4 WALTHAM® Centre for Pet Nutrition, Waltham-on-the-Wolds, Melton Mowbray, Leicestershire, LE14 4RT, UK

5 Proteomics Laboratory, School of Biosciences, University of Nottingham, Sutton Bonington Campus, Leicestershire, LE12 5RD, UK

6 School of Computer Science, University of Nottingham, Jubilee Campus, Nottingham, NG8 1BB, UK

7 The D-BOARD European Consortium for Biomarker Discovery, University of Nottingham, University Park, Nottingham, NG7 2RD, UK

8 School of Computing Science, Newcastle University, Claremont Tower, Newcastle-upon-Tyne, NE1 7RU, UK

9 Arthritis Research UK Centre for Sport, Exercise and Osteoarthritis, Nottingham University Hospitals, Nottingham, NG7 2UH, UK

10 Arthritis Research UK Pain Centre, The University of Nottingham, Queen's Medical Centre, Nottingham, NG7 2UH, UK

11 Medical Research Council and Arthritis Research UK Centre for Musculoskeletal Ageing Research, The University of Nottingham, Queen’s Medical Centre, Nottingham, NG7 2UH, UK

12 Center of Excellence in Genomic Medicine Research (CEGMR), King Fahad Medical Research Center (KFMRC), King AbdulAziz University, Jeddah, 21589, Kingdom of Saudi Arabia

13 Schools of Pharmacy and Life Sciences, University of Bradford, Richmond Road, Bradford, BD7 1DP, UK

14 Comparative Physiology, Medical Research Council-Arthritis Research UK Centre for Musculoskeletal Ageing Research, Arthritis Research UK Pain Centre, Arthritis Research UK Centre for Sport, Exercise, and Osteoarthritis, Faculty of Medicine and Health Sciences, The University of Nottingham, Sutton Bonington Campus, Leicestershire, LE12 5RD, UK

15 Faculty of Medicine and Health Sciences, The University of Nottingham, Sutton Bonington Campus, Leicestershire, LE12 5RD, UK

For all author emails, please log on.

BMC Musculoskeletal Disorders 2013, 14:349  doi:10.1186/1471-2474-14-349

Published: 13 December 2013

Abstract

Background

Osteoarthritis (OA) is an inflammatory disease of synovial joints involving the loss and degeneration of articular cartilage. The gold standard for evaluating cartilage loss in OA is the measurement of joint space width on standard radiographs. However, in most cases the diagnosis is made well after the onset of the disease, when the symptoms are well established. Identification of early biomarkers of OA can facilitate earlier diagnosis, improve disease monitoring and predict responses to therapeutic interventions.

Methods

This study describes the bioinformatic analysis of data generated from high throughput proteomics for identification of potential biomarkers of OA. The mass spectrometry data was generated using a canine explant model of articular cartilage treated with the pro-inflammatory cytokine interleukin 1 β (IL-1β). The bioinformatics analysis involved the application of machine learning and network analysis to the proteomic mass spectrometry data. A rule based machine learning technique, BioHEL, was used to create a model that classified the samples into their relevant treatment groups by identifying those proteins that separated samples into their respective groups. The proteins identified were considered to be potential biomarkers. Protein networks were also generated; from these networks, proteins pivotal to the classification were identified.

Results

BioHEL correctly classified eighteen out of twenty-three samples, giving a classification accuracy of 78.3% for the dataset. The dataset included the four classes of control, IL-1β, carprofen, and IL-1β and carprofen together. This exceeded the other machine learners that were used for a comparison, on the same dataset, with the exception of another rule-based method, JRip, which performed equally well. The proteins that were most frequently used in rules generated by BioHEL were found to include a number of relevant proteins including matrix metalloproteinase 3, interleukin 8 and matrix gla protein.

Conclusions

Using this protocol, combining an in vitro model of OA with bioinformatics analysis, a number of relevant extracellular matrix proteins were identified, thereby supporting the application of these bioinformatics tools for analysis of proteomic data from in vitro models of cartilage degradation.

Keywords:
Osteoarthritis; Cartilage; Biomarker; Interleukin 1 β; Carprofen; Bioinformatics; Machine learning