Thanks to David Cairns (MRC Research Fellow in Biostatistics), Roz Banks (Professor of Biomedical Proteomics) and Dave Perkins (Principal Research Scientist in Bioinformatics) from the Section of Epidemiology and Biostatistics and the Clinical Proteomics Research Group, Leeds Institute of Molecular Medicine, University of Leeds, UK and to Cancer Research UK for funding.


Banks RE, Stanley AJ, Cairns DA, Barrett JH, Clarke P, Thompson D, Selby PJ. Influence of blood sample processing on low-molecular-weight proteome identified by surface-enhanced laser desorption/ionisation mass spectrometry. Clinical Chemistry 2005; 51: 1637-1649.

Barrett JH and Cairns DA. Application of the Random Forest Classification Method to Peaks Detected from Mass Spectrometric Proteomic Profiles of Cancer Patients and Controls. Statistical Applications in Genetics and Molecular Biology 2008, 7(2), Article 4.

Breiman L. Random Forests. Machine Learning 2001; 45: 5-32.

Cairns DA, Barrett JH, Billingham LJ, Stanley AJ, Xinarianos G, Field JK, Johnson PJ, Selby PJ and Banks RE. Sample size determination in clinical proteomic profiling experiments using mass spectrometry for class comparison. Proteomics, 2009; 9:74-86.

Cairns DA, Thompson D, Perkins DN, Stanley AJ, Selby PJ and Banks RE. Proteomic profiling using mass spectrometry – does normalizing by total ion current potentially mask some biological differences? Proteomics 2008; 8: 21-27.

Hand DJ. Statistical Applications in Genetics and Molecular Biology 2008; 7(2): 15.

Hill EG, Schwacke JH, Comte-Walters S, Slate EH, Oberg AL, Eckel-Passow JE, Therneau TM and Schey KL. A statistical model for iTRAQ data analysis. Journal of Proteome Research 2008; 7: 3091-3101.

Mertens B. Organizing a competition on clinical mass spectrometry based proteomic diagnosis. Statistical Applications in Genetics and Molecular Biology 2008; 7(2): 3.

Morris JS, Coombes KR, Koomen J, Baggerly KA and Kobayashi R. Feature extraction and quantification for mass spectrometry in biomedical applications using the mean spectrum. Bioinformatics 2005; 21: 1764-1775.

Oberg AL and Vitek O. Statistical design of quantitative mass spectrometry-based proteomic experiments. Journal of Proteome Research 2009; 8: 2144-2156.

Rogers MA, Clarke P, Noble J, Munro NP, Paul A, Selby PJ and Banks RE. Proteomic profiling of urinary proteins in renal cancer by surface enhanced laser desorption ionization and neural-network analysis: Identification of key issues affecting potential clinical utility. Cancer Research 2003; 63: 6971-6983.

Tibshirani R, Hastie T, Narasimhan B, Soltys S, Shi GY, Koong A and Le QT. Sample classification from protein mass spectrometry, by 'peak probability contrasts'. Bioinformatics 2004; 20: 3034-3044.