Personal webpage: Colin Campbell

Contact details:
Room 2.39, Merchant Venturer's Building,
University of Bristol,
Bristol BS8 1UB,
United Kingdom

Tel: +44 (0)117-33-15620
Fax: +44 (0)117-954-5208 (attn: Colin Campbell (EMAT))
Mobile: 07891-608-017

Brief Biography:

I gained a First Class Honours degree in Physics from Imperial College, London and a Doctorate from the Department of Mathematics, King's College, London, under the supervision of Prof. Peter West FRS. I am currently a Reader in the Merchant Venturer's School of Engineering, University of Bristol. For research purposes our group is a component part of the Intelligent Systems Laboratory at the University of Bristol, of which I'm currently Head. For teaching purposes I am associated with the Department of Engineering Mathematics. My research interests are machine learning, including probabilistic graphical models and kernel-based methods, algorithm design and the applications of machine learning techniques in bioinformatics, particularly medical bioinformatics. I've been focussed on the latter area over the last few years, since projects in this area look to be highest impact. Our research is currently funded by the generous support of the the EPSRC and the Medical Research Council.

Research News

Research News blog for an informal outline of some current research themes.

Recent Journal Papers

  • Mark Rogers, Hashem Shihab, Tom Gaunt, and Colin Campbell. CScape: a tool for predicting oncogenic single-point mutations in the cancer genome. Scientific Reports (Nature) 7, article number: 11597, doi:10.1038/s41598-017-11746-4, (2017) (main paper and supplementary). This method uses integrative machine learning methods to propose a classifier for predicting if a single point mutation in the cancer genome is a disease-driver or neutral, for mutations in both non-coding and coding regions (predictions are based on reference GRCh37/hg19 (ENSEMBL release 87) of the human genome). Our CScape predictor is located here and uses a wide variety of data sources to predict disease-driver status.
  • Mark F. Rogers, Hashem A. Shihab, Matthew Mort, David N. Cooper, Tom R. Gaunt and Colin Campbell. FATHMM-XF: accurate prediction of pathogenic point mutations via extended features. Bioinformatics btx536, (2017). Using machine learning methods we propose a classifier for predicting if single point mutations in the human genome are disease-drivers or neutral: the method gives a confidence measure associated with each predicted class label. The FATHMM-XF server for GRCh37/hg19 is available here. This predictor uses more types of data than our earlier FATHMM-MKL predictor, with some methodology improvement in addition.
  • Michael Ferlaino, Mark F. Rogers, Hashem A. Shihab, Matthew Mort, David N. Cooper, Tom R. Gaunt and Colin Campbell. An integrative approach to predicting the functional effects of small indels in non-coding regions of the human genome. BMC Bioinformatics (2017). Using machine learning methods we propose a classifier for predicting if small indels in the human genome are disease-drivers or neutral. The FATHMM-indel server is available here.
  • Su-Yi Loh, Thomas Jahans-Price, Michael Greenwood, Mingkwan Greenwood, See-Ziau Hoe, Agnieszka Konopacka, Colin Campbell, David Murphy, and Charles Hindmarch. Unsupervised network analysis of the plastic supraoptic nucleus transcriptome predicts Caprin-2 regulatory interactions. eNeuro (2017). We use a graphical lasso algorithm with microarray data to find hub nodes (genes) playing a major role in the regulation of hypertension.
  • Hashem Shihab, Mark Rogers, Colin Campbell and Tom Gaunt. HIPred: an integrative approach to predicting haploinsufficient genes. Bioinformatics (2017) 33 (12): 1751-1757.
  • Hashem A. Shihab, Mark F. Rogers, Michael Ferlaino, Colin Campbell and Tom R. Gaunt. GTB - an online genome tolerance browser. BMC Bioinformatics 2017, 18:20, DOI: 10.1186/s12859-016-1436-4. The Genome Tolerance Browser enables visualisation of predicted tolerance of genomic regions to mutational variation. It includes 13 genome-wide prediction algorithms and conservation scores, 12 non-synonymous prediction algorithms and four cancer-specific algorithms.
  • Tom G Richardson, Nicholas J Timpson, Colin Campbell and Tom R Gaunt. A pathway-centric approach to rare variant association analysis. European Journal of Human Genetics (, (2016), 1-7, doi:10.1038/ejhg.2016.113.
  • Richardson T.G., Campbell C., Timpson N.J. and Gaunt T.R. Incorporating Non-Coding Annotations into Rare Variant Analysis. PLoS ONE 11(4) (2016): e0154181.
  • Richardson T.G., Shihab H.A., Rivas M.A., McCarthy M.I., Campbell C., Timpson N.J. and Gaunt T.R. A Protein Domain and Family Based Approach to Rare Variant Association Analysis. PLoS ONE 11(4) (2016): e0153803.
  • Richardson T.G. et al. Collapsed Methylation Quantitative Trait Loci analysis for Low Frequency and Rare variants. Human Molecular Genetics (2016) doi: 10.1093/hmg/ddw283.
  • Lulu Jiang, Charles C. T. Hindmarch, Mark Rogers, Colin Campbell, Christy Waterfall, Jane Coghill, Peter W. Mathieson and Gavin I. Welsh. RNA sequencing analysis of human podocytes reveals glucocorticoid regulated gene networks targeting non-immune pathways. Scientific Reports (Nature) 6, article number: 35671 (2016) doi:10.1038/srep35671.
  • Hannah Scott, Mark F. Rogers, Helen L. Scott, Colin Campbell, Elizabeth C. Warburton and James B. Uney. Recognition memory-induced gene expression in the perirhinal cortex: A transcriptomic analysis. Behavioural Brain Research (2017) 328:1-12.
  • Carlos Fernandez-Lozano, Jose A. Seoane, Marcos Gestal, Tom R. Gaunt, Julain Dorado, Alejandro Pazos and Colin Campbell. Texture analysis in gel electrophoresis images using an integrative kernel-based approach. Scientific Reports (Nature), 6, Article number 19256 (2016).
  • C. Rivers, H. Scott, M. Rogers, Y. Lee, G. Toye, J. Idris, J. Gaunt, C. Hales, T. Curk, C. Campbell, J. Ule, M. Norman, J. B. Uney. iCLIP identifies novel neuronal roles for SAFB1 in regulating RNA processing and neuronal function. BMC Biology 13:111 (2015)
  • Hashem Shihab, Mark Rogers, Julian Gough, Matthew Mort, David Cooper, Ian Day, Tom Gaunt and Colin Campbell. An Integrative Approach to Predicting the Functional Effects of Non-Coding and Coding Sequence Variation Bioinformatics 31(10): 1536-1543 (2015). Supplementary information and website for the coding/non-coding predictor. This method uses integrative machine learning methods to predict if single nucleotide variants in the human genome are likely functional in disease. The predictor outputs a confidence label associated with the prediction and it gives predictions for sequence variants in both the coding and non-coding regions of the human genome. There is further information about this approach and various extensions of this project in the Available software submenu on the left.

  • Book on kernel-based learning methods:

    Learning with Support Vector Machines by Colin Campbell and Yiming Ying (Morgan and Claypool, 2011). This is a concise introduction to Support Vector Machines and kernel-based learning. It is available as an ebook from Morgan and Claypool or as hardcopy from Amazon or Waterstones. Introductory Lectures on Support Vector Machines, from the 6th International Summer School on Pattern Recognition, provide a shortened summary of some of the content of this book.

    PhD Opportunities:

    PhD funding for projects in our areas of interest is available from a number of sources:

  • Departmental Training Awards (DTAs).
  • In addition there are further Bristol university scholarships for both UK/EU candidates and overseas (non-UK and non-EU) candidates.
  • Occasionally we also have other PhD studentships which are open to nationals of any country and are linked to a specific project.
  • Please email Dr. Campbell directly (C.Campbell(at) for further information.

    Postdoctoral Opportunities:

    For very well qualified candidates we support applications for Fellowship awards from a variety of research sponsors.

    Previous Group Members:

    Michael Ferlaino has moved to the Data Science Institute, University of Oxford. Yiming Ying is now Professor in the Department of Mathematics and Statistics, State University of New York at Albany. Kaizhu Huang is now Associate Professor at the National Laboratory of Pattern Recognition, The Chinese Academy of Sciences, Beijing, China. UK-based academic staff who are alumni of the group include Nello Cristianini, Professor at the University of Bristol, Simon Rogers (University of Glasgow) and Stephen Coombes, Professor at the University of Nottingham.

    Video lectures:

  • Various talks on kernel-based learning.
  • Past Workshops organised:

  • Cancer Bioinformatics Workshop, Cambridge, 2-4 September, 2010
  • Several NIPS Workshops on machine learning and bioinformatics.