AI at Bristol
Artificial Intelligence @ Bristol




  • Christophe Ladroue, Colin Campbell, Juan-Pablo Casas, Ian Day and Tom Gaunt A phenotypic approach to SNP filtering for genome-wide association studies. Journal submission, 2012.

  • Colin Campbell. Machine Learning Methodology in Bioinformatics. Handbook of Bio- and Neuro-informatics, ed. Irwin King and Kaizhu Huang. Spinger-Verlag, 2012, 45 pages.

  • Yiming Ying, Kaizhu Huang and Colin Campbell. Enhanced Protein Fold Recognition through a Novel Data Integration Approach. BMC Bioinformatics, 2009, 10:267.

    Download the pdf. Also available is a NIPS2009 Workshop Abstract pdf summarising the multi-kernel learning methods in this paper.

  • Yiming Ying, Colin Campbell, Theodoros Damoulas and Mark Girolami. Class Prediction from Disparate Biological Data Sources using an Iterative Multi-kernel Algorithm. Lecture Notes in Bioinformatics 5780 (2009) pp.427-438.

    Download the pdf

  • Phaedra Agius, Yiming Ying and Colin Campbell. Bayesian Unsupervised Learning with Multiple Data Types. Statistical Applications in Genetics and Molecular Biology: Volume 8, Issue 1, Article 27 (2009).

    Download the pdf

  • Yiming Ying, Peng Li and Colin Campbell. A marginalized variational Bayesian approach to the analysis of array data. BMC Proceedings, 2008, 2(Suppl 4):S7.

    Download the pdf

  • Theodoros Damoulas, Yiming Ying, Mark Girolami and Colin Campbell. Inferring Sparse Kernel Combinations and Relevance Vectors: An application to subcellular localization of proteins. Proceedings of the Seventh International Conference on Machine Learning and Applications (ICMLA'08), San Diego, California.

    Download the pdf

  • Colin S Cooper, Colin Campbell and Sameer Jhavar. Mechanisms of Disease: biomarkers and molecular targets from microarray gene expression studies in prostate cancer. Nature (Clinical Practice Urology). (2007) Volume 4, pages 677-687.

  • Peng Li, Yiming Ying and Colin Campbell. A Variational Approach to Semi-Supervised Clustering. Proceedings, ESANN2009, p. 11-16.

    Download the pdf. A fuller length report is available here.

  • Luke Carrivick, Simon Rogers, Jeremy Clark, Colin Campbell, Mark Girolami and Colin Cooper. Identification of Prognostic Signatures in Breast Cancer Microarray Data using Bayesian Techniques. Journal of the Royal Society: Interface Vol. 3 (2006) pages 367-381.

    Two new Bayesian unsupervised learning methods are applied to four microarray datasets for breast cancer. The analysis suggests a minimum 4 or 5 subtypes for sporadic breast cancer, each with quite distinct clinical outcomes. One subtype is purely indolent. The genes GRB7 and ERBB2 (HER2) only over-express in one subtype. The most aggressive subtype is the most distinct and associated with the basaloid or basal-like subtype of breast cancer: it is marked by a distinct reciprocity relation for the forkhead transcription factor genes: FOXA1 and FOXC1 (for more detail see our paper in Statistical Applications in Genetics and Molecular Biology above). The paper illustrates the important insights gained from using Bayesian methods in this context.

    Download the postscript (3.5 Mb)
    Download the pdf (0.5Mb) or
    Journal pdf (0.5Mb)

  • Luke Carrivick and Colin Campbell. A Bayesian Approach to the Analysis of Microarray Datasets using Variational Inference. Technical Report TR-CI-2006 1st February, 2006.

    This Technical Report gives details of the variational Bayes approach to clustering used in subsequent papers. However, note that the alpha-update was not implemented in this TR. This TR gives some further detail of the distinctive genetic signature of the basaloid subtype of breast cancer (see above paper) and proposes the use of a normalised ratio of FOXC1 over FOXA1 as a biomarker for this subtype. The role of microRNA within this subtype is further discussed in our paper `Bayesian Unsupervised Learning with Multiple Data Types' above.

    Download the pdf

  • Luke Carrivick. Probabilistic Models in the Biomedical Sciences. PhD thesis (2006).

    Download the pdf (4.5MB)

  • Simon Rogers, Mark Girolami, Colin Campbell and Rainer Breitling. The Latent Process Decomposition of cDNA Microarray Datasets. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2005, Vol. 2, pages 143-156.

    Download the postscript (7.3MB)
    Download the pdf (0.4MB)

  • Zsofia Kote-Jarai, Lucy Matthews, Ana Osorio, Susan Shanley, Ian Giddings, Francois Moreews, Imogen Locke, D. Gareth Evans, Diana Eccles, Carrier Clinic Collaborators, Richard D. Williams, Mark Girolami, Colin Campbell and Ros Eeles. Accurate prediction of BRCA1 and BRCA2 heterozygous genotype using expression profiling after induced DNA damage, Clinical Cancer Research, 2006, Vol. 12(13), pages 3896-3901.

  • Sashi Kommu and Colin Campbell. The Impact of Bioinformatics in Uro-oncology, BJU International, 2006, Volume 98(2), pages 249-251 (Editorial Comment).

  • Richard D Williams, Sandra N. Hing, Braden T. Greer, Craig C., Whiteford, Jun S. Wei, Rachael Natrajan, Anna Kelsey, Simon Rogers, Colin Campbell, Kathy Pritchard-Jones and Javed Khan. Prognostic Classification of Relapsing Favourable Histology Wilms Tumour using cDNA Microarray Expression Profiling and Support Vector Machines. Genes, Chromosomes and Cancer, 2004, Volume 41, Issue 1, pages 65 - 79.

    Download the pdf

  • Simon Rogers, Richard D. Williams and Colin Campbell. Class Prediction with Microarray Datasets, in U. Seiffert, L.C. Jain and P. Schweizer (eds), Bioinformatics using Computational Intelligence Paradigms, Springer, 2005, pages p. 119-141.

    Download the postscript
    Download the pdf

  • Sandra Edwards, Colin Campbell, Penny Flohr, Janet Shipley, Ian Giddings, Robert te-Poele, Andrew Dodson, Christophe Foster, Jeremy Clark, Sameer Jhavar, Gyula Kovacs and Colin S Cooper. Expression analysis onto microarrays of randomly selected cDNA clones highlights HOXB13 as a marker of human prostate cancer . British Journal of Cancer, Vol. 92, 2005, pages 376-381.

  • Kote-Jarai Z, Williams RD, Cattini N, Copeland M, Giddings I, Wooster R, tePoele RH, Workman P, Gusterson B, Peacock J, Gui G, Campbell C, Eeles R. Gene expression profiling after radiation-induced DNA damage is strongly predictive of BRCA1 mutation carrier status. Clinical Cancer Research 10(2004) 958-63.

  • S. Rogers, M. Girolami and C. Campbell. A Latent Process Decomposition Model for Interpreting cDNA Microarray Datasets. "Currents in Computational Molecular Biology 2004", Eigth Annual International Conference on Research in Computational Molecular Biology (RECOMB 2004), San Diego.

  • Simon Rogers. Machine learning techniques for microarray analysis. PhD thesis (2004). Download the pdf (2.4MB)

  • Y.-J.Lu, D. Williamson, R. Wang, B. Summersgill, S. Rodriguez, S. Rogers, K. Pritchard-Jones, C. Campbell, J. Shipley. Expression profiling targeting chromosomes for tumor classification and prediction of clinical behavior Genes, Chromosomes and Cancer 2003, 38: 207-214.

  • J. Clark, S. Edwards, A. Feber, P. Flohr, M. John, I. Giddings, S. Crossland, M. R Stratton, R. Wooster, C. Campbell, C.S. Cooper. Genome-wide screening for complete genetic loss in prostate cancer by comparative hybridization onto cDNA microarrays. Oncogene (Nature Publishing Group) 2003, 22: 1247-1252.

  • J. Clark, S. Edwards, M. John, P. Flohr, T. Gordon, K. Maillard, I. Giddings, C. Brown, A. Bagherzadeh, C. Campbell, J.Shipley, R. Wooster, C. S. Cooper. Identification of amplified and expressed genes in breast cancer by comparative hybridization onto microarrays of randomly selected cDNA clones Genes, Chromosomes and Cancer 2002, 34:104-114.

  • S. Mukherjee, P. Tamayo, S. Rogers, R. Rifkin, A. Engle, C.Campbell, T. Golub and J. Mesirov, Estimating Dataset Size Requirements for Classifying DNA Microarray Data, Journal of Computational Biology, 2003, 10: 119-142.

  • Y. Li, C. Campbell and M. Tipping. Bayesian automatic relevance determination algorithms for classifying gene expression data. Bioinformatics 2002 18: 1332-1339.

    Outlines two Bayesian ARD algorithms for classifying gene expression data. The algorithms perform feature selection and build an accurate hypothesis using relatively few features. They are evaluated on three cancer datasets (colon cancer, ovarian cancer and leukemia).

    Download the postscript or the pdf

  • Support Vector Machine Classification and Validation of Cancer Tissue Samples using Microarray Expression Data. T. Furey, N. Cristianini, N. Duffy, D. Bednarski, Michel Schummer and D. Haussler Bioinformatics, 2000, 16:906-914.
    Applies SVMs to classifying gene expression data for cancer.

    View details

  • Knowledge-based Analysis of Microarray Gene Expression Data using Support Vector Machines. M. Brown, W. Grundy, D. Lin, N. Cristianini C. Sugnet, T. Furey, M. Ares Jr., D. Haussler Proceedings of the National Academy of Sciences 2000, 97(1) p. 262-267.
    Application of SVMs to a gene expression dataset for the budding yeast S. Cerevisiae.

    View details

  • C. Campbell, An Introduction to Kernel Methods. Chapter 7 in Radial Basis Function Networks: Design and Applications. R.J. Howlett and L.C. Jain (eds), Physica Verlag, 2001.