Dr Kevin Bryson

  • Senior Lecturer (School of Computing Science)

Biography

I joined the School in 2021 as a Senior Lecturer in Bioinformatics and Machine Learning.

I received a BSc honours degree (1st class) in Mathematics and Computer Science from Heriot-Watt University in 1991 and a DPhil in Physics from the University of York in 1996, and then spent 3 years in industry working at Oxford Molecular Ltd. developing bioinformatics software before taking up a BBSRC Fellowship at University of Warwick, studying the application of multi-agent systems to bioinformatics.

After my postdoc position at Warwick, I got an EU Individual Marie Curie Fellowship at INRA in Paris where we developed another cooperative distributed system for annotating the genomes of fermented sausage, cheese and yogurt bacteria.

I then moved to the Department of Computer Science at UCL to take up a Fellowship position analyzing gene expression profiles of stem cells; leading onto a lectureship position, senior lecturer and associate professor in in bioinformatics and systems biology where we applied machine learning techniques to protein structure, biological networks, -omics data and histopathology images, collaborating with bioscience groups mostly in the area of cancer.

 

Research interests

We use machine learning, and in particular deep learning, to tackle challenges in the area of bioscience. A lot of our research has been in the area of cancer and we are grateful to the clinical research groups that have allowed us to work with them on these problems.

We work with -omics data including gene expression, genomic methylation, proteomics and metabolics data. We employ supervised and unsupervised machine learning approaches to make predictions and reveal patterns in the data. We use biological network information to integrate data and gain holistic understanding of biological mechanisms. We also analyze image data including fluorescent labelled images of E. coli and H&E microscope slide images of cancer tissues sections. The long-term goal is to integrate molecular information, imaging data and clinical data to gain holistic understanding of diseases, particularly targeted at cancer.

Projects involving clinical prediction from -omics data have included:
  • Breast cancer subtypes.
  • Psychiatric conditions such as depression and autism.

We have also developed a number of machine learning tools to:

  • Find patterns within large heterogeneous gene expression data collections (MCbiclust based on R).
  • Create realistic synthetic gene expression datasets (GANs using TensorFlow).

We have recently started projects doing traditional image analysis (scikit-image) and CNN image prediction (PyTorch/Tensorflow) including:

  • Phenotype analysis of fluorescent C. elegans worms.
  • Nucleus image analysis using PCA, t-SNE and TensorFlow.
  • Classification between liposarcoma and lipoma using H&E whole slide images.
  • Classification between synovial sarcoma and singular fibrous tumour using H&E images.

We also analyze protein sequences using machine learning approaches to predict both structural and functional aspects of proteins including:

  • Secondary structure.
  • Protein disorder.
  • Amyloid propensity.
  • B-cell epitopes.
 

Publications

List by: Type | Date

Jump to: 2022 | 2021 | 2017 | 2016 | 2015 | 2013 | 2012 | 2010 | 2008 | 2007 | 2006
Number of items: 17.

2022

Viñas, R., Andrés-Terré, H., Liò, P. and Bryson, K. (2022) Adversarial generation of gene expression data. Bioinformatics, 38(3), pp. 730-737. (doi: 10.1093/bioinformatics/btab035) (PMID:33471074) (PMCID:PMC8756177)

2021

Park, G. W. (W.) and Bryson, K. (2021) LDEncoder: Reference deep learning-based feature detector for transfer learning in the field of epigenomics. In: 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB '21), Gainesville, Florida, 1-4 August 2021, p. 58. ISBN 9781450384506 (doi: 10.1145/3459930.3469487)

Yan, Y. et al. (2021) A continuously benchmarked and crowdsourced challenge for rapid development and evaluation of models to predict COVID-19 diagnosis and hospitalization. JAMA Network Open, 4(10), e2124946. (doi: 10.1001/jamanetworkopen.2021.24946) (PMID:34633425) (PMCID:PMC8506231)

2017

Malki, K. et al. (2017) Highly polygenic architecture of antidepressant treatment response: comparative analysis of SSRI and NRI treatment in an animal model of depression. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics, 174(3), pp. 235-250. (doi: 10.1002/ajmg.b.32494) (PMID:27696737) (PMCID:PMC5434854)

2016

Jiang, Y. et al. (2016) An expanded evaluation of protein function prediction methods shows an improvement in accuracy. Genome Biology, 17, 184. (doi: 10.1186/s13059-016-1037-6) (PMID:27604469) (PMCID:PMC5015320)

2015

Karr, J. R. et al. (2015) Summary of the DREAM8 parameter estimation challenge: toward parameter identification for whole-cell models. PLoS Computational Biology, 11(5), e1004096. (doi: 10.1371/journal.pcbi.1004096) (PMID:26020786) (PMCID:PMC4447414)

2013

Buchan, D. W.A., Minneci, F., Nugent, T. C.O., Bryson, K. and Jones, D. T. (2013) Scalable web services for the PSIPRED Protein Analysis Workbench. Nucleic Acids Research, 41(W1), W349-W357. (doi: 10.1093/nar/gkt381) (PMID:23748958) (PMCID:PMC3692098)

Radivojac, P. et al. (2013) A large-scale evaluation of computational protein function prediction. Nature Methods, 10(3), pp. 221-227. (doi: 10.1038/nmeth.2340) (PMID:23353650) (PMCID:PMC3584181)

Cozzetto, D., Buchan, D. W.A., Bryson, K. and Jones, D. T. (2013) Protein function prediction by massive integration of evolutionary analyses and multiple data sources. BMC Bioinformatics, 14(Sup 3), S1. (doi: 10.1186/1471-2105-14-S3-S1) (PMID:23514099) (PMCID:PMC3584902)

Medlar, A., Głowacka, D., Stanescu, H., Bryson, K. and Kleta, R. (2013) SwiftLink: parallel MCMC linkage analysis using multicore CPU and GPU. Bioinformatics, 29(4), pp. 413-419. (doi: 10.1093/bioinformatics/bts704) (PMID:23239673)

2012

Leung, M. H., Bryson, K. , Freystatter, K., Pichon, B., Edwards, G., Charalambous, B. M. and Gillespie, S. H. (2012) Sequetyping: serotyping Streptococcus pneumoniae by a single PCR sequencing strategy. Journal of Clinical Microbiology, 50(7), pp. 2419-2427. (doi: 10.1128/JCM.06384-11) (PMID:22553238) (PMCID:PMC3405617)

2010

Itan, Y., Bryson, K. and Thomas, M. G. (2010) Detecting gene duplications in the human lineage. Annals of Human Genetics, 74(6), pp. 555-565. (doi: 10.1111/j.1469-1809.2010.00609.x) (PMID:20946257)

Buchan, D.W.A., Ward, S.M., Lobley, A.E., Nugent, T.C.O., Bryson, K. and Jones, D.T. (2010) Protein annotation and modelling servers at University College London. Nucleic Acids Research, 38(Suppl2), W563-W568. (doi: 10.1093/nar/gkq427) (PMID:20507913) (PMCID:PMC2896093)

2008

Edwards, Y. J.K., Bryson, K. and Jones, D. T. (2008) A meta-analysis of microarray gene expression in mouse stem cells: redefining stemness. PLoS ONE, 3(7), e2712. (doi: 10.1371/journal.pone.0002712) (PMID:18628962) (PMCID:PMC2444034)

2007

Bryson, K. , Cozzetto, D. and Jones, D. T. (2007) Computer-assisted protein domain boundary prediction using the dom-pred server. Current Protein and Peptide Science, 8(2), pp. 181-188. (doi: 10.2174/138920307780363415) (PMID:17430199)

2006

Van De Guchte, M. et al. (2006) The complete genome sequence of Lactobacillus bulgaricus reveals extensive and ongoing reductive evolution. Proceedings of the National Academy of Sciences of the United States of America, 103(24), pp. 9274-9279. (doi: 10.1073/pnas.0603024103) (PMID:16754859) (PMCID:PMC1482600)

McGuffin, L. J., Smith, R. T., Bryson, K. , Sørensen, S.-A. and Jones, D. T. (2006) High throughput profile-profile based fold recognition for the entire human proteome. BMC Bioinformatics, 7, 288. (doi: 10.1186/1471-2105-7-288) (PMID:16759376) (PMCID:PMC1513610)

This list was generated on Sat Dec 3 23:13:59 2022 GMT.
Jump to: Articles | Conference Proceedings
Number of items: 17.

Articles

Viñas, R., Andrés-Terré, H., Liò, P. and Bryson, K. (2022) Adversarial generation of gene expression data. Bioinformatics, 38(3), pp. 730-737. (doi: 10.1093/bioinformatics/btab035) (PMID:33471074) (PMCID:PMC8756177)

Yan, Y. et al. (2021) A continuously benchmarked and crowdsourced challenge for rapid development and evaluation of models to predict COVID-19 diagnosis and hospitalization. JAMA Network Open, 4(10), e2124946. (doi: 10.1001/jamanetworkopen.2021.24946) (PMID:34633425) (PMCID:PMC8506231)

Malki, K. et al. (2017) Highly polygenic architecture of antidepressant treatment response: comparative analysis of SSRI and NRI treatment in an animal model of depression. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics, 174(3), pp. 235-250. (doi: 10.1002/ajmg.b.32494) (PMID:27696737) (PMCID:PMC5434854)

Jiang, Y. et al. (2016) An expanded evaluation of protein function prediction methods shows an improvement in accuracy. Genome Biology, 17, 184. (doi: 10.1186/s13059-016-1037-6) (PMID:27604469) (PMCID:PMC5015320)

Karr, J. R. et al. (2015) Summary of the DREAM8 parameter estimation challenge: toward parameter identification for whole-cell models. PLoS Computational Biology, 11(5), e1004096. (doi: 10.1371/journal.pcbi.1004096) (PMID:26020786) (PMCID:PMC4447414)

Buchan, D. W.A., Minneci, F., Nugent, T. C.O., Bryson, K. and Jones, D. T. (2013) Scalable web services for the PSIPRED Protein Analysis Workbench. Nucleic Acids Research, 41(W1), W349-W357. (doi: 10.1093/nar/gkt381) (PMID:23748958) (PMCID:PMC3692098)

Radivojac, P. et al. (2013) A large-scale evaluation of computational protein function prediction. Nature Methods, 10(3), pp. 221-227. (doi: 10.1038/nmeth.2340) (PMID:23353650) (PMCID:PMC3584181)

Cozzetto, D., Buchan, D. W.A., Bryson, K. and Jones, D. T. (2013) Protein function prediction by massive integration of evolutionary analyses and multiple data sources. BMC Bioinformatics, 14(Sup 3), S1. (doi: 10.1186/1471-2105-14-S3-S1) (PMID:23514099) (PMCID:PMC3584902)

Medlar, A., Głowacka, D., Stanescu, H., Bryson, K. and Kleta, R. (2013) SwiftLink: parallel MCMC linkage analysis using multicore CPU and GPU. Bioinformatics, 29(4), pp. 413-419. (doi: 10.1093/bioinformatics/bts704) (PMID:23239673)

Leung, M. H., Bryson, K. , Freystatter, K., Pichon, B., Edwards, G., Charalambous, B. M. and Gillespie, S. H. (2012) Sequetyping: serotyping Streptococcus pneumoniae by a single PCR sequencing strategy. Journal of Clinical Microbiology, 50(7), pp. 2419-2427. (doi: 10.1128/JCM.06384-11) (PMID:22553238) (PMCID:PMC3405617)

Itan, Y., Bryson, K. and Thomas, M. G. (2010) Detecting gene duplications in the human lineage. Annals of Human Genetics, 74(6), pp. 555-565. (doi: 10.1111/j.1469-1809.2010.00609.x) (PMID:20946257)

Buchan, D.W.A., Ward, S.M., Lobley, A.E., Nugent, T.C.O., Bryson, K. and Jones, D.T. (2010) Protein annotation and modelling servers at University College London. Nucleic Acids Research, 38(Suppl2), W563-W568. (doi: 10.1093/nar/gkq427) (PMID:20507913) (PMCID:PMC2896093)

Edwards, Y. J.K., Bryson, K. and Jones, D. T. (2008) A meta-analysis of microarray gene expression in mouse stem cells: redefining stemness. PLoS ONE, 3(7), e2712. (doi: 10.1371/journal.pone.0002712) (PMID:18628962) (PMCID:PMC2444034)

Bryson, K. , Cozzetto, D. and Jones, D. T. (2007) Computer-assisted protein domain boundary prediction using the dom-pred server. Current Protein and Peptide Science, 8(2), pp. 181-188. (doi: 10.2174/138920307780363415) (PMID:17430199)

Van De Guchte, M. et al. (2006) The complete genome sequence of Lactobacillus bulgaricus reveals extensive and ongoing reductive evolution. Proceedings of the National Academy of Sciences of the United States of America, 103(24), pp. 9274-9279. (doi: 10.1073/pnas.0603024103) (PMID:16754859) (PMCID:PMC1482600)

McGuffin, L. J., Smith, R. T., Bryson, K. , Sørensen, S.-A. and Jones, D. T. (2006) High throughput profile-profile based fold recognition for the entire human proteome. BMC Bioinformatics, 7, 288. (doi: 10.1186/1471-2105-7-288) (PMID:16759376) (PMCID:PMC1513610)

Conference Proceedings

Park, G. W. (W.) and Bryson, K. (2021) LDEncoder: Reference deep learning-based feature detector for transfer learning in the field of epigenomics. In: 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB '21), Gainesville, Florida, 1-4 August 2021, p. 58. ISBN 9781450384506 (doi: 10.1145/3459930.3469487)

This list was generated on Sat Dec 3 23:13:59 2022 GMT.

Teaching

Currently I'm the Director of the MSc in Data Science and also the MSc in Computer Science.

I currently teach the following courses:

  • COMPSCI5103 Deep Learning for MSc
  • COMPSCI4084 Programming and Development

Previously I have taught at Glasgow:

  • COMPSCI4039 Programming (IT)

Previously, at UCL, I was the Undergraduate Programme Director and also the Director of the MSc in Computer Science. I have taught in the past the following subjects:

  • BIOC0016 (3rd year Computational and Systems Biology within the Department of Structural and Molecular Biology, UCL)
  • COMP0008 (2nd year Computer Architecture and Concurrency)
  • COMP0082 (Bioinformatics module as part of the MSc in Machine Learning)
  • COMP1001 (1st year Computer Architecture) using assembly language programming to explain the underlying working of the MIPS processor (and processors in general).
  • COMP2007 (2nd year Networking and Concurrency) teaching Java Concurrent Programming and introduces the concepts of computer networking by developing concurrent Java simulators demonstrating the key principles.
  • COMP3006 (Advanced Mathematics) where I taught advanced linear algebra and vector calculus.
  • CPLXG001 (MRes Advanced Biological Modelling and Bioinformatics within CoMPLEX) teaching bioinformatics.
  • CPLXG003 (MRes Transferrable Skills Module within CoMPLEX) teaching the application of SQL relational databases within bioinformatics.
  • INFN3004 (MSc and Intercalating Medical BSc in Immunology and Cell Pathology and Infection) taught introductory bioinformatics to medical students.
  • WIBRG001 (MSc Drug Design within the Wolfson Institute of Medical Research) teaching introductory bioinformatics.

I was also an Honorary Teaching Fellow at Birkbeck College where I taught:

  • Birkbeck MSc in Bioinformatics and Systems Biology teaching biological networks and mathematical modelling.