Dr Colin Mclean

Senior Research Fellow in Data Science and Health Economics

Biography

Background

Currently employed by the CRUK Scotland Centre as a senior data scientist. Dr Colin Mclean holds a PhD in Experimental Particle Physics, where his research focused on designing statistical code to model and analysis the particle physics decay Bs->J/psiphi, at the LHCb experiment (CERN). His work contributed towards the measurement of the CKM angle betas.  


He has over 10 years research experience in biomedicine collaborating on large international science projects including the Human Brain Project (HBP). Whilst on the HBP he helped create a data resource to build configurable models of the synaptic proteome. He has developed machine learning algorithms to infer community structure in, and propagate disease information through, biomolecular networks. He is coauthor of the R package BioNAR: a network analysis package for biomedical practitioners.


 Dr Mclean has published papers in the field of medical physics, particle physics, synaptic proteomics and network science. He is on the supervisory teams for clinical and non-clinical PhD students. He has supervised MSc informatics students, and tutored undergraduate students in experimental, mathematical and computational physics.

CV

PDF icon 156416.pdf

Qualifications

PhD, BSc

Undergraduate teaching

MSc supervision

Postgraduate teaching

I sit on panels for clinical & non-clinical PhD students 

Open to PhD supervision enquiries?

Yes

Areas of interest for supervision

PhD projects involved in multi-modal or causal machine learning algorithm development and analysis applied to real-world healthcare data

Current PhD students supervised

Begoña Bolos, PhD in Cancer Informatics, Multimodal deep learning models to predict recurrence in Scottish colorectal cancer cohort, supervisor.

Past PhD students supervised

Marnane, Aidan, PhD in Informatics,  20/11/19 to 9/08/21, Supervisor 30.00%. Grant Robertson, PhD in Informatics, Network analysis of the Post Synaptic proteome and its implication for cognition, 15/12/2022, mentoring and support from 2014-2020. Provided the implementation of spectral community detection used in this thesis and carried out the community detection. 

Research summary

Application of machine learning and causal methodology to real-world healthcare and genomics data. 
Evidence based training and career policies to aid early career data scientists in biomedicine.

Current research interests

Developing machine models applied to clinical and genomics cancer data in collaboration with molecular pathologists from the University of Glasgow. Real-world data studies using NHS Lothian oncology data mapped to the OMOP Common Data Model (CDM). Data linkage of national cancer datasets for the PHS. 

Past research interests

Modelling of synaptic mammalian proteomic data for the EU projects: EuroSpin, SynSys, and Human Brian Project. Implementing and developing (un)supervised machine learning algorithms from network science, to find underlying community structure in Protein-Protein Interaction networks. Analysis of the SAFARI SPARK ASD patient datasets, building of patients networks and use of graphical databases to store patient data. Analysis of LHC data from the CERN LHCb experiment. Analysis of the clinical laser systems and medical attachments for the cancer treatment Photodynamic Therapy.

Knowledge exchange

I am community lead for CRUK on data science education and training: engaging with cancer and data science communities to develop polices for early career researchers.

Project activity

CRUK Data Research Strategy: co-developing postgraduate career scheme for data scientists 

This article was published on