Dr Alastair Droop
- Position: UKRI Rutherford Research Fellow
- Areas of expertise: bioinformatics; computational biology; machine learning; neural networks; transcriptomics; NGS
- Email: A.P.Droop@leeds.ac.uk
- Location: Worsley Building
I have a Masters by research in Bioinformatics and a PhD in computational biology from the University of York. My PhD thesis focused on the application of large transcriptomics datasets to oil yield maximisation in Arabidopsis seeds using multivariate correlation analyses. Although my background is in molecular biology, I have extensive experience in computer science and computational biology, gained during my role as a bioinformatician in the Leeds CRUK Centre.
My previous role as the Leeds CRUK Centre bioinformatician required me to work on multiple projects simultaneously for multiple research groups.
My current role as UKRI Rutherford Research Fellow in LIDA has allowed me to move away from my previous, service-focussed position and to develop my own research within Leeds in the areas of computational biology and machine learning.
Machine Learning (ML) and Artificial Intelligence (AI) are exciting developments in large data analysis. Deep learning is a set of techniques in ML which use layered neural networks to learn structure and patterns in complex data. These techniques are particularly suited to analysis problems where we do not know the exact structure of the data de novo, and thus have to infer the interesting features from the data. This ability to learn complex problems makes deep learning a good conceptual fit to modern biology and healthcare challenges. As neural networks learn structure from data during a training phase, the quality of the result is heavily reliant on the quality of its training data. As with any ML task, there is a constant danger of overfitting, in which specific (and often irrelevant) features of the training set are learned as discriminatory. Overfitting is especially problematic when the training data are too small, or non-representative of the real-world problem we are attempting to address.
My research aims to advance our ability to apply ML techniques (especially Deep Neural Networks) to large-scale complex patient data, specifically my research aims are:
- to build novel software to integrate domain knowledge into ML (using the Tensorflow framework) using publicly-available data. This involves both biologically-informed data embedding and the development of biologically appropriate network topologies;
- to develop tools and techniques for supervised data preprocessing for use with SystmOne patient data; and
- in collaboration with clinicians in the Leeds Teaching Hospital, to explore the utility of DNNs in multiple large patient datasets.
- PhD Computational Biology
- MRes Bioinformatics
- BSc with Honours Molecular Biology