Dylan Adlard
DPhil student
Reproducible AMR catalogues and predictions for Tb diagnostics
I am a DPhil student under the supervision of Philip Fowler and David Eyre, working within the Modernising Medical Microbiology group. My research focuses on developing statistical methods to classify antimicrobial resistance (AMR) variants in Mycobacterium tuberculosis, with the goal of building reproducible catalogues that inform drug susceptibility profiles within a diagnostic framework. I also design inferential models trained on structural and physicochemical data of drug targets, allowing susceptibility predictions to extend to novel or unseen mutations. A key aspect of my work is ensuring full reproducibility and implementing sustainable, full-stack software development practices.
Recent publications
Predicting pyrazinamide resistance in Mycobacterium tuberculosis using a graph convolutional network
Journal article
Dissanayake D. et al, (2026), BMC Microbiology
Predicting pyrazinamide resistance in Mycobacterium tuberculosis using a graph convolutional network
Preprint
Dissanayake D. et al, (2025)
Rapidly and reproducibly building a comprehensive catalogue of resistance-associated variants for M. tuberculosis
Preprint
Adlard D. et al, (2025)
An improved catalogue for whole-genome sequencing prediction of bedaquiline resistance in Mycobacterium tuberculosis using a reproducible algorithmic approach
Journal article
Adlard D. et al, (2025), Microbial Genomics, 11
Predicting rifampicin resistance in Mycobacterium tuberculosis using machine learning informed by protein structural and chemical features
Journal article
Lynch CI. et al, (2025), ERJ Open Research, 11, 00952 - 2024
