Technologies for doctors to make better decisions faster
Leveraging theory, computation and experiments, my group and I are creating novel measurement and prediction systems for integrated cancer biology. We work in translational projects on three frontiers:
![]() |
![]() |
![]() |
Tumour evolution | Tissue context | Interaction networks |
(1) Revealing the mutational processes acting on cancer genomes, measuring their impact on patient phenotypes, and using them for personalised therapy decisions; |
(2) Improved patient stratification, early detection, and prognosis by predictive modelling of tumour imaging and genomics data; |
(3) Predicting strategies to overcome resistance and reduce toxicity by comparative network analysis of transcriptional responses to combinatorial CRISPR perturbations in single cells. |
Publications
- Gehrung et al (2021), Triage-driven diagnosis of Barrett esophagus for early detection of esophageal adenocarcinoma using deep learning, Nature Medicine
- Crispin-Ortuzar et al (2020), Three-Dimensional Printed Molds for image-guided surgical biopsies: an open source computational platform, JCO CCI
- Cmero et al (2020), SVclone: inferring structural variant cancer cell fraction, Nature Comms
Software
- PathML - A Python library for deep learning on whole-slide images
- OncoNEM - Clonal evolution trees from single cell data
- Bitphylogeny - Bayesian framework for intra-tumour phylogenies
- MEDICC - intra-tumor copy-number comparisons
- nem - inferring Nested Effects Models from downstream perturbation effects