Reader for Molecular Informatics
Associate Director Computational ADME and Safety (Clinical Pharmacology & Safety Sciences/Data Science and Artificial Intelligence - CPSS/DSAI) at AstraZeneca Cambridge
Co-founder of Healx Ltd.
Co-founder of PharmEnable Ltd.
- Committed to developing new life science data analysis methods (AI/ML/data science) and their application, primarily related to chemical biology, drug discovery and in silico toxicology
- Expertise comprises data ranging from chemical structure and gene expression data to phenotypic readouts and preclinical information, applied to both efficacy- and safety/tox-related questions
- Collaborating with academic research groups, as well as pharmaceutical, chemical, and consumer goods companies (Eli Lilly, AstraZeneca, GSK, BASF, Johnson&Johnson/Janssen, Unilever, ...)
- Co-founder/founding CTO and current SAB member of Healx Ltd. (data-driven drug repurposing for rare diseases, and beyond); co-founder of PharmEnable Ltd.; SAB member of Lhasa Ltd. (toxicology and metabolism prediction) and Cresset Ltd.
- Coordinator of the Computational & In Silico Toxicology Specialty Section of the British Toxicology Society (BTS)
- Steering Committee Member of the Cambridge Alliance on Medicines Safety (CAMS)
- Currently leading a group of ca. 15 PhD students, postdocs, project students and visitors at the Centre for Molecular Informatics at the University of Cambridge, https://www-cmi.ch.cam.ac.uk/centre-molecular-informatics
Publications
Understanding Conditional Associations between ToxCast in Vitro Readouts and the Hepatotoxicity of Compounds Using Rule-Based Methods.
– Chem Res Toxicol
(2020)
33,
137
Leveraging heterogeneous data from GHS toxicity annotations, molecular and protein target descriptors and Tox21 assay readouts to predict and rationalise acute toxicity
– J Cheminform
(2019)
11,
36
(DOI: 10.1186/s13321-019-0356-5)
Applying synergy metrics to combination screening data: agreements, disagreements and pitfalls.
– Drug Discov Today
(2019)
24,
2286
(DOI: 10.1016/j.drudis.2019.09.002)
Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account
– Current protocols in chemical biology
(2019)
11,
e73
(DOI: 10.1002/cpch.73)
Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout.
– Journal of Chemical Information and Modeling
(2019)
59,
3330
(DOI: 10.1021/acs.jcim.9b00297)
Triazole-Pyridine Dicarbonitrile Targets Phosphodiesterase 4 to Induce Anticancer Activity in Lung Carcinoma Cells.
– Chemistry & Biodiversity
(2019)
16,
e1900234
(DOI: 10.1002/cbdv.201900234)
KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images.
– Journal of cheminformatics
(2019)
11,
41
(DOI: 10.1186/s13321-019-0364-5)
KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images.
– J Cheminform
(2019)
11,
41
(DOI: 10.1186/s13321-019-0364-5)
Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen.
– Nature Communications
(2019)
10,
2674
(DOI: 10.1038/s41467-019-09799-2)
Synthesis of C C, C N coupled novel substituted dibutyl benzothiazepinone derivatives and evaluation of their thrombin inhibitory activity
– Bioorg Chem
(2019)
87,
142
(DOI: 10.1016/j.bioorg.2019.03.004)
- 1 of 31