Lewis Mervin

AstraZeneca (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

20h-index1.6kcitations73works14.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Computational Drug Discovery Methods(45), Machine Learning in Materials Science(15), Cell Image Analysis Techniques(9), Protein Structure and Dynamics(8), Biosimilars and Bioanalytical Methods(5)

Publications71 total

Temporal distribution shift in real-world pharmaceutical data: Implications for uncertainty quantification in QSAR models
Artificial Intelligence in the Life Sciences·2025· 2 citedOpen Access
Publishing neural networks in drug discovery might compromise training data privacy
Journal of Cheminformatics·2025· 1 citedOpen Access
Achieving well-informed decision-making in drug discovery: a comprehensive calibration study using neural network-based structure-activity models
Journal of Cheminformatics·2025· 2 citedOpen Access
Enhancing uncertainty quantification in drug discovery with censored regression labels
Artificial Intelligence in the Life Sciences·2025· 4 citedOpen Access
Temporal Distribution Shift in Real-World Pharmaceutical Data: Implications for Uncertainty Quantification in QSAR Models
arXiv (Cornell University)·2025Open Access
Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy
arXiv (Cornell University)·2024Open Access
Registries in Machine Learning-Based Drug Discovery: A Shortcut to Code Reuse
Lecture notes in computer science·2024Open Access
Temporal Evaluation of Probability Calibration with Experimental Errors
Lecture notes in computer science·2024· 1 citedOpen Access
Temporal Evaluation of Uncertainty Quantification Under Distribution Shift
Lecture notes in computer science·2024· 1 citedOpen Access
Enhancing Uncertainty Quantification in Drug Discovery with Censored Regression Labels
arXiv (Cornell University)·2024Open Access
Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Models
arXiv (Cornell University)·2024Open Access
QSARtuna: An Automated QSAR Modeling Platform for Molecular Property Prediction in Drug Design
Journal of Chemical Information and Modeling·2024· 19 cited
QSARtuna: an automated QSAR modelling platform for molecular property prediction in drug design
2024· 2 citedOpen Access
Reinvent 4: Modern AI–driven generative molecule design
Journal of Cheminformatics·2024· 186 citedOpen Access
Qptuna: an automated QSAR modelling platform for molecular property prediction in drug design
2024· 3 citedOpen Access
REINVENT4: Modern AI–Driven Generative Molecule Design
2023· 24 citedOpen Access
Data‐driven approaches for identifying hyperparameters in multi‐step retrosynthesis
Molecular Informatics·2023· 10 citedOpen Access
MELLODDY: Cross-pharma Federated Learning at Unprecedented Scale Unlocks Benefits in QSAR without Compromising Proprietary Information
Journal of Chemical Information and Modeling·2023· 94 citedOpen Access
Industry-Scale Orchestrated Federated Learning for Drug Discovery
Proceedings of the AAAI Conference on Artificial Intelligence·2023· 37 citedOpen Access
Optimizing the Cell Painting assay for image-based profiling
Nature Protocols·2023· 144 cited
page 1 of 4Next →

Frequent Co-authors

Ola Engkvist(31), Andreas Bender(24), Avid M. Afzal(13), Noé Sturm(9), Ian P. Barrett(9), Maria‐Anna Trapotsi(8), Hugo Ceulemans(7), Ádám Arany(7), Lukas Friedrich(6), Adam Zalewski(6), Martijn Oldenhof(6), Peter Schmidtke(6), Jaak Simm(6), Yves Moreau(6), Alexey Voronov(5), Elizabeth Mouchet(5), Tiziana Monteverde(5), Guy Williams(5), Wouter Heyndrickx(5), Ansgar Schuffenhauer(5)