Big insight from big data
Co-reporting with the PerCathe project.
Our work on drug synergy prediction has been particularly important in 2020. We developed Bayesian methods to estimate drug synergy in drug screening experiments, on the basis of heterogeneous types of data.
We are now able to estimate when two cancer drugs are more efficient in killing cancer cells than either drug on its own. We published three R-packages, because making software easily available to the public is essential for open science.
Our work is fully cross-disciplinary, merging the competence from statisticians, biologists, clinicians, bioinformaticians, molecular biologists, in our team.
Zhao Z, Zucknick M. Structured penalized regression for drug sensitivity prediction. Journal of the Royal Statistical Society, Series C. 2020;69(3):525-45.
- Zhao Z*, Banterle M*, Bottolo L, Richardson S, Lewin A, Zucknick M (2020). BayesSUR: Bayesian Seemingly Unrelated Regression. R package version 1.2-4. *joint first authors
- Rønneberg L, Cremaschi A, Zucknick M (2020). BayeSyneRgy: Bayesian semi-parametric modelling for in-vitro drug combination experiments. R package version 2.2, .
- Cremaschi A, Rønneberg L, Zucknick M (2020). synergysplines: A Bayesian approach for the study of synergistic interaction effects in in-vitro drug combination experiments. R package version 1.0
PhD candidates 2020
Zhi Zhao, UiO
Multivariate structured penalized and Bayesian regressions for pharmacogenomic screens (summary, full-text not available)
Dagim Shiferaw Tadele, UiO
Development of novel approaches for treatment of leukemia (summary, full-text not available)
Laure Piechaczyk, UiO
Identifying new avenues for leukemia treatment using genomewide CRISPR/Cas9 and ex vivo drug sensitivity screens (summary, full-text not available)
Aurelie Nguea, UiO
Nutrient stress responses in the budding yeast. Saccharomyces cerevisiae
Salim Ghannoum from Institute for Basic Medical Sciences, Torgeir Mo and Mariaserena Giliberto from the Institute for Cancer Research will defend their theses in 2021.
Scientific publications i2020: 18
The aim of the project is to develop statistical and machine learning methods in the health sector, among others. The research includes modelling of early development of cancer, personalised cancer therapy, analysis of health data from hospitals, as well as epidemiological predictions to improve public health.
Innovation: The researchers in BigInsight develop analytical tools to extract knowledge from large databases. 12 partners contribute to the project, both private and public enterprises.
BigInsight is a Centre for Research-based Innovation, funded by the Norwegian Research Council.