Abstract
In order to improve anti-cancer treatment, we need to better understand why some patients respond to a given anti-cancer treatment, while others do not. To this end, several large-scale drug response screens have been performed in recent years, in which hundreds of tumor cell lines have been characterized formany molecular features (e.g. mutations, CNAs, methylation and gene expression), as well as for response to hundreds of anti-cancer drugs. By statistically associating these molecular features with the drug response, we can identify biomarkers of drug response: markers that (after thorough testing) can ultimately be used to help identify which treatment should be given to which patient.
While performing such statistical analyses, we found that there are strong relationships between the different molecular datasets (e.g. mutations, CNAs, methylation and gene expression) and that these relationships can negatively affect our ability to identify biomarkers. Following these results, we have developed TANDEM, a method to identify biomarkers while taking into account these relationships between datasets, and iTOP, a method to infer how different datasets are related to each other.
For difficult cases where the number of cell lines is very small, we have developed a method that predicts drug response simultaneously for all drugs in the screen, thereby gaining statistical power. We based this method on a machine learning methodology called multi-task learning. In contrast to other multi-task learning methods, our approach provides insight into which features are important for a given treatment, thereby allowing us to identify biomarkers fromthese models.
Finally, we analyzed a screen of 54 drug combinations across 765 cell lines. We report which combinations show synergy (i.e. where the effect of the combination was larger than onewould expect based on the individual drug effects) most frequently, hence making them broadly applicable. In addition, for each drug combination, we statistically associated molecular features (i.e. mutations, copy number aberrations, gene expression and proteomics) with the synergy, from which the strongest associations may be good candidate biomarkers.
While performing such statistical analyses, we found that there are strong relationships between the different molecular datasets (e.g. mutations, CNAs, methylation and gene expression) and that these relationships can negatively affect our ability to identify biomarkers. Following these results, we have developed TANDEM, a method to identify biomarkers while taking into account these relationships between datasets, and iTOP, a method to infer how different datasets are related to each other.
For difficult cases where the number of cell lines is very small, we have developed a method that predicts drug response simultaneously for all drugs in the screen, thereby gaining statistical power. We based this method on a machine learning methodology called multi-task learning. In contrast to other multi-task learning methods, our approach provides insight into which features are important for a given treatment, thereby allowing us to identify biomarkers fromthese models.
Finally, we analyzed a screen of 54 drug combinations across 765 cell lines. We report which combinations show synergy (i.e. where the effect of the combination was larger than onewould expect based on the individual drug effects) most frequently, hence making them broadly applicable. In addition, for each drug combination, we statistically associated molecular features (i.e. mutations, copy number aberrations, gene expression and proteomics) with the synergy, from which the strongest associations may be good candidate biomarkers.
| Original language | English |
|---|---|
| Awarding Institution |
|
| Supervisors/Advisors |
|
| Award date | 31 Oct 2019 |
| DOIs | |
| Publication status | Published - 2019 |
