PT  - JOURNAL ARTICLE
AU  - Joshua M. Dempster
AU  - John Krill-Burger
AU  - Allison Warren
AU  - James M. McFarland
AU  - Todd R. Golub
AU  - Aviad Tsherniak
TI  - Gene expression has more power for predicting <em>in vitro</em> cancer cell vulnerabilities than genomics
AID  - 10.1101/2020.02.21.959627
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2020.02.21.959627
4099  - http://biorxiv.org/content/early/2020/02/24/2020.02.21.959627.short
4100  - http://biorxiv.org/content/early/2020/02/24/2020.02.21.959627.full
AB  - Achieving precision oncology requires accurate identification of targetable cancer vulnerabilities in patients. Generally, genomic features are regarded as the state-of-the-art method for stratifying patients for targeted therapies. In this work, we conduct the first rigorous comparison of DNA- and expression-based predictive models for viability across five datasets encompassing chemical and genetic perturbations. We find that expression consistently outperforms DNA for predicting vulnerabilities, including many currently stratified by canonical DNA markers. Contrary to their perception in the literature, the most successful expression-based models depend on few features and are amenable to biological interpretation. This work points to the importance of exploring more comprehensive expression profiling in clinical settings.