Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen

By Michael P. Menden, Dennis Wang, Mike J Mason, B. Szalai, Krishna Chaitanya Bulusu, Yuanfang Guan, Thomas Yu, Jaewoo Kang, Minji Jeon, Russell D. Wolfinger and 16 more. Nature Communications, 2019

299 citations recorded by the source corpus.

The effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca’s large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60% of combinations. However, 20% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells. Resistance to first line treatment is a major hurdle in cancer treatment, that can be overcome with drug combinations. Here, the authors provide a large drug combination screen across cancer cell lines to benchmark crowdsourced methods and to computationally predict drug synergies.

Subfields: Computational Theory and Mathematics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/0babdc5493acddb6091a2c52b73fd07c66b6c1d6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

Predicting cellular responses to complex perturbations in high‐throughput screens (2023, background): “Combinatorial drug therapies are hypothesized to address the limited effectiveness of mono-therapies (Menden et al , 2019) and prevent drug resistance in cancer therapies (Jia et al , 2009; Menden et al , 2019; Adam et al , 2020).”
A review on machine learning approaches and trends in drug discovery (2021, methodology): “…AstraZeneca of 910 drug combinations on 85 molecularly characterised cancer cell lines (expression, copy number variation, methylation, mutations) [140], 160 international teams try to predict the best synergies between drug pairs and biomarkers for which different approaches were used: SVM, MKL,…”
Artificial Intelligence in Cancer Research and Precision Medicine (2021, background): “With more than 80 distinct models submitted, they found that those that integrated genomic features with other information (such as a chemical structure or known biological interactions) tended to produce higher overall accuracies (120).”