Deciphering the signaling network of breast cancer improves drug sensitivity prediction

Transfer learning (TL) algorithms aim to improve the prediction performance in a target task (e.g. the prediction of cisplatin sensitivity in triple-negative breast cancer patients) via transferring knowledge from auxiliary data of a related task (e.g. the prediction of docetaxel sensitivity in breast cancer patients), where the distribution and even the feature space of the data pertaining to the tasks can be different. In real-world applications, we sometimes have a limited training set in a target task while we have auxiliary data from a related task. To obtain a better prediction performance in the target task, supervised learning requires a sufficiently large training set in the target task to perform well in predicting future test examples of the target task. In this paper, we propose a TL approach for cancer drug sensitivity prediction, where our approach combines three techniques. First, we shift the representation of a subset of examples from auxiliary data of a related task to a representation closer to a target training set of a target task. Second, we align the shifted representation of the selected examples of the auxiliary data to the target training set to obtain examples with representation aligned to the target training set. Third, we train machine learning algorithms using both the target training set and the aligned examples. We evaluate the performance of our approach against baseline approaches using the Area Under the receiver operating characteristic (ROC) Curve (AUC) on real clinical trial datasets pertaining to multiple myeloma, nonsmall cell lung cancer, triple-negative breast cancer, and breast cancer. Experimental results show that our approach is better than the baseline approaches in terms of performance and statistical significance.

Download Full-text

Deciphering the Signaling Network Landscape of Breast Cancer Improves Drug Sensitivity Prediction

10.1101/2020.01.21.907691 ◽

2020 ◽

Cited By ~ 1

Author(s):

Marco Tognetti ◽

Attila Gabor ◽

Mi Yang ◽

Valentina Cappelletti ◽

Jonas Windhager ◽

...

Keyword(s):

Breast Cancer ◽

Single Cell ◽

Breast Cancer Cell ◽

Drug Sensitivity ◽

Kinase Inhibitors ◽

Network Models ◽

Signaling Network ◽

Breast Cancer Cell Lines ◽

Mass Cytometry ◽

Genomic Features

ABSTRACTAlthough genetic and epigenetic abnormalities in breast cancer have been extensively studied, it remains difficult to identify those patients who will respond to particular therapies. This is due in part to our lack of understanding of how the variability of cellular signaling affects drug sensitivity. Here, we used mass cytometry to characterize the single-cell signaling landscapes of 62 breast cancer cell lines and five lines from healthy tissue. We quantified 34 markers in each cell line upon stimulation by the growth factor EGF in the presence or absence of five kinase inhibitors. These data – on more than 80 million single cells from 4,000 conditions – were used to fit mechanistic signaling network models that provide unprecedented insights into the biological principles of how cancer cells process information. Our dynamic single-cell-based models more accurately predicted drug sensitivity than static bulk measurements for drugs targeting the PI3K-MTOR signaling pathway. Finally, we identified genomic features associated with drug sensitivity by using signaling phenotypes as proxies, including a missense mutation in DDIT3 predictive of PI3K-inhibition sensitivity. This provides proof of principle that single-cell measurements and modeling could inform matching of patients with appropriate treatments in the future.One-linerSingle-cell proteomics coupled to perturbations improves accuracy of breast tumor drug sensitivity predictions and reveals mechanisms of sensitivity and resistance.HIGHLIGHTSMass cytometry study of signaling responses of 62 breast cancer cell lines and five lines from healthy tissue to EGF stimulation with or without perturbation with five kinase inhibitors.Single-cell signaling features and mechanistic signaling network models predicted drug sensitivity.Mechanistic signaling network models deepen the understanding of drug resistance and sensitivity mechanisms.We identify drug sensitivity-predictive genomic features via proxy signaling phenotypes.

Download Full-text