A data-driven interactome of synergistic genes improves network-based cancer outcome prediction

Robustly predicting outcome for cancer patients from gene expression is an important challenge on the road to better personalized treatment. Network-based outcome predictors (NOPs), which considers the cellular wiring diagram in the classification, hold much promise to improve performance, stability and interpretability of identified marker genes. Problematically, reports on the efficacy of NOPs are conflicting and for instance suggest that utilizing random networks performs on par to networks that describe biologically relevant interactions. In this paper we turn the prediction problem around: instead of using a given biological network in the NOP, we aim to identify the network of genes that truly improves outcome prediction. To this end, we propose SyNet, a gene network constructed ab initio from synergistic gene pairs derived from survival-labelled gene expression data. To obtain SyNet, we evaluate synergy for all 69 million pairwise combinations of genes resulting in a network that is specific to the dataset and phenotype under study and can be used to in a NOP model. We evaluated SyNet and 11 other networks on a compendium dataset of >4000 survival-labelled breast cancer samples. For this purpose, we used cross-study validation which more closely emulates real world application of these outcome predictors. We find that SyNet is the only network that truly improves performance, stability and interpretability in several existing NOPs. We show that SyNet overlaps significantly with existing gene networks, and can be confidently predicted (~85% AUC) from graph-topological descriptions of these networks, in particular the breast tissue-specific network. Due to its data-driven nature, SyNet is not biased to well-studied genes and thus facilitates post-hoc interpretation. We find that SyNet is highly enriched for known breast cancer genes and genes related to e.g. histological grade and tamoxifen resistance, suggestive of a role in determining breast cancer outcome.Author summary: Cancer is caused by disrupted activity of several pathways. Therefore, to predict cancer patient prognosis from gene expression profiles, it may be beneficial to consider the cellular interactome (e.g. the protein interaction network). These so-called Network based Outcome Predictors (NOPs) hold the potential to facilitate identification of dysregulated pathways and delivering improved prognosis. Nonetheless, recent studies revealed that compared to classical models, neither performance nor consistency (in terms of identified markers across independent studies) can be improved using NOPs. In this work, we argue that NOPs can only perform well when supplied with suitable networks. The commonly used networks may miss associations specially for under-studied genes. Additionally, these networks are often generic with low coverage of perturbations that arise in cancer. To address this issue, we exploit ~4100 samples and infer a disease-specific network called SyNet linking synergistic gene pairs that collectively show predictivity beyond the individual performance of genes. Using a thorough cross-validation, we show that a NOP yields superior performance and that this performance gain is the result of the wiring of genes in SyNet. Due to simplicity of our approach, this framework can be used for any phenotype of interest. Our findings confirm the value of network-based models and the crucial role of the interactome in improving outcome prediction.