Revealing the Impact of Genomic Alterations on Cancer Cell Signaling with an Interpretable Deep Learning Model

Simple Summary Cancer results from aberrant cellular signaling caused by somatic genomic alterations (SGAs). However, inferring how SGAs cause aberrations in cellular signaling and lead to cancer remains challenging. We designed an interpretable deep learning model to encode the impact of SGAs on cellular signaling systems (represented by hidden nodes in the model) and eventually on tumor gene expression. The transparent deep learning architecture enabled the model to discover drivers affecting common signaling pathways and partially resolve the causal structure of signaling proteins. This is an early attempt to use transparent deep learning model, in contrast to conventional black box approach, to learn interpretable insights into cancer cell signaling systems. A better representation of signaling system of a cancer cell sheds light on the disease mechanisms of the cancer and can guide precision medicine. Cancer is a disease of aberrant cellular signaling resulting from somatic genomic alterations (SGAs). Heterogeneous SGA events in tumors lead to tumor-specific signaling system aberrations. We interpret the cancer signaling system as a causal graphical model, where SGAs affect signaling proteins, propagate their effects through signal transduction, and ultimately change gene expression. To represent such a system, we developed a deep learning model called redundant-input neural network (RINN) with a transparent redundant-input architecture. Our findings demonstrate that by utilizing SGAs as inputs, the RINN can encode their impact on the signaling system and predict gene expression accurately when measured as the area under ROC curves. Moreover, the RINN can discover the shared functional impact (similar embeddings) of SGAs that perturb a common signaling pathway (e.g., PI3K, Nrf2, and TGF). Furthermore, the RINN exhibits the ability to discover known relationships in cellular signaling systems.

Automated summary

By designing an interpretable deep learning model, we were able to encode the impact of SGAs on cellular signaling systems and tumor gene expression, uncover drivers affecting common signaling pathways, and partially resolve the causal structure of signaling proteins. This early attempt to use a transparent deep learning model provides interpretable insights into cancer cell signaling systems, shedding light on disease mechanisms and guiding precision medicine.