Search

This Perspective explores the application of machine learning toward improved diagnosis and treatment. We outline a vision for how machine learning can transform three broad areas of biomedicine: clinical diagnostics, precision treatments, and health monitoring, where the goal is to maintain health through a range of diseases and the normal aging process. For each area, early instances of successful machine learning applications are discussed, as well as opportunities and challenges for machine learning. When these challenges are met, machine learning promises a future of rigorous, outcomes-based medicine with detection, diagnosis, and treatment strategies that are continuously adapted to individual and environmental differences.

The recent wide-spread adoption of single-cell profiling technologies has revealed that individual cancers are not homogenous collections of deregulated cells, but instead comprise multiple genetically and phenotypically distinct cell subpopulations that exhibit a wide range of responses to extracellular signals and therapeutic insult. Such observations point to the urgent need to understand cancer as a complex, adaptive system. Cancer systems biology studies seek to develop the experimental and theoretical methods required to understand how biological components work together to determine how cancer cells function. Ultimately, such approaches will lead to improvements in how cancer is managed and treated. In this review, we discuss recent advances in cancer systems biology approaches to quantify, model, and elucidate mechanisms of heterogeneity.

Mechanisms of therapeutic resistance and vulnerability evolve in metastatic cancers as tumor cells and extrinsic microenvironmental influences change during treatment. To support the development of methods for identifying these mechanisms in individual people, here we present an omic and multidimensional spatial (OMS) atlas generated from four serial biopsies of an individual with metastatic breast cancer during 3.5 years of therapy. This resource links detailed, longitudinal clinical metadata that includes treatment times and doses, anatomic imaging, and blood-based response measurements to clinical and exploratory analyses, which includes comprehensive DNA, RNA, and protein profiles; images of multiplexed immunostaining; and 2- and 3-dimensional scanning electron micrographs. These data report aspects of heterogeneity and evolution of the cancer genome, signaling pathways, immune microenvironment, cellular composition and organization, and ultrastructure. We present illustrative examples of how integrative analyses of these data reveal potential mechanisms of response and resistance and suggest novel therapeutic vulnerabilities.

The Library of Integrated Network-Based Cellular Signatures (LINCS) is an NIH Common Fund program that catalogs how human cells globally respond to chemical, genetic, and disease perturbations. Resources generated by LINCS include experimental and computational methods, visualization tools, molecular and imaging data, and signatures. By assembling an integrated picture of the range of responses of human cells exposed to many perturbations, the LINCS program aims to better understand human disease and to advance the development of new therapies. Perturbations under study include drugs, genetic perturbations, tissue micro-environments, antibodies, and disease-causing mutations. Responses to perturbations are measured by transcript profiling, mass spectrometry, cell imaging, and biochemical methods, among other assays. The LINCS program focuses on cellular physiology shared among tissues and cell types relevant to an array of diseases, including cancer, heart disease, and neurodegenerative disorders. This Perspective describes LINCS technologies, datasets, tools, and approaches to data accessibility and reusability.

SUMMARY Extrinsic signals are implicated in breast cancer resistance to HER2-targeted tyrosine kinase inhibitors (TKIs). To examine how microenvironmental signals influence resistance, we monitored TKI-treated breast cancer cell lines grown on microenvironment microarrays composed of printed extracellular matrix proteins supplemented with soluble proteins. We tested ~2,500 combinations of 56 soluble and 46 matrix microenvironmental proteins on basal-like HER2+ (HER2E) or luminal-like HER2+ (L-HER2+) cells treated with the TKIs lapatinib or neratinib. In HER2E cells, hepatocyte growth factor, a ligand for MET, induced resistance that could be reversed with crizotinib, an inhibitor of MET. In L-HER2+ cells, neuregulin1-β1 (NRG1β), a ligand for HER3, induced resistance that could be reversed with pertuzumab, an inhibitor of HER2-HER3 heterodimerization. The subtype-specific responses were also observed in 3D cultures and murine xenografts. These results, along with bioinformatic pathway analysis and siRNA knockdown experiments, suggest different mechanisms of resistance specific to each HER2+ subtype: MET signaling for HER2E and HER2-HER3 heterodimerization for L-HER2+ cells., In Brief We describe a powerful platform for discovery of microenvironment signals that influence drug responses. We show through application of the platform to HER2+ breast cancer cell lines that NRG1β and HGF suppress responses to lapatinib and neratinib in L-HER2+ and HER2E cells, respectively. We show that these differences are caused by differences in epigenomic status and regulatory pathway use between L-HER2+ and HER2E breast cancers. We also present evidence suggesting that microenvironment-mediated resistance to HER2-targeted tyrosine kinase inhibitors can be overcome in L-HER2+ cancers by co-treatment with pertuzumab, and in HER2E cancers by co-treatment with crizotinib or trametinib.

Summary Signaling networks downstream of receptor tyrosine kinases are among the most extensively studied biological networks, but new approaches are needed to elucidate causal relationships between network components and understand how such relationships are influenced by biological context and disease. Here, we investigate the context specificity of signaling networks within a causal conceptual framework using reverse-phase protein array time-course assays and network analysis approaches. We focus on a well-defined set of signaling proteins profiled under inhibition with five kinase inhibitors in 32 contexts: four breast cancer cell lines (MCF7, UACC812, BT20, and BT549) under eight stimulus conditions. The data, spanning multiple pathways and comprising ∼70,000 phosphoprotein and ∼260,000 protein measurements, provide a wealth of testable, context-specific hypotheses, several of which we experimentally validate. Furthermore, the data provide a unique resource for computational methods development, permitting empirical assessment of causal network learning in a complex, mammalian setting., Graphical Abstract, Highlights Time-course assays of signaling proteins in cancer cell lines under kinase inhibition Causal conceptual framework for network analysis Data shed light on causal protein networks that are specific to biological context Resource for signaling biology and for benchmarking computational methods, Time-course assays under kinase inhibition are used to investigate protein signaling networks in cancer cell lines within a causal conceptual framework. This reveals that patterns of causal influence between signaling proteins depend on the biological context. The data provide a resource for signaling biology and computational methods development.