No abstract

Tumor relapse after chemotherapy is a major hurdle for successful cancer therapy. Chemotherapeutic drugs select for resistant tumor cells and reshape tumor microenvironment, including the blood supply system. Using animal models, we observed on macrophages in tumor tissue a close correlation between upregulated Tie2 expression and tumor relapse upon chemotherapy.

Different aspects of a clinical sample can be revealed by multiple types of omics data. Integrated analysis of multiomics data provides a comprehensive view of patients, which has the potential to facilitate more accurate clinical decision making. However, omics data are normally high dimensional with large number of molecular features and relatively small number of available samples with clinical labels. The "dimensionality curse" makes it challenging to train a machine learning model using high dimensional omics data like DNA methylation and gene expression profiles. Here we propose an end-to-end deep learning model called OmiVAE to extract low dimensional features and classify samples from multi-omics data. OmiVAE combines the basic structure of variational autoencoders with a classification network to achieve task-oriented feature extraction and multi-class classification. The training procedure of OmiVAE is comprised of an unsupervised phase without the classifier and a supervised phase with the classifier. During the unsupervised phase, a hierarchical cluster structure of samples can be automatically formed without the need for labels. And in the supervised phase, OmiVAE achieved an average classification accuracy of 97.49% after 10-fold cross-validation among 33 tumour types and normal samples, which shows better performance than other existing methods. The OmiVAE model learned from multi-omics data outperformed that using only one type of omics data, which indicates that the complementary information from different omics datatypes provides useful insights for biomedical tasks like cancer classification.

Myeloid-derived suppressor cells (MDSCs) often expand during cancer or chronic inflammation and dampen immune responses. However, mechanisms underlying their capacity to escape intrinsic apoptosis in the inflammatory environment are still largely unknown. In this study, we investigated this in mouse tumor models with MDSC accumulation. Spontaneous rejection of tumors implanted into mice deficient for the small Ca2+-binding protein S100A4 (S100A4−/−) was accompanied by low numbers of peripheral MDSCs. This was independent of S100A4 expression on tumor cells. In contrast, MDSCs from S100A4−/− tumor-bearing mice showed a diminished resistance to the induction of intrinsic apoptosis. Further studies demonstrated that S100A4 protects MDSCs from apoptosis through toll-like receptor-4/extracellular signal-regulated kinase-dependent caspase-9 inhibition. The finding that S100A4 is critical for MDSC survival in inflammatory environments might have important implications for the clinical treatment of cancer or inflammation-related diseases.