PubMed · 9348587
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
1997. Computerized system streamlines chemotherapy order process.. https://pubmed.ncbi.nlm.nih.gov/9348587/
Cite the original work for its findings. Save a collection to share your selection of sources.
KEEP EXPLORING
Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational autoencoder (VAE) model to compress thousands of genes into latent vectors in a low-dimensional space. We then demonstrate that these encoded vectors could accurately impute drug response, outperform standard signature-gene based approaches, and appropriately control the overfitting problem. We apply rigorous quality assessment and validation, including assessing the impact of cell line lineage, cross-validation, cross-panel evaluation, and application in independent clinical data sets, to warrant the accuracy of the imputed drug response in both cell lines and cancer samples. Specifically, the expression-regulated component (EReX) of the observed drug response achieves high correlation across panels. Using the well-trained models, we impute drug response of The Cancer Genome Atlas data and investigate the features and signatures associated with the imputed drug response, including cell line origins, somatic mutations and tumor mutation burdens, tumor microenvironment, and confounding factors. In summary, our deep learning method and the results are useful for the study of signatures and markers of drug response.
Along with degradation of type IV collagen in basement membrane, destruction of the stromal collagens, types I and III, is an essential step in the invasive/metastatic behavior of tumor cells, and it is mediated, at least in part, by interstitial collagenase 1 (matrix metalloproteinase 1 (MMP-1)). Because A2058 melanoma cells produce substantial quantities of MMP-1, we used these cells as models for studying invasion of type I collagen. With a sensitive and quantitative in vitro invasion assay, we monitored the ability of these cells to invade a matrix of type I collagen and the ability of a serine proteinase inhibitor and all-trans-retinoic acid to block invasion. Although these cells produce copious amounts of MMP-1, they do not invade collagen unless they are co-cultured with fibroblasts or with conditioned medium derived from fibroblasts. Our studies indicate that a proteolytic cascade that depends on stromal/tumor cell interactions facilitates the ability of A2058 melanoma cells to invade a matrix of type I collagen. This cascade activates latent MMP-1 and involves both serine proteinases and MMPs, particularly stromelysin 1 (MMP-3). All-trans-retinoic acid (10(-6) M) suppresses the invasion of tumor cells by several mechanisms that include suppression of MMP synthesis and an increase in levels of tissue inhibitor of metalloproteinases 1 and 2. We conclude that invasion of stromal collagen by A2058 melanoma cells is mediated by a novel host/tumor cell interaction in which a proteolytic cascade culminates in the activation of pro-MMP-1 and tumor cell invasion.
Explore the source record for details and available documents.