PubMed · 9922769
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
P Piedbois, M Buyse. 1998. [Randomizations!].. https://doi.org/10.1016/s1278-3218(99)80004-3
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.
DNA-microarray technology can be used to assess the expression of several thousands of genes at the same time. The identification of the gene expression profiles may help to better characterize human cancer. These studies may reveal subclasses of tumor types with similar histopathologic profile but different clinical courses.Furthermore,such studies could help to define therapeutic sensitivity and to estimate prognosis of various cancers. Identification of gene expression profiles of cancer can identify new therapeutic targets or cancer susceptibility genes. The DNA-microarray technology may write a new chapter in molecular oncology.
The survival of patients affected by cutaneous melanoma has improved dramatically in the last 10 years, because of earlier diagnosis. Despite this, the therapeutic results obtained in metastatic melanoma (MM) are very disappointing due to its poor responsiveness to cytotoxic agents. In this type of solid tumor, tumor chemosensitivity assays have been suggested to be an important tool to predict clinical responsiveness to therapy. Metastatic melanoma cells (MMCs) were obtained from subcutaneous melanoma metastases of five patients and cultured for several consecutive passages. An immunofluorescence and an electron microscopic study were performed in order to establish the ultrastructural and physiopathological features of MMCs. A sulphorodamine-B test was used to measure in vitro sensitivity of MMCs to temozolomide, cisplatin, vindesine, taxol and interpheron alpha-2a. Following a 72 h exposure, maximum activity was obtained with vindesine (median inhibitory concentration, IC(50), 0.23 nM) and taxol (median IC(50) 0.31 nM). Cisplatin median IC(50) values were higher (4.6 microM) than taxol and vindesine, but still in the range of clinically achievable plasma concentrations. Temozolomide inhibited cell proliferation only at very high concentrations (median IC(50) 228 microM). No significant cell growth inhibitory effects (<or=25%) were observed with interferon alpha-2a concentrations up to 8000 IU/ml. MMCs expressed progression markers typical of cutaneous metastatic melanoma and showed poor sensitivity in vitro to most anticancer drugs tested, including temozolomide.