19 March 2021 in Nature Communications
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.
17 February 2016 in Applied Microbiology and Biotechnology
1 March 2019 in Bioinformatics
Motivation: Diseases and traits are under dynamic tissue-specific regulation. However, heterogeneous tissues are often collected in biomedical studies, which reduce the power in the identification of disease-associated variants and gene expression profiles. Results: We present deTS, an R package, to conduct tissue-specific enrichment analysis with two built-in reference panels. Statistical methods are developed and implemented for detecting tissue-specific genes and for enrichment test of different forms of query data. Our applications using multi-trait genome-wide association studies data and cancer expression data showed that deTS could effectively identify the most relevant tissues for each query trait or sample, providing insights for future studies. Availability and implementation: https://github.com/bsml320/deTS and CRAN https://cran.r-project.org/web/packages/deTS/ Supplementary information: Supplementary data are available at Bioinformatics online.
5 February 2018 in Biotechnology for Biofuels
Photosynthetic cyanobacteria have attracted a significant attention as promising chassis to produce renewable fuels and chemicals due to their capability to utilizing solar energy and CO2. Notably, the enhancing supply of key precursors like malonyl-CoA would benefit the production of many bio-compounds. Nevertheless, the lacking of genetic tools in cyanobacteria, especially the knockdown strategies for essential pathways, has seriously restricted the attempts to re-direct carbon flux from the central carbohydrate metabolism to the synthesis of bioproducts. Aiming at developing new genetic tools, two small RNA regulatory tools are reported for the model cyanobacterium Synechocystis sp. PCC6803, based on paired termini RNAs as well as the exogenous Hfq chaperone and MicC scaffold (Hfq-MicC) previously developed in Escherichia coli. Both regulatory tools functioned well in regulating exogenous reporter gene lacZ and endogenous glgC gene in Synechocystis sp. PCC6803, achieving a downregulation of gene expression up to 90% compared with wildtype. In addition, the Hfq-MicC tool was developed to simultaneously regulate multiple genes related to essential fatty acids biosynthesis, which led to decreased fatty acids content by 11%. Furthermore, aiming to re-direct the carbon flux, the Hfq-MicC tool was utilized to interfere the competing pathway of malonyl-CoA, achieving an increased intracellular malonyl-CoA abundance up to 41% (~ 698.3 pg/mL/OD730 nm) compared to the wildtype. Finally, the Hfq-MicC system was further modified into an inducible system based on the theophylline-inducible riboswitch. In this study, two small RNA regulatory tools for manipulating essential metabolic pathways and re-directing carbon flux are reported for Synechocystis sp. PCC6803. The work introduces efficient and valuable metabolic regulatory strategies for photosynthetic cyanobacteria.