ADAGE-Based Integration of Publicly Available Pseudomonas aeruginosa Gene Expression Data with Denoising Autoencoders Illuminates Microbe-Host Interactions

Abstract

The quantity and breadth of genome-scale data sets that examine RNA expression in diverse bacterial and eukaryotic species are increasing more rapidly than for curated knowledge. Our ADAGE method integrates such data without requiring gene function, gene pathway, or experiment labeling, making practical its application to any large gene expression compendium. We built a Pseudomonas aeruginosa ADAGE model from a diverse set of publicly available experiments without any prespecified biological knowledge, and this model was accurate and predictive. We provide ADAGE results for the complete P. aeruginosa GeneChip compendium for use by researchers studying P. aeruginosa and source code that facilitates ADAGE’s application to other species and data types.

Extracting a biologically relevant latent space from cancer transcriptomes with variational autoencoders

“…Reconstructing gene expression input data using autoencoder frameworks has been previously shown to reveal novel biological patterns. [7][8][9] VAEs and GANs are generative models, which means they learn to approximate a data generating distribution. Through approximation and compression, the models have been shown to capture an underlying data manifold -a constrained, lower dimensional space where data is distributed -and disentangle sources of variation from different classes of data.…”

A machine learning classifier trained on cancer transcriptomes detects NF1 inactivation signal in glioblastoma

“…This finding supports using mRNA as a summary measurement capable of capturing system-wide responses to molecular events beyond transcription factor alterations. Machine learning has been applied to gene expression in a variety of studies with various goals [37][38][39][40][41]. In a similar study, Guinney et al trained a classifier to model RAS activity in colorectal cancer and demonstrated its clinical utility by predicting response to MEK inhibitors and anti-EGFR based treatments [18].…”

Deep Genomic Signature for early metastasis prediction in prostate cancer

“…the proposed DGS method consists of four steps: 1) Similar to the methods of (Danaee et al, 2016;Tan et al, 2015Tan et al, , 2016Tan et al, , 2017, a DAE is trained with a large unlabelled gene expression dataset to extract salient features. The output of this step is the learned parameters to be transferred to the next DAE.…”

“…3) After training the second DAE, genes with high weights in this DAE are selected based on a standard deviation filter on their connectivity weights. This selection approach is similar to (Danaee et al, 2016;Tan et al, 2015Tan et al, , 2016Tan et al, , 2017Way and Greene, 2018). The idea of this gene selection step is to provide the classifier with a few rich genes with the strongest signals based on both the labelled and unlabelled datasets.…”

“…For instance, DAE was applied in the Analysis Using Denoising Auto-Encoders of Gene Expression (ADAGE) method on compendium of Pseudomonas aeruginosa gene expression profiling experiments to identify biological patterns (Tan et al, 2016). Further, in order to enhance robustness and generate better signatures (more consistent with biological pathways), an ensemble version of ADAGE (eADAGE) was developed that integrated stable signatures across models (Tan et al, 2017).…”