knaack

Sharing and Specificity of Co-expression Networks across 35 Human Tissues

This entry was posted in evolution network_inference on by

Our paper selection for Monday, October 26th is about an analysis of RNAseq data from the GTEx collaboration, titled Sharing and Specificity of Co-expression Networks across 35 Human Tissues. It is available at the PLOS Computational Biology website. The abstract reads as follows.

To understand the regulation of tissue-specific gene expression, the GTEx Consortium generated RNA-seq expression data for more than thirty distinct human tissues. This data provides an opportunity for deriving shared and tissue specific gene regulatory networks on the basis of co-expression between genes. However, a small number of samples are available for a majority of the tissues, and therefore statistical inference of networks in this setting is highly underpowered. To address this problem, we infer tissue-specific gene co-expression networks for 35 tissues in the GTEx dataset using a novel algorithm, GNAT, that uses a hierarchy of tissues to share data between related tissues. We show that this transfer learning approach increases the accuracy with which networks are learned. Analysis of these networks reveals that tissue-specific transcription factors are hubs that preferentially connect to genes with tissue specific functions. Additionally, we observe that genes with tissue-specific functions lie at the peripheries of our networks. We identify numerous modules enriched for Gene Ontology functions, and show that modules conserved across tissues are especially likely to have functions common to all tissues, while modules that are upregulated in a particular tissue are often instrumental to tissue-specific function. Finally, we provide a web tool, available at mostafavilab.stat.ubc.ca/GNAT, which allows exploration of gene function and regulation in a tissue-specific manner.

We look forward to seeing those who can attend on the 26th, and please feel free to start the discussion section below.

Elucidating Compound Mechanism of Action by Network Perturbation Analysis

This entry was posted in cancer methodological network_inference on by

Our next paper selection is a network perturbation paper from Cell, titled Elucidating Compound Mechanism of Action by Network Perturbation Analysis. It is available from ScienceDirect. The abstract is as follows:

Genome-wide identification of the mechanism of action (MoA) of small-molecule compounds characterizing their targets, effectors, and activity modulators represents a highly relevant yet elusive goal, with critical implications for assessment of compound efficacy and toxicity. Current approaches are labor intensive and mostly limited to elucidating high-affinity binding target proteins. We introduce a regulatory network-based approach that elucidates genome-wide MoA proteins based on the assessment of the global dysregulation of their molecular interactions following compound perturbation. Analysis of cellular perturbation profiles identified established MoA proteins for 70% of the tested compounds and elucidated novel proteins that were experimentally validated. Finally, unknown-MoA compound analysis revealed altretamine, an anticancer drug, as an inhibitor of glutathione peroxidase 4 lipid repair activity, which was experimentally confirmed, thus revealing unexpected similarity to the activity of sulfasalazine. This suggests that regulatory network analysis can provide valuable mechanistic insight into the elucidation of small-molecule MoA and compound similarity.

We will meet on Monday, October 12th in room 3160 of the Discovery Building at noon, per our usual schedule. Feel free to start our discussion in the comments section below.

Predicting effects of noncoding variants with deep learning–based sequence model

This entry was posted in network_inference on by

This week we will conclude our Deep Learning Theme with a loot at DeepSEA. Our meeting will be at noon Monday, September 28th in room 3160 of the Discovery building.

The title of the paper is Predicting effects of noncoding variants with deep learning–based sequence model, and it is available at http://www.nature.com/nmeth/journal/vaop/ncurrent/full/nmeth.3547.html. The abstract reads as follows:

Identifying functional effects of noncoding variants is a major challenge in human genetics. To predict the noncoding-variant effects de novo from sequence, we developed a deep learning–based algorithmic framework, DeepSEA (http://deepsea.princeton.edu/), that directly learns a regulatory sequence code from large-scale chromatin-profiling data, enabling prediction of chromatin effects of sequence alterations with single-nucleotide sensitivity. We further used this capability to improve prioritization of functional variants including expression quantitative trait loci (eQTLs) and disease-associated variants.

We look forward to seeing all who can attend next Monday, and please feel free to start the discussion in the comments section below.

Sara and Debbie

Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

This entry was posted in methodological network_inference on by

On Monday Sept. 14th, we will meet in room 3160 of the Discovery Building to discuss a Deep Learning method named DeepBind. The paper, is available at http://www.nature.com/nbt/journal/v33/n8/full/nbt.3300.html

The abstract of the paper reads as follows:

Knowing the sequence specificities of DNA- and RNA-binding proteins is essential for developing models of the regulatory processes in biological systems and for identifying causal disease variants. Here we show that sequence specificities can be ascertained from experimental data with ‘deep learning’ techniques, which offer a scalable, flexible and unified computational approach for pattern discovery. Using a diverse array of experimental data and evaluation metrics, we find that deep learning outperforms other state-of-the-art methods, even when training on in vitro data and testing on in vivo data. We call this approach DeepBind and have built a stand-alone software tool that is fully automatic and handles millions of sequences per experiment. Specificities determined by DeepBind are readily visualized as a weighted ensemble of position weight matrices or as a ‘mutation map’ that indicates how variations affect binding within a specific sequence.

We welcome you to post your questions and ideas here in the Comments section of this blog.