Network-based approaches that exploit inferred transcription factor activity to analyze the impact of genetic variation on gene expression

Bussemaker, Harmen J.; Causton, Helen C.; Fazlollahi, Mina; Lee, Eunjee; Muroff, Ivor

doi:10.1016/j.coisb.2017.04.002

Cited by 4 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ability to infer molecular mechanisms distinguishes KPNNs from most methods for single-cell RNA-seq data analysis [ 102 , 103 ]. More generally, KPNNs provide a deep learning-based framework that complements existing bioinformatic methods for identifying key transcription factors [ 104 – 106 ] and other regulatory proteins [ 107 – 109 ] from single-cell gene expression data [ 110 , 111 ]. KPNNs are also complementary to well-established paradigms for mathematical modeling and computational simulation of signaling pathways and gene regulatory networks [ 46 , 47 , 112 ].…”

Section: Discussionmentioning

confidence: 99%

Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data

Fortelny

Bock

2020

Genome Biol

View full text Add to dashboard Cite

Background Deep learning has emerged as a versatile approach for predicting complex biological phenomena. However, its utility for biological discovery has so far been limited, given that generic deep neural networks provide little insight into the biological mechanisms that underlie a successful prediction. Here we demonstrate deep learning on biological networks, where every node has a molecular equivalent, such as a protein or gene, and every edge has a mechanistic interpretation, such as a regulatory interaction along a signaling pathway. Results With knowledge-primed neural networks (KPNNs), we exploit the ability of deep learning algorithms to assign meaningful weights in multi-layered networks, resulting in a widely applicable approach for interpretable deep learning. We present a learning method that enhances the interpretability of trained KPNNs by stabilizing node weights in the presence of redundancy, enhancing the quantitative interpretability of node weights, and controlling for uneven connectivity in biological networks. We validate KPNNs on simulated data with known ground truth and demonstrate their practical use and utility in five biological applications with single-cell RNA-seq data for cancer and immune cells. Conclusions We introduce KPNNs as a method that combines the predictive power of deep learning with the interpretability of biological networks. While demonstrated here on single-cell sequencing data, this method is broadly relevant to other research areas where prior domain knowledge can be represented as networks.

show abstract

Section: Discussionmentioning

confidence: 99%

Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data

Fortelny

Bock

2020

Genome Biol

View full text Add to dashboard Cite

show abstract

“…The direct evidence is motivated by the idea that changes in transcription factor expression may lead to similar changes in in target gene expression. The coexpression of co-targeted genes is long established in the literature [ 9 , 10 ], and evidence also points to the coexpression of transcription factor genes with targets of that transcription factor [ 11 , 12 ]. Moreover, studies across multiple tissues have shown widely varying expression of transcription factor genes, indicating that this expression can be used to predict their regulatory involvement [ 13 ].…”

Section: Methodsmentioning

confidence: 99%

Estimating drivers of cell state transitions using gene regulatory network models

et al. 2017

View full text Add to dashboard Cite

BackgroundSpecific cellular states are often associated with distinct gene expression patterns. These states are plastic, changing during development, or in the transition from health to disease. One relatively simple extension of this concept is to recognize that we can classify different cell-types by their active gene regulatory networks and that, consequently, transitions between cellular states can be modeled by changes in these underlying regulatory networks.ResultsHere we describe MONSTER, MOdeling Network State Transitions from Expression and Regulatory data, a regression-based method for inferring transcription factor drivers of cell state conditions at the gene regulatory network level. As a demonstration, we apply MONSTER to four different studies of chronic obstructive pulmonary disease to identify transcription factors that alter the network structure as the cell state progresses toward the disease-state.ConclusionsWe demonstrate that MONSTER can find strong regulatory signals that persist across studies and tissues of the same disease and that are not detectable using conventional analysis methods based on differential expression. An R package implementing MONSTER is available at github.com/QuackenbushLab/MONSTER.Electronic supplementary materialThe online version of this article (doi:10.1186/s12918-017-0517-y) contains supplementary material, which is available to authorized users.

show abstract

“…In principle, TF activity inference could also be used to predict the transcriptomic effects of direct perturbations of TF activity levels, such as deletion or over-expression. Finally, inferred activity levels could be used to improve TF network mapping (5,12,14,16,(22)(23)(24)(26)(27)(28)(29)(30)(31)(32)(33).…”

Section: Introductionmentioning

confidence: 99%

“…In principle, TF activity inference could also be used to predict the transcriptomic effects of direct perturbations of TF activity levels, such as deletion or over-expression of a TF-encoding gene. Finally, inferred activity levels could be used to improve TF network mapping ( Arrieta-Ortiz et al, 2015 ; Barenco et al, 2009 ; Bussemaker et al, 2001 , 2017 ; Cokus et al , 2006 ; Fu et al , 2011 ; Gao et al , 2004 ; Gitter et al , 2013 ; Lam et al, 2016 ; Lee and Bussemaker, 2010 ; Nachman et al , 2004 ; Shi et al , 2009 ; Tchourine et al , 2018 ; Wang et al, 2008 ; Yang et al, 2005 ; Yu and Li, 2005 ).…”

Section: Introductionmentioning

confidence: 99%

Inferring TF activities and activity regulators from gene expression data with constraints from TF perturbation data

Cynthia

Brent

2020

Bioinformatics

View full text Add to dashboard Cite

Motivation The activity of a transcription factor (TF) in a sample of cells is the extent to which it is exerting its regulatory potential. Many methods of inferring TF activity from gene expression data have been described, but due to the lack of appropriate large-scale datasets, systematic and objective validation has not been possible until now. Results We systematically evaluate and optimize the approach to TF activity inference in which a gene expression matrix is factored into a condition-independent matrix of control strengths and a condition-dependent matrix of TF activity levels. We find that expression data in which the activities of individual TFs have been perturbed are both necessary and sufficient for obtaining good performance. To a considerable extent, control strengths inferred using expression data from one growth condition carry over to other conditions, so the control strength matrices derived here can be used others. Finally, we apply these methods to gain insight into the upstream factors that regulate the activities of yeast TFs Gcr2, Gln3, Gcn4, and Msn2. Conclusions When a high-quality network map and TF perturbation-response data are available, inferring TF activity levels by factoring gene expression matrices is effective. Furthermore, it can provide insight into regulators of TF activity. Availability and implementation Evaluation code and data available at https://doi.org/10.5281/zenodo.4050573 Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Network-based approaches that exploit inferred transcription factor activity to analyze the impact of genetic variation on gene expression

Cited by 4 publications

References 49 publications

Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data

Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data

Estimating drivers of cell state transitions using gene regulatory network models

Inferring TF activities and activity regulators from gene expression data with constraints from TF perturbation data

Contact Info

Product

Resources

About