Fully Interpretable Deep Learning Model of Transcriptional Control

Liu, Yi; Barr, Kenneth; Reinitz, John

doi:10.1101/655639

Cited by 8 publications

(8 citation statements)

References 43 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we assume the information content of the input message to be the promoter state as the source, since the binding and unbinding of transcription factors to the enhancer induces the state of the promoter of the receptor gene [ 23 , 24 ]. The processing of all information arriving at the receptor is not considered here [ 25 , 26 , 27 , 28 ], as we are interested on the reliability of the information content of the message.…”

Section: Introductionmentioning

confidence: 99%

Binary Expression Enhances Reliability of Messaging in Gene Networks

Gama

Giovanini

Balázsi

et al. 2020

Entropy

View full text Add to dashboard Cite

The promoter state of a gene and its expression levels are modulated by the amounts of transcription factors interacting with its regulatory regions. Hence, one may interpret a gene network as a communicating system in which the state of the promoter of a gene (the source) is communicated by the amounts of transcription factors that it expresses (the message) to modulate the state of the promoter and expression levels of another gene (the receptor). The reliability of the gene network dynamics can be quantified by Shannon’s entropy of the message and the mutual information between the message and the promoter state. Here we consider a stochastic model for a binary gene and use its exact steady state solutions to calculate the entropy and mutual information. We show that a slow switching promoter with long and equally standing ON and OFF states maximizes the mutual information and reduces entropy. That is a binary gene expression regime generating a high variance message governed by a bimodal probability distribution with peaks of the same height. Our results indicate that Shannon’s theory can be a powerful framework for understanding how bursty gene expression conciliates with the striking spatio-temporal precision exhibited in pattern formation of developing organisms.

show abstract

Section: Introductionmentioning

confidence: 99%

Binary Expression Enhances Reliability of Messaging in Gene Networks

Gama

Giovanini

Balázsi

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…For this we used a gene set enrichment based method, Dorothea 11 , that estimates probabilities of TF activities from mRNA concentrations of their target genes. Given that the lifetime of mRNA is expected to be much shorter than regulatory changes in transcription rates 34 , mRNA concentrations can be expected to be proportional to their formation rates and thus reflect the activity of the TFs that regulate their expression. A potential limitation with this approach is that the statically inferred probabilities of activation may not have a direct biological interpretation.…”

Section: Predicting Signaling In Ligand Stimulated Macrophagesmentioning

confidence: 99%

Artificial neural networks enable genome-scale simulations of intracellular signaling

Nilsson

Peters

Bryson

et al. 2021

Preprint

View full text Add to dashboard Cite

Mammalian cells adapt their functional state in response to external signals in form of ligands that bind receptors on the cell-surface. Mechanistically, this involves signal-processing through a complex network of molecular interactions that govern transcription factor (TF) activity patterns. Computer simulations of the information flow through this network could help predict cellular responses in health and disease. Here we develop a recurrent neural network constrained by prior knowledge of the signaling network with ligand concentrations as input, TF activity as output and signaling molecules as hidden nodes. Simulations are assumed to reach steady state, and we regularize the parameters to enforce this. Using synthetic data, we train models that generalize to unseen data and predict the effects of gene knockouts. We also fit models to a small experimental data set from literature and confirm the predictions using cross validation. This demonstrates the feasibility of simulating intracellular signaling at the genome-scale.

show abstract

“…Therefore, we assume the information content of the input message to be the promoter state of the source, since the binding of transcription factors to the enhancer induces the state of the promoter of the receptor gene [29,30]. The processing of all information arriving at the receptor is not considered here [31][32][33][34], as we are interested on the reliability of the information content of the message. Hence, we employ Shannon's theory to compute the entropy of the message and the mutual information between the message and the promoter state of the source [35] by means of the probabilities given by the steady state exact solutions for the stochastic model for binary gene expression [36][37][38].…”

Section: Introductionmentioning

confidence: 99%

Bursty Expression Enhances Reliability of Messaging in Gene Networks

Gama

Giovanini

Balazsi³

et al. 2020

Preprint

View full text Add to dashboard Cite

The promoter state of a gene and its expression levels are modulated by the amounts of transcription factors interacting with its regulatory regions. Hence, one may interpret a gene network as a communicating system in which the state of the promoter of a gene (the source) is communicated by the amounts of transcription factors that it expresses (the message) to modulate the state of the promoter and expression levels of another gene (the receptor). The reliability of the gene network dynamics can be quantified by the Shannon's entropy of the message and the mutual information between the message and the promoter state. Here we consider a stochastic model for a binary gene and use its exact steady state solutions to calculate the entropy and mutual information. We show that a slow switching promoter having long and equally standing ON and OFF states maximizes the mutual information and reduces entropy. That is a bursty regime generating a high variance message governed by a bimodal probability distribution with peaks of the same height. Our results indicate that Shannon's theory can be a powerful framework for understanding how bursty gene expression conciliates with the striking spatio-temporal precision exhibited in pattern formation of developing organisms.

show abstract

Fully Interpretable Deep Learning Model of Transcriptional Control

Cited by 8 publications

References 43 publications

Binary Expression Enhances Reliability of Messaging in Gene Networks

Binary Expression Enhances Reliability of Messaging in Gene Networks

Artificial neural networks enable genome-scale simulations of intracellular signaling

Bursty Expression Enhances Reliability of Messaging in Gene Networks

Contact Info

Product

Resources

About