An information theoretic treatment of sequence-to-expression modeling

Khajouei, Farzaneh; Sinha, Saurabh

doi:10.1371/journal.pcbi.1006459

Cited by 5 publications

(8 citation statements)

References 52 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We set up the GEMSTAT model with 13 different parameters as in (27,29) reported reduction in CIC-DNA binding by locally activated ERK is modeled using the parameter, as explained in (27). Henceforth, we refer to any setting of values for the above 13 parameters as a model.…”

Section: Model Trainingmentioning

confidence: 99%

“…We then followed the procedure in our previous work (29) to first cluster all models in an ensemble and then construct a probability distribution over the models such that each cluster (or group) of models has the same overall probability. We then computed the average predicted effect of every possible single nucleotide mutations in the ind enhancer.…”

Section: Systematic Prediction Of Snp Effects Using Ensemble Of Modelsmentioning

confidence: 99%

“…In the current work, we first modeled the expression data available for the 'intermediate neuroblasts defective' (ind) gene in Drosophila melanogaster, following our previous work (29).…”

Section: Expression Data Support Diverse Mechanistic Models Of Ind Enmentioning

confidence: 99%

“…However, when using these models one is faced with a trade-off in predictive accuracy: one fits the model to many different enhancers (22) if one wishes to capture broad regulatory mechanisms, but the resulting models are not capable of predicting the effect of minor changes such as single nucleotide variations. To achieve this latter capability, one typically fits the model to fewer, more closely related enhancers (27), but this results in underconstrained models and parameter uncertainty (29). The result is not a unique trained model but an ensemble of models, representing distinct mechanistic explanations of the data, and thus an ensemble of predictions about the effect of the same sequence mutation.…”

Section: Introductionmentioning

confidence: 99%

“…We had previously shown how ensemble modeling of the thermodynamics-based GEMSTAT model (27,29) can provide useful insights about the ind enhancer. Here, we used the ensemble of models to predict the effect of each single nucleotide mutation in the enhancer, and used our previously published probabilistic framework to identify mutations with high expected impact and/or high variance in predicted impact.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Model-based analysis of polymorphisms in an enhancer reveals cis-regulatory mechanisms

Khajouei

Samper

Djabrayan

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

It is challenging to predict the impact of small genetic changes such as single nucleotide polymorphisms on gene expression, since mechanisms involved in gene regulation and their cis-regulatory encoding are not well-understood. Recent studies have attempted to predict the functional impact of non-coding variants based on available knowledge of cis-regulatory encoding, e.g., transcription factor (TF) motifs. In this work, we explore the relationship between regulatory variants and cis-regulatory encoding from the opposite angle, using the former to inform the latter. We employ sequence-to-expression modeling to resolve ambiguities regarding gene regulatory mechanisms using information about effects of single nucleotide variations in an enhancer. We demonstrate our methodology using a well-studied enhancer of the developmental gene intermediate neuroblasts defective (ind) in D. melanogaster. We first trained the thermodynamics-based model GEMSTAT to relate the neuroectodermal expression pattern of ind to its enhancer's sequence, and constructed an ensemble of models that represent different parameter settings consistent with available data for this gene. We then predicted the effects of every possible single nucleotide variation within this enhancer, and compared these to SNP data recorded in the Drosophila Genome Reference Panel. We chose specific SNPs for which different models in the ensemble made conflicting predictions, and tested their effect in vivo. These experiments narrowed in on one mechanistic model as capable of explaining the observed effects. We further confirmed the generalizability of this model to orthologous enhancers and other related developmental enhancers. In conclusion, mechanistic models of cis-regulatory function not only help make specific predictions of variant impact, they may also be learned more accurately using data on variants.A central issue in analyzing variations in the non-coding genome is to interpret their functional impact, and their connections to phenotype differences and disease etiology. Machine learning methods based on statistical modeling have been developed to associate genetic variants to expression changes. However, associations predicted by these models may not be functionally relevant, despite being statisticaly significant. We describe how mathematical modeling of gene expression can be employed to systematically study the non-coding sequence and its relationship to gene expression. We demonstrate our method in a well studied developmental enhancer of the fruitfly. We establish the efficacy of mathematical models in combination with the polymorphism data to reveal new mechanistic insights.

show abstract

Section: Model Trainingmentioning

confidence: 99%

Section: Systematic Prediction Of Snp Effects Using Ensemble Of Modelsmentioning

confidence: 99%

“…In the current work, we first modeled the expression data available for the 'intermediate neuroblasts defective' (ind) gene in Drosophila melanogaster, following our previous work (29).…”

Section: Expression Data Support Diverse Mechanistic Models Of Ind Enmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Model-based analysis of polymorphisms in an enhancer reveals cis-regulatory mechanisms

Khajouei

Samper

Djabrayan

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Global shape of Toll activation is determined bywntDenhancer properties

Rahimi

Carmon

Averbukh

et al. 2020

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

View full text Add to dashboard Cite

Buffering variability in morphogen distribution is essential for reproducible patterning. A theoretically proposed class of mechanisms, termed “distal pinning,” achieves robustness by combining local sensing of morphogen levels with global modulation of gradient spread. Here, we demonstrate a critical role for morphogen sensing by a gene enhancer, which ultimately determines the final global distribution of the morphogen and enables reproducible patterning. Specifically, we show that, while the pattern of Toll activation in the early Drosophila embryo is robust to gene dosage of its locally produced regulator, WntD, it is sensitive to a single-nucleotide change in the wntD enhancer. Thus, enhancer properties of locally produced WntD directly impinge on the global morphogen profile.

show abstract

Deciphering enhancer sequence using thermodynamics-based models and convolutional neural networks

Dibaeinia

Sinha

2021

Nucleic Acids Research

Self Cite

View full text Add to dashboard Cite

Deciphering the sequence-function relationship encoded in enhancers holds the key to interpreting non-coding variants and understanding mechanisms of transcriptomic variation. Several quantitative models exist for predicting enhancer function and underlying mechanisms; however, there has been no systematic comparison of these models characterizing their relative strengths and shortcomings. Here, we interrogated a rich data set of neuroectodermal enhancers in Drosophila, representing cis- and trans- sources of expression variation, with a suite of biophysical and machine learning models. We performed rigorous comparisons of thermodynamics-based models implementing different mechanisms of activation, repression and cooperativity. Moreover, we developed a convolutional neural network (CNN) model, called CoNSEPT, that learns enhancer ‘grammar’ in an unbiased manner. CoNSEPT is the first general-purpose CNN tool for predicting enhancer function in varying conditions, such as different cell types and experimental conditions, and we show that such complex models can suggest interpretable mechanisms. We found model-based evidence for mechanisms previously established for the studied system, including cooperative activation and short-range repression. The data also favored one hypothesized activation mechanism over another and suggested an intriguing role for a direct, distance-independent repression mechanism. Our modeling shows that while fundamentally different models can yield similar fits to data, they vary in their utility for mechanistic inference. CoNSEPT is freely available at: https://github.com/PayamDiba/CoNSEPT.

show abstract

An information theoretic treatment of sequence-to-expression modeling

Cited by 5 publications

References 52 publications

Model-based analysis of polymorphisms in an enhancer reveals cis-regulatory mechanisms

Model-based analysis of polymorphisms in an enhancer reveals cis-regulatory mechanisms

Global shape of Toll activation is determined bywntDenhancer properties

Deciphering enhancer sequence using thermodynamics-based models and convolutional neural networks

Contact Info

Product

Resources

About