Network inference in systems biology: recent developments, challenges, and applications

Saint-Antoine, Michael; Singh, Abhyudai

doi:10.1016/j.copbio.2019.12.002

Cited by 73 publications

(51 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, these approaches have all struggled with the complex and nonlinear dynamics that shape gene regulation, containing several saturation effects and abundant negative and positive feed-backs. These non-linearities impede most of the available correlation-based methods used to study gene expression [11].…”

Section: Introductionmentioning

confidence: 99%

White-box Deep Neural Network Prediction of Genome-Wide Transcriptome Signatures

Magnusson¹,

Jn²,

Gustafsson³

2021

Preprint

View full text Add to dashboard Cite

Prediction algorithms for protein or gene structures, including transcription factor binding from sequence information, have been transformative in understanding gene regulation. Here we ask whether human transcriptomic profiles can be predicted solely from the expression of transcription factors (TFs). To this end, we explore whether a neural network (NN) could predict the transcriptome from TFs. Using at least one hidden layer, we find that the expression of 1,600 TFs can explain >95% of variance in 25,000 genes. Using the light-up technique to inspect the trained NN, we find an overrepresentation of known TF-gene regulations. Furthermore, the learned prediction network has a hierarchical organization. A smaller set of around 125 core TFs could explain close to 80% of the variance. Interestingly, reducing the number of TFs below 500 induces a rapid decline in prediction performance. Next, we evaluated the prediction model using transcriptional data from 22 human diseases. The TFs were sufficient to predict the target genes' dysregulation (rho=0.61, P < 10^-216). By inspecting the model, key causative TFs could be extracted for subsequent validation using disease-associated genetic variants. In conclusion, we demonstrate the construction of an interpretable neural network predictor. Analysis of the predictors revealed key TFs that were inducing transcriptional changes during disease.

show abstract

Section: Introductionmentioning

confidence: 99%

White-box Deep Neural Network Prediction of Genome-Wide Transcriptome Signatures

Magnusson¹,

Jn²,

Gustafsson³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…), measuring time-series data has become relatively easy. Accordingly, inferring direct regulations along with type (positive/negative) solely given time-series data is an important tool to provide key insights into the mechanisms underlying the system in a timely and inexpensive manner (1).…”

Section: Introductionmentioning

confidence: 99%

“…This transformation enables accurate and precise inference of the (self-)regulation type (e.g., positive, negative, or a mixture) between two components X and Y described by Eqn. (1). This allows us to infer various network structures such as a cycle, multiple cycles, and a cycle with outputs from in silico oscillatory time-series data.…”

Section: Introductionmentioning

confidence: 99%

Inferring causality in biological oscillators

Tyler

Forger

Kim

2021

Preprint

View full text Add to dashboard Cite

A fundamental goal of biological study is to identify regulatory interactions among components. The recent surge in time-series data collection in biology provides a unique opportunity to infer regulatory networks computationally. However, when the components oscillate, model-free inference methods, while easily implemented, struggle to distinguish periodic synchrony and causality. Alternatively, model-based methods test whether time series are reproducible with a specific model but require inefficient simulations and have limited applicability. Here, we develop an inference method based on a general model of molecular, neuronal, and ecological oscillatory systems that merges the advantages of both model-based and model-free methods, namely accuracy, broad applicability, and usability. Our method successfully infers the positive and negative regulations of various oscillatory networks, including the repressilator and a network of cofactors of pS2 promoter, outperforming popular inference methods. We also provide a computational package, ION (Inferring Oscillatory Networks), that users can easily apply to noisy, oscillatory time series to decipher the mechanisms by which diverse systems generate oscillations.

show abstract

“…It remains an open problem. Many signaling network inference models are based on correlation, regression and Bayesian analysis [3]. For example, the weighted correlation network analysis (WGCNA) model was widely used [4].…”

Section: Introductionmentioning

confidence: 99%

Signaling interaction link prediction using deep graph neural networks integrating protein-protein interactions and omics data

Feng

Zeng

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Uncovering signaling links or cascades among proteins that potentially regulate tumor development and drug response is one of the most critical and challenging tasks in cancer molecular biology. Inhibition of the targets on the core signaling cascades can be effective as novel cancer treatment regimens. However, signaling cascades inference remains an open problem, and there is a lack of effective computational models. The widely used gene co-expression network (no-direct signaling cascades) and shortest-path based protein-protein interaction (PPI) network analysis (with too many interactions, and did not consider the sparsity of signaling cascades) were not specifically designed to predict the direct and sparse signaling cascades. To resolve the challenges, we proposed a novel deep learning model, deepSignalingLinkNet, to predict signaling cascades by integrating transcriptomics data and copy number data of a large set of cancer samples with the protein-protein interactions (PPIs) via a novel deep graph neural network model. Different from the existing models, the proposed deep learning model was trained using the curated KEGG signaling pathways to identify the informative omics and PPI topology features in the data-driven manner to predict the potential signaling cascades. The validation results indicated the feasibility of signaling cascade prediction using the proposed deep learning models. Moreover, the trained model can potentially predict the signaling cascades among the new proteins by transferring the learned patterns on the curated signaling pathways. The code was available at: https://github.com/fuhaililab/deepSignalingPathwayPrediction.

show abstract

Network inference in systems biology: recent developments, challenges, and applications

Cited by 73 publications

References 74 publications

White-box Deep Neural Network Prediction of Genome-Wide Transcriptome Signatures

White-box Deep Neural Network Prediction of Genome-Wide Transcriptome Signatures

Inferring causality in biological oscillators

Signaling interaction link prediction using deep graph neural networks integrating protein-protein interactions and omics data

Contact Info

Product

Resources

About