Prediction of Time Series Gene Expression and Structural Analysis of Gene Regulatory Networks Using Recurrent Neural Networks

Monti, Michele; Fiorentino, Jonathan; Milanetti, Edoardo; Gosti, Giorgio; Tartaglia, Gian Gaetano

doi:10.3390/e24020141

Cited by 20 publications

(17 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed earlier, these can be placed into two groups based on the input data. The "one-step" methods estimate dynamics by directly using expression trajectories; these include RNAForecaster [6] (which is an out-of-the-box NeuralODE), and PRESCIENT [4], among others [14,15]. PHOENIX is more similar to these methods.…”

Section: Phoenix Exceeds the Most Optimistic Performances Of Current ...mentioning

confidence: 99%

See 1 more Smart Citation

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Hossain

Fanfani

Quackenbush

et al. 2023

Preprint

View full text Add to dashboard Cite

Models that are formulated as ordinary differential equations (ODEs) can accurately explain temporal gene expression patterns and promise to yield new insights into important cellular processes, disease progression, and intervention design. Learning such ODEs is challenging, since we want to predict the evolution of gene expression in a way that accurately encodes the causal gene-regulatory network (GRN) governing the dynamics and the nonlinear functional relationships between genes. Most widely used ODE estimation methods either impose too many parametric restrictions or are not guided by meaningful biological insights, both of which impedes scalability and/or explainability. To overcome these limitations, we developed PHOENIX, a modeling framework based on neural ordinary differential equations (NeuralODEs) and Hill-Langmuir kinetics, that can flexibly incorporate prior domain knowledge and biological constraints to promote sparse, biologically interpretable representations of ODEs. We test accuracy of PHOENIX in a series of in silico experiments benchmarking it against several currently used tools for ODE estimation. We also demonstrate PHOENIX's flexibility by studying oscillating expression data from synchronized yeast cells and assess its scalability by modelling genome-scale breast cancer expression for samples ordered in pseudotime. Finally, we show how the combination of user-defined prior knowledge and functional forms from systems biology allows PHOENIX to encode key properties of the underlying GRN, and subsequently predict expression patterns in a biologically explainable way.

show abstract

Section: Phoenix Exceeds the Most Optimistic Performances Of Current ...mentioning

confidence: 99%

“…. ; x t T } without additional steps or consideration of other regulatory inputs [4,6,15]. In the process of learning transitions between PHOENIX 3 consecutive time points, these "one-step" methods implicitly learn the local derivative (often referred to as "RNA velocity" [16]) dx dt | x=xt m , as an intermediary to estimating f .…”

Section: Introductionmentioning

confidence: 99%

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Hossain

Fanfani

Quackenbush

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…2) Stationary and Instant Recurrent Network: Although the windowed attention can reduce the complexity to O(L), the information utilization could be sacrificed for LTTF due to point-wise sparse connections. RNNs have achieved big successes in many sequential data applications [41]- [44] attributed to their capabilities of capturing dynamics in sequences via cycles in the network of nodes. To enhance information utilization without increasing time and memory complexities, we, therefore, renovate the recurrent network accordingly.…”

Section: A Input Representationmentioning

confidence: 99%

Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution

Li¹,

Lu²,

Xiong³

et al. 2023

Preprint

View full text Add to dashboard Cite

Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. Though one could lower the complexity of Transformers by inducing the sparsity in point-wise self-attentions for LTTF, the limited information utilization prohibits the model from exploring the complex dependencies comprehensively. To this end, we propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects: (i) an encoderdecoder architecture incorporating a linear complexity without sacrificing information utilization is proposed on top of slidingwindow attention and Stationary and Instant Recurrent Network (SIRN); (ii) a module derived from the normalizing flow is devised to further improve the information utilization by inferring the outputs with the latent variables in SIRN directly; (iii) the inter-series correlation and temporal dynamics in time-series data are modeled explicitly to fuel the downstream self-attention mechanism. Extensive experiments on seven real-world datasets demonstrate that Conformer outperforms the state-of-the-art methods on LTTF and generates reliable prediction results with uncertainty quantification.

show abstract

“…To model the dynamics of gene expression, we used the Gillespie algorithm, 30 a well-established stochastic simulation method of choice in computational biology. 31 To ensure a comprehensive exploration of system dynamics, we implemented a parallelized approach, allowing for an in-depth examination of interactions among molecular components and their consequent impact on gene expression dynamics over a defined time horizon. Simulations were carried out with the same concentrations of trigger RNA and the DNA template used in the cell-free reactions.…”

Section: 4mentioning

confidence: 99%

Signal Amplification for Cell-Free Biosensors, an Analog-to-Digital Converter

Franco,

Brenner,

Zocca

et al. 2023

ACS Synth. Biol.

View full text Add to dashboard Cite

Toehold switches are biosensors useful for the detection of endogenous and environmental RNAs. They have been successfully engineered to detect virus RNAs in cell-free gene expression reactions. Their inherent sequence programmability makes engineering a fast and predictable process. Despite improvements in the design, toehold switches suffer from leaky translation in the OFF state, which compromises the fold change and sensitivity of the biosensor. To address this, we constructed and tested signal amplification circuits for three toehold switches triggered by Dengue and SARS-CoV-2 RNAs and an artificial RNA. The serine integrase circuit efficiently contained leakage, boosted the expression fold change from OFF to ON, and decreased the detection limit of the switches by 3–4 orders of magnitude. Ultimately, the integrase circuit converted the analog switches’ signals into digital-like output. The circuit is broadly useful for biosensors and eliminates the hard work of designing and testing multiple switches to find the best possible performer.

show abstract

Prediction of Time Series Gene Expression and Structural Analysis of Gene Regulatory Networks Using Recurrent Neural Networks

Cited by 20 publications

References 70 publications

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution

Signal Amplification for Cell-Free Biosensors, an Analog-to-Digital Converter

Contact Info

Product

Resources

About