Computational modeling of mRNA degradation dynamics using deep neural networks

Abstract

Motivation mRNA degradation plays critical roles in post-transcriptional gene regulation. A major component of mRNA degradation is determined by 3’UTR elements. Hence, researchers are interested in studying mRNA dynamics as a function of 3’UTR elements. A recent study measured the mRNA degradation dynamics of tens of thousands of 3’UTR sequences using a massively parallel reporter assay. However, the computational approach used to model mRNA degradation was based on a simplifying assumption of a linear degradation rate. Consequently, the underlying mechanism of 3’UTR elements is still not fully understood. Results Here, we developed deep neural networks to predict mRNA degradation dynamics and interpreted the networks to identify regulatory elements in the 3’UTR and their positional effect. Given an input of a 110 nt-long 3’UTR sequence and an initial mRNA level, the model predicts mRNA levels of 8 consecutive times points. Our deep neural networks significantly improve prediction performance of mRNA degradation dynamics compared to extant methods for the task. Moreover, we demonstrated that models predicting the dynamics of two identical 3’UTR sequences, differing by their poly(A) tail, perform better than single-task models. On the interpretability front, by using Integrated Gradients, our CNNs models identified known and novel cis-regulatory sequence elements of mRNA degradation. By applying a novel systematic evaluation of model interpretability, we demonstrated that the RNN models are inferior to the CNN models in terms of interpretability and that random initialization ensemble improves both predictions and interoperability performance. Moreover, using a mutagenesis analysis, we newly discovered the positional effect of various 3’UTR elements. Availability All the code developed through this study is available at github.com/OrensteinLab/DeepUTR/. Supplementary information Supplementary data are available at Bioinformatics online.

Nucleic acid degradation as barrier to gene delivery: a guide to understand and overcome nuclease activity

“…451 Yaish and Orenstein used deep neural networks to predict mRNA degradation dynamics and identified known and novel cis -regulatory sequence elements of mRNA degradation. 452 As well, DNA degradation in water was simulated by quantile models. 453 The performance of such models might be restricted in predicting RNA/DNA degradation patterns due to the amount of data available for training and the limited accuracy of structure prediction.…”

Diverse intrinsic properties shape transcript stability and stabilization inMycolicibacterium smegmatis

“…However, a limitation is that these models simplify the relationship between the features by assuming that they can be combined linearly to determine transcript half-life. Although more advanced sequence-based machine learning models could also be applied to predict stability, their performances rely on large amounts of data for training with the focus more on achieving accurate prediction rather than understanding the underlying mechanisms 36,37 .…”