TEC-miTarget: enhancing microRNA target prediction based on deep learning of ribonucleic acid sequences

Abstract

Background: MicroRNAs play a critical role in regulating gene expression by binding to specific target sites within gene transcripts, making the identification of microRNA targets a prominent focus of research. Conventional experimental methods for identifying microRNA targets are both time-consuming and expensive, prompting the development of computational tools for target prediction. However, the existing computational tools exhibit limited performance in meeting the demands of practical applications, highlighting the need to improve the performance of microRNA target prediction models.

Results: In this paper, we utilize the most popular natural language processing and computer vision technologies to propose a novel approach, called TEC-miTarget, for microRNA target prediction based on transformer encoder and convolutional neural networks. TEC-miTarget treats RNA sequences as a natural language and encodes them using a transformer encoder, a widely used encoder in natural language processing. It then combines the representations of a pair of microRNA and its candidate target site sequences into a contact map, which is a three-dimensional array similar to a multi-channel image. Therefore, the contact map's features are extracted using a four-layer convolutional neural network, enabling the prediction of interactions between microRNA and its candidate target sites. We applied a series of comparative experiments to demonstrate that TEC-miTarget significantly improves microRNA target prediction, compared with existing state-of-the-art models. Our approach is the first approach to perform comparisons with other approaches at both sequence and transcript levels. Furthermore, it is the first approach compared with both deep learning-based and seed-match-based methods. We first compared TEC-miTarget's performance with approaches at the sequence level, and our approach delivers substantial improvements in performance using the same datasets and evaluation metrics. Moreover, we utilized TEC-miTarget to predict microRNA targets in long mRNA sequences, which involves two steps: selecting candidate target site sequences and applying sequence-level predictions. We finally showed that TEC-miTarget outperforms other approaches at the transcript level, including the popular seed match methods widely used in previous years.

Conclusions: We propose a novel approach for predicting microRNA targets at both sequence and transcript levels, and demonstrate that our approach outperforms other methods based on deep learning or seed match. We also provide our approach as an easy-to-use software, TEC-miTarget, at https://github.com/tingpeng17/TEC-miTarget . Our results provide new perspectives for microRNA target prediction.

Keywords: Convolutional neural networks; Deep learning; MicroRNAs; Target prediction; Transformer encoder; miRNA targets.

Fig. 1

The architecture of TEC-miTarget

Fig. 2

The candidate target site (CTS) of size 3$l$ for a given transcript sequence

Fig. 3

The radar charts of the comparative results. A–C The performance of TEC-miTarget on the miRAW test set (A), miRAW independent test set (B), and DeepMirTar test set (C), compared with miRAW, DeepMirTar, miTAR, and GraphTar. D The average performance of TEC-miTarget on deepTargetPro test sets, compared with deepTarget, deepTargetPro, and TargetNet

Fig. 4

Base interaction probability maps. A TP pair. B TN pair. C FP pair. D FN pair

Fig. 5

The performance of TEC-miTarget utilizing four different encoders. Models are trained on the DeepMirTar training set and evaluated on the DeepMirTar independent test set

Fig. 6

Waston Crick pairing for some atypical positive pair (A) and negative pair (B)