# A Multi-Input Neural Network Model for Accurate MicroRNA Target Site Detection

## TL;DR

This paper introduces a new neural network model that accurately identifies microRNA target sites by integrating various biological features, improving upon existing computational methods.

## Contribution

The novel contribution is a multi-input neural network that uses biologically relevant features to enhance microRNA target site detection accuracy.

## Key findings

- The model achieves an AUPRC of 0.9373, outperforming existing computational methods.
- It demonstrates high precision and recall on experimentally validated test data.
- The model generalizes well to sequentially distant samples using structural and energetic features.

## Abstract

(1) Background: MicroRNAs are non-coding RNA sequences that regulate cellular functions by targeting messenger RNAs and inhibiting protein synthesis. Identifying their target sites is vital to understanding their roles. However, it is challenging due to the high cost and time demands of experimental methods and the high false-positive rates of computational approaches. (2) Methods: We introduce a Multi-Input Neural Network (MINN) algorithm that integrates diverse biologically relevant features, including the microRNA duplex structure, substructures, minimum free energy, and base-pairing probabilities. For each feature derived from a microRNA target-site duplex, we create a corresponding image. These images are processed in parallel by the MINN algorithm, allowing it to learn a comprehensive and precise representation of the underlying biological mechanisms. (3) Results: Our method, on an experimentally validated test set, detects target sites with an AUPRC of 0.9373, Precision of 0.8725, and Recall of 0.8703 and outperforms several commonly used computational methods of microRNA target-site predictions. (4) Conclusions: Incorporating diverse biologically explainable features, such as duplex structure, substructures, their MFEs, and binding probabilities, enables our model to perform well on experimentally validated test data. These features, rather than nucleotide sequences, enhance our model to generalize beyond specific sequence contexts and perform well on sequentially distant samples.