# Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models

## TL;DR

This paper introduces Hi-Enhancer, a two-stage framework that improves enhancer prediction and localization using flexible combinations of epigenetic signals.

## Contribution

The novel contribution is the development of Blending-KAN and Stacking-Auto models for accurate and flexible enhancer prediction.

## Key findings

- The Blending-KAN model achieved 99.69 ± 0.11% accuracy with five epigenetic signals.
- The Stacking-Auto model outperformed 17 existing methods with 80.50% accuracy.
- The framework maintains high accuracy even with Gaussian noise and in cross-cell line predictions.

## Abstract

Gene expression plays a crucial role in cell function, and enhancers can regulate gene expression precisely. Therefore, accurate prediction of enhancers is particularly critical. However, existing prediction methods have low accuracy or rely on fixed multiple epigenetic signals, which may not always be available.

We propose a two-stage framework that accurately predicts enhancers by flexibly combining multiple epigenetic signals. In the first stage, we designed a Blending-KAN model, which integrates the results of various base classifiers and employs Kolmogorov–Arnold Networks (KAN) as a meta-classifier to predict enhancers based on flexible combinations of multiple epigenetic signals. In the second stage, we developed a Stacking-Auto model, which extracted sequence features using DNABERT-2 and located the enhancers based on the Stacking strategy and AutoGluon framework. The accuracy of the Blending-KAN model reached 99.69 ± 0.11% when five epigenetic signals were used. In cross-cell line prediction, the accuracy was more significant than or equal to 93.72%. With Gaussian noise, it still maintains an accuracy of 98.74 ± 0.03%. In the second stage, the accuracy of the Stacking-Auto model is 80.50%, which is better than the existing 17 methods. The results show that our models can be flexibly used to predict and locate enhancers utilizing a combination of multiple epigenetic signals.

The source code is available at https://github.com/emanlee/Hi-Enhancer and https://doi.org/10.6084/m9.figshare.29262158.v1.