TRENDY: Gene Regulatory Network Inference Enhanced by Transformer

TL;DR

TRENDY introduces a transformer-based method to improve gene regulatory network inference, demonstrating superior performance on various datasets and enhancing existing inference techniques.

Contribution

It is the first to integrate transformer models into GRN inference, significantly boosting accuracy and applicability of existing methods.

Findings

Outperforms existing GRN inference methods on simulated data

Effective on experimental gene expression datasets

Broadly enhances multiple inference approaches

Abstract

Gene regulatory networks (GRNs) play a crucial role in the control of cellular functions. Numerous methods have been developed to infer GRNs from gene expression data, including mechanism-based approaches, information-based approaches, and more recent deep learning techniques, the last of which often overlook the underlying gene expression mechanisms. In this work, we introduce TRENDY, a novel GRN inference method that integrates transformer models to enhance the mechanism-based WENDY approach. Through testing on both simulated and experimental datasets, TRENDY demonstrates superior performance compared to existing methods. Furthermore, we apply this transformer-based approach to three additional inference methods, showcasing its broad potential to enhance GRN inference.