DNA-GCN: Graph convolutional networks for predicting DNA-protein binding

TL;DR

This paper introduces DNA-GCN, a novel graph convolutional network approach for DNA-protein binding prediction, leveraging k-mer graphs to improve motif inference and outperform traditional CNN methods.

Contribution

The study pioneers the application of graph convolutional networks to DNA motif inference, building a k-mer graph and jointly learning embeddings for sequences and k-mers.

Findings

DNA-GCN performs competitively on 50 ENCODE datasets.

The model effectively learns embeddings for k-mers and sequences.

Different architectures can be designed to adapt to various datasets.

Abstract

Predicting DNA-protein binding is an important and classic problem in bioinformatics. Convolutional neural networks have outperformed conventional methods in modeling the sequence specificity of DNA-protein binding. However, none of the studies has utilized graph convolutional networks for motif inference. In this work, we propose to use graph convolutional networks for motif inference. We build a sequence k-mer graph for the whole dataset based on k-mer co-occurrence and k-mer sequence relationship and then learn DNA Graph Convolutional Network (DNA-GCN) for the whole dataset. Our DNA-GCN is initialized with a one-hot representation for all nodes, and it then jointly learns the embeddings for both k-mers and sequences, as supervised by the known labels of sequences. We evaluate our model on 50 datasets from ENCODE. DNA-GCN shows its competitive performance compared with the baseline model. Besides, we analyze our model and design several different architectures to help fit different datasets.