Ying Wang

KGRACDA predicts circRNA-disease associations by capturing local depth information in a knowledge graph, outperforming existing methods.

BertNDA predicts associations between miRNA, lncRNA, and diseases using a graph-Bert model with multi-scale information fusion, achieving better performance than existing methods.

KGETCDA predicts circRNA-disease associations using a knowledge graph encoder from Transformer, outperforming existing methods by capturing high-order interactions.

This paper introduces lncDLSM, a deep learning framework for identifying long non-coding RNAs without prior biological knowledge, showing effectiveness across species.

This paper proposes a deep ensemble model, DeepInteract, to predict circRNA-disease associations by integrating miRNA interactions and disease-related miRNA information, showing superior performance over existing methods.