Summary of Heterogeneous Network and Graph Attention Auto-encoder For Lncrna-disease Association Prediction, by Jin-xing Liu et al.
Heterogeneous network and graph attention auto-encoder for LncRNA-disease association prediction
by Jin-Xing Liu, Wen-Yu Xi, Ling-Yun Dai, Chun-Hou Zheng, Ying-Lian Gao
First submitted to arxiv on: 3 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel deep learning model called HGATELDA that accurately identifies nonlinear lncRNA-disease associations (LDAs). The model leverages multiple biomedical data sources to construct characteristics of lncRNAs and diseases, integrating both linear and nonlinear features. Linear characteristics are created using miRNA-lncRNA interaction matrices and miRNA-disease interaction matrices, while nonlinear features are extracted using a graph attention auto-encoder that retains critical information and aggregates neighborhood information. The model achieves an impressive AUC value of 0.9692 in a 5-fold cross-validation, outperforming recent prediction models. Case studies demonstrate the effectiveness of HGATELDA in identifying novel LDAs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand how to predict when certain long non-coding RNAs (lncRNAs) are associated with diseases. Current methods have limitations, so scientists created a new model called HGATELDA that uses lots of biomedical data and combines different types of information. The model is really good at finding patterns between lncRNAs and diseases that we might not see otherwise. This can help us diagnose and treat diseases more effectively. |
Keywords
» Artificial intelligence » Attention » Auc » Deep learning » Encoder
