Author:
Ubingazhibov Aidyn,Gomez-Cabrero David,Kiani Narsis A.,Tegner Jesper
Abstract
AbstractThe human interactome is a valuable tool for unraveling disease mechanisms, advancing precision medicine, facilitating drug discovery, and identifying biomarkers. Yet, current interactomes are incomplete, in part due to limited experimental coverage. Therefore, augmenting the human interactome by predicting missing links in the Protein-Protein interaction network (PPI), is a core challenge for precision medicine. This study proposes an end-to-end trainable transformer-based neural network for enhanced aggregation of Gene Ontology (GO) terms features. We augment the model’s predictive capabilities by incorporating semantic anc2vec features, complementing the structural node2vec embeddings specifically designed for sparse PPIs. As a result, by integrating semantic and graph features, we demonstrate superior performance in link prediction.
Publisher
Cold Spring Harbor Laboratory
Reference15 articles.
1. Friends and neighbors on the Web
2. Chi Thang Duong , Thanh Dat Hoang , Ha The Hien Dang , Quoc Viet Hung Nguyen , and Karl Aberer . On node features for graph neural networks, 2019.
3. Anc2vec: embedding gene ontology terms by preserving ancestors relationships;Briefings in Bioinformatics,2022
4. Matthias Fey and Jan E. Lenssen . Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds, 2019.
5. F. Gao , K. Musial , C. Cooper , and S. Tsoka . Link prediction methods and their accuracy for different social networks and network metrics. Scientific Programming, 2015, 2015.