Integrating node embeddings and biological annotations for genes to predict disease-gene associations

Abstract

BackgroundPredicting disease causative genes (or simply, disease genes) has played critical roles in understanding the genetic basis of human diseases and further providing disease treatment guidelines. While various computational methods have been proposed for disease gene prediction, with the recent increasing availability of biological information for genes, it is highly motivated to leverage these valuable data sources and extract useful information for accurately predicting disease genes.ResultsWe present an integrative framework called N2VKO to predict disease genes. Firstly, we learn the node embeddings from protein-protein interaction (PPI) network for genes by adapting the well-known representation learning method node2vec. Secondly, we combine the learned node embeddings with various biological annotations as rich feature representation for genes, and subsequently build binary classification models for disease gene prediction. Finally, as the data for disease gene prediction is usually imbalanced (i.e. the number of the causative genes for a specific disease is much less than that of its non-causative genes), we further address this serious data imbalance issue by applying oversampling techniques for imbalance data correction to improve the prediction performance. Comprehensive experiments demonstrate that our proposed N2VKO significantly outperforms four state-of-the-art methods for disease gene prediction across seven diseases.ConclusionsIn this study, we show that node embeddings learned from PPI networks work well for disease gene prediction, while integrating node embeddings with other biological annotations further improves the performance of classification models. Moreover, oversampling techniques for imbalance correction further enhances the prediction performance. In addition, the literature search of predicted disease genes also shows the effectiveness of our proposed N2VKO framework for disease gene prediction.

Supervised-learning is an accurate method for network-based gene classification

“…Akin to LP [38,75,76] , node embeddings also offer a convenient route to incorporating multiple networks into SL approaches. While methods such as SL-I and SL-A may require concatenating the original networks or integrating them into a single network before learning, recent work has shown that SL-E-based methods can embed information from multiple molecular/heterogeneous networks and learn gene classifiers in tandem [77][78][79][80][81][82][83][84][85] . However, none of these studies have compared the variety of SL-E methods to learning directly on the adjacency matrix.…”

A Knowledge-Based Machine Learning Approach to Gene Prioritisation in Amyotrophic Lateral Sclerosis

“…Many use graph-based methods, the most widely used being diffusion or random walk algorithms [ 12 , 13 , 14 , 15 , 16 , 17 ]. Other graph-based approaches include N2VKO [ 18 ], using node embeddings based on node2vec [ 19 ], CIPHER [ 20 ], based on gene network closeness and phenotype similarity, a gene gravity-like algorithm [ 21 ], and deep learning [ 22 ]. Other approaches not based on graphs include machine learning algorithms trained on functional similarity [ 23 ].…”

A novel one-class classification approach to accurately predict disease-gene association in acute myeloid leukemia cancer

“…To build this model they derived gene-gene mutual information from known gene-disease association data and then combined them with known protein-protein interaction networks using a boosted tree regression method [7]. In a different study, Ata et al, proposed N2VKO as an integrative framework to predict disease genes using binary classification [8]. Moreover, Luo et al [9] and Han et al [10] predicted disease-gene associations using the joint features and deep learning classifier.…”