Integration of Human Protein Sequence and Protein-Protein Interaction Data by Graph Autoencoder to Identify Novel Protein-Abnormal Phenotype Associations

Abstract

Understanding gene functions and their associated abnormal phenotypes is crucial in the prevention, diagnosis and treatment against diseases. The Human Phenotype Ontology (HPO) is a standardized vocabulary for describing the phenotype abnormalities associated with human diseases. However, the current HPO annotations are far from completion, and only a small fraction of human protein-coding genes has HPO annotations. Thus, it is necessary to predict protein-phenotype associations using computational methods. Protein sequences can indicate the structure and function of the proteins, and interacting proteins are more likely to have same function. It is promising to integrate these features for predicting HPO annotations of human protein. We developed GraphPheno, a semi-supervised method based on graph autoencoders, which does not require feature engineering to capture deep features from protein sequences, while also taking into account the topological properties in the protein–protein interaction network to predict the relationships between human genes/proteins and abnormal phenotypes. Cross validation and independent dataset tests show that GraphPheno has satisfactory prediction performance. The algorithm is further confirmed on automatic HPO annotation for no-knowledge proteins under the benchmark of the second Critical Assessment of Functional Annotation, 2013–2014 (CAFA2), where GraphPheno surpasses most existing methods. Further bioinformatics analysis shows that predicted certain phenotype-associated genes using GraphPheno share similar biological properties with known ones. In a case study on the phenotype of abnormality of mitochondrial respiratory chain, top prioritized genes are validated by recent papers. We believe that GraphPheno will help to reveal more associations between genes and phenotypes, and contribute to the discovery of drug targets.

Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review

“…Several studies have applied representation learning and autoencoders for auxiliary PPI prediction tasks. Liu et al [ 72 ] designed GraphPheno, a semi-supervised method based on graph autoencoders, for predicting relationships between human proteins and abnormal phenotypes. Nourani et al [ 73 ] presented TripletProt, a deep representation learning approach for proteins, based on Siamese neural networks.…”

Node2vec enhanced attributed graph matrix factorization algorithm

“…Complex network in the real world can be abstracted in the form of graphs [1] , such as social networks, transportation networks and biological protein structure networks [2] , etc. Community is an important substructure on the graph, which reflects the internal similarity between nodes on the graph.…”