deepNF: deep network fusion for protein function prediction

Abstract

MotivationThe prevalence of high-throughput experimental methods has resulted in an abundance of large-scale molecular and functional interaction networks. The connectivity of these networks provides a rich source of information for inferring functional annotations for genes and proteins. An important challenge has been to develop methods for combining these heterogeneous networks to extract useful protein feature representations for function prediction. Most of the existing approaches for network integration use shallow models that encounter difficulty in capturing complex and highly non-linear network structures. Thus, we propose deepNF, a network fusion method based on Multimodal Deep Autoencoders to extract high-level features of proteins from multiple heterogeneous interaction networks.ResultsWe apply this method to combine STRING networks to construct a common low-dimensional representation containing high-level protein features. We use separate layers for different network types in the early stages of the multimodal autoencoder, later connecting all the layers into a single bottleneck layer from which we extract features to predict protein function. We compare the cross-validation and temporal holdout predictive performance of our method with state-of-the-art methods, including the recently proposed method Mashup. Our results show that our method outperforms previous methods for both human and yeast STRING networks. We also show substantial improvement in the performance of our method in predicting gene ontology terms of varying type and specificity.Availability and implementation deepNF is freely available at: https://github.com/VGligorijevic/deepNF.Supplementary information Supplementary data are available at Bioinformatics online.

Accurate and Efficient Gene Function Prediction using a Multi-Bacterial Network

“…The median value of F max dropped from 0.990 for α = 1.0 with 1,000 iterations, to 0.982 for α = 0.95 with 10 iterations ( Figure S6c). This decrease of 0.08% in the median F max value was statistically significant (rank-sum test p-value = 2.5 × 10 −11 ) likely because of the large number of species-GO terms pairs (6,591).…”

“…Techniques that utilize multiple complementary data sources have been shown to be more accurate than those that use a single data source [6,7,18]. Therefore, we integrated the SSN with networks from the STRING database, a widely-used resource for multiple types of high-quality interaction data (such as based on physical binding, co-expression, and co-occurence) that is available for many species [19].…”

“…For instance, fewer than 0.01% (about 10,000 out of 104 million) of prokaryotic genes in the UniProt Knowledgebase [2] have a Gene Ontology (GO) [3] annotation with an experimental evidence code. To address this gap, several computational methods have been developed to associate molecular functions and biological processes with genes lacking experimental annotations [4][5][6][7][8][9][10][11]. These predicted associations assist in prioritizing follow-up experiments to determine the biological functions performed by gene products [12].…”

“…These predicted associations assist in prioritizing follow-up experiments to determine the biological functions performed by gene products [12]. Network-based techniques are among the most accurate and widely-used approaches for gene function prediction [4][5][6]9].…”

Integrating multi-network topology for gene function prediction using deep neural networks

“…Deep learning can solve the high dimensional feature learning problems effectively by the non-linear activation function. A few approaches have been proposed recently to learn non-linear network representations from complex data sources using autoencoder and convolutional neural network (Tian et al, 2014;Cao et al, 2016;Zitnik et al, 2018b;Gligorijevic et al, 2017). AutoEncoder (Rumelhart et al, 1986;Baldi, 2011) is a typical unsupervised deep learning model, which aims to learn a new encoding representation of input data.…”