Abstract
Automated protein function prediction is critical for the annotation of uncharacterized protein sequences, where accurate prediction methods are still required. Recently, deep learning based methods have outperformed conventional algorithms in computer vision and natural language processing due to the prevention of overfitting and efficient training. Here, we propose DEEPred, a hierarchical stack of multi-task feed-forward deep neural networks, as a solution to Gene Ontology (GO) based protein function prediction. DEEPred was optimized through rigorous hyper-parameter tests, and benchmarked using three types of protein descriptors, training datasets with varying sizes and GO terms form different levels. Furthermore, in order to explore how training with larger but potentially noisy data would change the performance, electronically made GO annotations were also included in the training process. The overall predictive performance of DEEPred was assessed using CAFA2 and CAFA3 challenge datasets, in comparison with the state-of-the-art protein function prediction methods. Finally, we evaluated selected novel annotations produced by DEEPred with a literature-based case study considering the ‘biofilm formation process’ in Pseudomonas aeruginosa. This study reports that deep learning algorithms have significant potential in protein function prediction; particularly when the source data is large. The neural network architecture of DEEPred can also be applied to the prediction of the other types of ontological associations. The source code and all datasets used in this study are available at: https://github.com/cansyl/DEEPred.
Highlights
Www.nature.com/scientificreports is an initiative, whose aim is the large-scale evaluation of protein function prediction methods, and the results of the first two CAFA challenges showed that protein function prediction is still a challenging area[9,10]
In terms of the model architecture and properties, Deep Neural Network (DNN) are classified into multiple groups, the most popular architectures are feed-forward DNN, recurrent neural network (RNN), restricted Boltzmann machine (RBM) and deep belief network (DBN), auto encoder deep neural networks, convolutional neural network (CNN), and graph convolutional network (GCN)[14,15,18,19,22,23]
We identified 8 genes in the P. aureginosa reference genome that are associated with biofilm formation, but not annotated with the corresponding Gene Ontology (GO) term or its functionally related neighboring terms, in the source databases at the time of this analysis
Summary
Www.nature.com/scientificreports is an initiative, whose aim is the large-scale evaluation of protein function prediction methods, and the results of the first two CAFA challenges showed that protein function prediction is still a challenging area[9,10]. One of the most critical obstacles against developing a practical DNN-based predictive tool is the computationally intensive training processes that limits the size of input data and the number of functional categories that can be included in the system. Due to this reason, previous studies mostly focused on a small number of protein families or GO terms. There is a need for new predictive approaches with high performance, and with real-world usability, to be able to support in vitro studies in protein function identification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
