Automated Protein Function Prediction Research Articles

An Overview of Protein Function Prediction Methods: A Deep Learning Perspective

Abstract: Predicting the function of proteins is a major challenge in the scientific community, particularly in the post-genomic era. Traditional methods of determining protein functions, such as experiments, are accurate but can be resource-intensive and time-consuming. The development of Next Generation Sequencing (NGS) techniques has led to the production of a large number of new protein sequences, which has increased the gap between available raw sequences and verified annotated sequences. To address this gap, automated protein function prediction (AFP) techniques have been developed as a faster and more cost-effective alternative, aiming to maintain the same accuracy level. : Several automatic computational methods for protein function prediction have recently been developed and proposed. This paper reviews the best-performing AFP methods presented in the last decade and analyzes their improvements over time to identify the most promising strategies for future methods. : Identifying the most effective method for predicting protein function is still a challenge. The Critical Assessment of Functional Annotation (CAFA) has established an international standard for evaluating and comparing the performance of various protein function prediction methods. In this study, we analyze the best-performing methods identified in recent editions of CAFA. These methods are divided into five categories based on their principles of operation: sequence-based, structure-based, combined-based, ML-based and embeddings-based. : After conducting a comprehensive analysis of the various protein function prediction methods, we observe that there has been a steady improvement in the accuracy of predictions over time, mainly due to the implementation of machine learning techniques. The present trend suggests that all the bestperforming methods will use machine learning to improve their accuracy in the future. : We highlight the positive impact that the use of machine learning (ML) has had on protein function prediction. Most recent methods developed in this area use ML, demonstrating its importance in analyzing biological information and making predictions. Despite these improvements in accuracy, there is still a significant gap compared with experimental evidence. The use of new approaches based on Deep Learning (DL) techniques will probably be necessary to close this gap, and while significant progress has been made in this area, there is still more work to be done to fully realize the potential of DL.

HEMDAG: a family of modular and scalable hierarchical ensemble methods to improve Gene Ontology term prediction.

Automated protein function prediction is a complex multi-class, multi-label, structured classification problem in which protein functions are organized in a controlled vocabulary, according to the Gene Ontology (GO). 'Hierarchy-unaware' classifiers, also known as 'flat' methods, predict GO terms without exploiting the inherent structure of the ontology, potentially violating the True-Path-Rule (TPR) that governs the GO, while 'hierarchy-aware' approaches, even if they obey the TPR, do not always show clear improvements with respect to flat methods, or do not scale well when applied to the full GO. To overcome these limitations, we propose Hierarchical Ensemble Methods for Directed Acyclic Graphs (HEMDAG), a family of highly modular hierarchical ensembles of classifiers, able to build upon any flat method and to provide 'TPR-safe' predictions, by leveraging a combination of isotonic regression and TPR learning strategies. Extensive experiments on synthetic and real data across several organisms firstly show that HEMDAG can be used as a general tool to improve the predictions of flat classifiers, and secondly that HEMDAG is competitive versus state-of-the-art hierarchy-aware learning methods proposed in the last CAFA international challenges. Fully tested R code freely available at https://anaconda.org/bioconda/r-hemdag. Tutorial and documentation at https://hemdag.readthedocs.io. Supplementary data are available at Bioinformatics online.

NetGO 2.0: improving large-scale protein function prediction with massive sequence, text, domain, family and network information.

With the explosive growth of protein sequences, large-scale automated protein function prediction (AFP) is becoming challenging. A protein is usually associated with dozens of gene ontology (GO) terms. Therefore, AFP is regarded as a problem of large-scale multi-label classification. Under the learning to rank (LTR) framework, our previous NetGO tool integrated massive networks and multi-type information about protein sequences to achieve good performance by dealing with all possible GO terms (>44 000). In this work, we propose the updated version as NetGO 2.0, which further improves the performance of large-scale AFP. NetGO 2.0 also incorporates literature information by logistic regression and deep sequence information by recurrent neural network (RNN) into the framework. We generate datasets following the critical assessment of functional annotation (CAFA) protocol. Experiment results show that NetGO 2.0 outperformed NetGO significantly in biological process ontology (BPO) and cellular component ontology (CCO). In particular, NetGO 2.0 achieved a 12.6% improvement over NetGO in terms of area under precision-recall curve (AUPR) in BPO and around 2.6% in terms of n}{}mathbf {F_{max}} in CCO. These results demonstrate the benefits of incorporating text and deep sequence information for the functional annotation of BPO and CCO. The NetGO 2.0 web server is freely available at http://issubmission.sjtu.edu.cn/ng2/.

Neural Network and Random Forest Models in Protein Function Prediction.

Over the past decade, the demand for automated protein function prediction has increased due to the volume of newly sequenced proteins. In this paper, we address the function prediction task by developing an ensemble system automatically assigning Gene Ontology (GO) terms to the given input protein sequence. We develop an ensemble system which combines the GO predictions made by random forest (RF) and neural network (NN) classifiers. Both RF and NN models rely on features derived from BLAST sequence alignments, taxonomy and protein signature analysis tools. In addition, we report on experiments with a NN model that directly analyzes the amino acid sequence as its sole input, using a convolutional layer. The Swiss-Prot database is used as the training and evaluation data. In the CAFA3 evaluation, which relies on experimental verification of the functional predictions, our submitted ensemble model demonstrates competitive performance ranking among top-10 best-performing systems out of over 100 submitted systems. In this paper, we evaluate and further improve the CAFA3-submitted system. Our machine learning models together with the data pre-processing and feature generation tools are publicly available as an open source software at https://github.com/TurkuNLP/CAFA3.

UNIPred-Web: a web tool for the integration and visualization of biomolecular networks for protein function prediction

BackgroundOne of the main issues in the automated protein function prediction (AFP) problem is the integration of multiple networked data sources. The UNIPred algorithm was thereby proposed to efficiently integrate —in a function-specific fashion— the protein networks by taking into account the imbalance that characterizes protein annotations, and to subsequently predict novel hypotheses about unannotated proteins. UNIPred is publicly available as R code, which might result of limited usage for non-expert users. Moreover, its application requires efforts in the acquisition and preparation of the networks to be integrated. Finally, the UNIPred source code does not handle the visualization of the resulting consensus network, whereas suitable views of the network topology are necessary to explore and interpret existing protein relationships.ResultsWe address the aforementioned issues by proposing UNIPred-Web, a user-friendly Web tool for the application of the UNIPred algorithm to a variety of biomolecular networks, already supplied by the system, and for the visualization and exploration of protein networks. We support different organisms and different types of networks —e.g., co-expression, shared domains and physical interaction networks. Users are supported in the different phases of the process, ranging from the selection of the networks and the protein function to be predicted, to the navigation of the integrated network. The system also supports the upload of user-defined protein networks. The vertex-centric and the highly interactive approach of UNIPred-Web allow a narrow exploration of specific proteins, and an interactive analysis of large sub-networks with only a few mouse clicks.ConclusionsUNIPred-Web offers a practical and intuitive (visual) guidance to biologists interested in gaining insights into protein biomolecular functions. UNIPred-Web provides facilities for the integration of networks, and supplies a framework for the imbalance-aware protein network integration of nine organisms, the prediction of thousands of GO protein functions, and a easy-to-use graphical interface for the visual analysis, navigation and interpretation of the integrated networks and of the functional predictions.

FunPred 3.0: improved protein function prediction using protein interaction network.

Proteins are the most versatile macromolecules in living systems and perform crucial biological functions. In the advent of the post-genomic era, the next generation sequencing is done routinely at the population scale for a variety of species. The challenging problem is to massively determine the functions of proteins that are yet not characterized by detailed experimental studies. Identification of protein functions experimentally is a laborious and time-consuming task involving many resources. We therefore propose the automated protein function prediction methodology using in silico algorithms trained on carefully curated experimental datasets. We present the improved protein function prediction tool FunPred 3.0, an extended version of our previous methodology FunPred 2, which exploits neighborhood properties in protein–protein interaction network (PPIN) and physicochemical properties of amino acids. Our method is validated using the available functional annotations in the PPIN network of Saccharomyces cerevisiae in the latest Munich information center for protein (MIPS) dataset. The PPIN data of S. cerevisiae in MIPS dataset includes 4,554 unique proteins in 13,528 protein–protein interactions after the elimination of the self-replicating and the self-interacting protein pairs. Using the developed FunPred 3.0 tool, we are able to achieve the mean precision, the recall and the F-score values of 0.55, 0.82 and 0.66, respectively. FunPred 3.0 is then used to predict the functions of unpredicted protein pairs (incomplete and missing functional annotations) in MIPS dataset of S. cerevisiae. The method is also capable of predicting the subcellular localization of proteins along with its corresponding functions. The code and the complete prediction results are available freely at: https://github.com/SovanSaha/FunPred-3.0.git.

DEEPred: Automated Protein Function Prediction with Multi-task Feed-forward Deep Neural Networks

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.

Evaluating the impact of topological protein features on the negative examples selection

BackgroundSupervised machine learning methods when applied to the problem of automated protein-function prediction (AFP) require the availability of both positive examples (i.e., proteins which are known to possess a given protein function) and negative examples (corresponding to proteins not associated with that function). Unfortunately, publicly available proteome and genome data sources such as the Gene Ontology rarely store the functions not possessed by a protein. Thus the negative selection, consisting in identifying informative negative examples, is currently a central and challenging problem in AFP. Several heuristics have been proposed through the years to solve this problem; nevertheless, despite their effectiveness, to the best of our knowledge no previous existing work studied which protein features are more relevant to this task, that is, which protein features help more in discriminating reliable and unreliable negatives.ResultsThe present work analyses the impact of several features on the selection of negative proteins for the Gene Ontology (GO) terms. The analysis is network-based: it exploits the fact that proteins can be naturally structured in a network, considering the pairwise relationships coming from several sources of data, such as protein-protein and genetic interactions. Overall, the proposed protein features, including local and global graph centrality measures and protein multifunctionality, can be term-aware (i.e., depending on the GO term) and term-unaware (i.e., invariant across the GO terms). We validated the informativeness of each feature utilizing a temporal holdout in three different experiments on yeast, mouse and human proteomes: (i) feature selection to detect which protein features are more helpful for the negative selection; (ii) protein function prediction to verify whether the features considered are also useful to predict GO terms; (iii) negative selection by applying two different negative selection algorithms on proteins represented through the proposed features.ConclusionsTerm-aware features (with some exceptions) resulted more informative for problem (i), together with node betweenness, which is the most relevant among term-unaware features. The node positive neighborhood instead is the most predictive feature for the AFP problem, while experiment (iii) showed that the proposed features allow negative selection algorithms to select effectively negative instances in the temporal holdout setting, with better results when nonlinear combinations of features are also exploited.

A GPU-based algorithm for fast node label learning in large and unbalanced biomolecular networks

BackgroundSeveral problems in network biology and medicine can be cast into a framework where entities are represented through partially labeled networks, and the aim is inferring the labels (usually binary) of the unlabeled part. Connections represent functional or genetic similarity between entities, while the labellings often are highly unbalanced, that is one class is largely under-represented: for instance in the automated protein function prediction (AFP) for most Gene Ontology terms only few proteins are annotated, or in the disease-gene prioritization problem only few genes are actually known to be involved in the etiology of a given disease. Imbalance-aware approaches to accurately predict node labels in biological networks are thereby required. Furthermore, such methods must be scalable, since input data can be large-sized as, for instance, in the context of multi-species protein networks.ResultsWe propose a novel semi-supervised parallel enhancement of COSNet, an imbalance-aware algorithm build on Hopfield neural model recently suggested to solve the AFP problem. By adopting an efficient representation of the graph and assuming a sparse network topology, we empirically show that it can be efficiently applied to networks with millions of nodes. The key strategy to speed up the computations is to partition nodes into independent sets so as to process each set in parallel by exploiting the power of GPU accelerators. This parallel technique ensures the convergence to asymptotically stable attractors, while preserving the asynchronous dynamics of the original model. Detailed experiments on real data and artificial big instances of the problem highlight scalability and efficiency of the proposed method.ConclusionsBy parallelizing COSNet we achieved on average a speed-up of 180x in solving the AFP problem in the S. cerevisiae, Mus musculus and Homo sapiens organisms, while lowering memory requirements. In addition, to show the potential applicability of the method to huge biomolecular networks, we predicted node labels in artificially generated sparse networks involving hundreds of thousands to millions of nodes.

Phylo-PFP: improved automated protein function prediction using phylogenetic distance of distantly related sequences.

Function annotation of proteins is fundamental in contemporary biology across fields including genomics, molecular biology, biochemistry, systems biology and bioinformatics. Function prediction is indispensable in providing clues for interpreting omics-scale data as well as in assisting biologists to build hypotheses for designing experiments. As sequencing genomes is now routine due to the rapid advancement of sequencing technologies, computational protein function prediction methods have become increasingly important. A conventional method of annotating a protein sequence is to transfer functions from top hits of a homology search; however, this approach has substantial short comings including a low coverage in genome annotation. Here we have developed Phylo-PFP, a new sequence-based protein function prediction method, which mines functional information from a broad range of similar sequences, including those with a low sequence similarity identified by a PSI-BLAST search. To evaluate functional similarity between identified sequences and the query protein more accurately, Phylo-PFP reranks retrieved sequences by considering their phylogenetic distance. Compared to the Phylo-PFP's predecessor, PFP, which was among the top ranked methods in the second round of the Critical Assessment of Functional Annotation (CAFA2), Phylo-PFP demonstrated substantial improvement in prediction accuracy. Phylo-PFP was further shown to outperform prediction programs to date that were ranked top in CAFA2. Phylo-PFP web server is available for at http://kiharalab.org/phylo_pfp.php. Supplementary data are available at Bioinformatics online.

DeepText2GO: Improving large-scale protein function prediction with deep semantic text representation.

As of April 2018, UniProtKB has collected more than 115 million protein sequences. Less than 0.15% of these proteins, however, have been associated with experimental GO annotations. As such, the use of automatic protein function prediction (AFP) to reduce this huge gap becomes increasingly important. The previous studies conclude that sequence homology based methods are highly effective in AFP. In addition, mining motif, domain, and functional information from protein sequences has been found very helpful for AFP. Other than sequences, alternative information sources such as text, however, may be useful for AFP as well. Instead of using BOW (bag of words) representation in traditional text-based AFP, we propose a new method called DeepText2GO that relies on deep semantic text representation, together with different kinds of available protein information such as sequence homology, families, domains, and motifs, to improve large-scale AFP. Furthermore, DeepText2GO integrates text-based methods with sequence-based ones by means of a consensus approach. Extensive experiments on the benchmark dataset extracted from UniProt/SwissProt have demonstrated that DeepText2GO significantly outperformed both text-based and sequence-based methods, validating its superiority.

ESG: Extended Similarity Group method for automated protein function prediction

Motivation: Importance of accurate automatic protein function prediction is ever increasing in the face of a large number of newly sequenced genomes and proteomics data that are awaiting biological interpretation. Conventional methods have focused on high sequence similarity-based annotation transfer which relies on the concept of homology. However, many cases have been reported that simple transfer of function from top hits of a homology search causes erroneous annotation. New methods are required to handle the sequence similarity in a more robust way to combine together signals from strongly and weakly similar proteins for effectively predicting function for unknown proteins with high reliability. Results: We present the extended similarity group (ESG) method, which performs iterative sequence database searches and annotates a query sequence with Gene Ontology terms. Each annotation is assigned with probability based on its relative similarity score with the multiple-level neighbors in the protein similarity graph. We will depict how the statistical framework of ESG improves the prediction accuracy by iteratively taking into account the neighborhood of query protein in the sequence similarity space. ESG outperforms conventional PSI-BLAST and the protein function prediction (PFP) algorithm. It is found that the iterative search is effective in capturing multiple-domains in a query protein, enabling accurately predicting several functions which originate from different domains. Availability: ESG web server is available for automated protein function prediction at http://dragon.bio.purdue.edu/ESG/ Contact: rk.ca.uac@krapsc; ude.eudrup@arahikd Supplementary information: Supplementary data are available at Bioinformatics online.

Multitask Protein Function Prediction through Task Dissimilarity.

Automated protein function prediction is a challenging problem with distinctive features, such as the hierarchical organization of protein functions and the scarcity of annotated proteins for most biological functions. We propose a multitask learning algorithm addressing both issues. Unlike standard multitask algorithms, which use task (protein functions) similarity information as a bias to speed up learning, we show that dissimilarity information enforces separation of rare class labels from frequent class labels, and for this reason is better suited for solving unbalanced protein function prediction problems. We support our claim by showing that a multitask extension of the label propagation algorithm empirically works best when the task relatedness information is represented using a dissimilarity matrix as opposed to a similarity matrix. Moreover, the experimental comparison carried out on three model organism shows that our method has a more stable performance in both "protein-centric" and "function-centric" evaluation settings.

RANKS: a flexible tool for node label ranking and classification in biological networks.

RANKS is a flexible software package that can be easily applied to any bioinformatics task formalizable as ranking of nodes with respect to a property given as a label, such as automated protein function prediction, gene disease prioritization and drug repositioning. To this end RANKS provides an efficient and easy-to-use implementation of kernelized score functions, a semi-supervised algorithmic scheme embedding both local and global learning strategies for the analysis of biomolecular networks. To facilitate comparative assessment, baseline network-based methods, e.g. label propagation and random walk algorithms, have also been implemented. The package is available from CRAN: https://cran.r-project.org/ The package is written in R, except for the most computationally intensive functionalities which are implemented in C. valentini@di.unimi.it Supplementary data are available at Bioinformatics online.

Regularization and Kernelization of the Maximin Correlation Approach

Robust classification becomes challenging when each class consists of multiple subclasses. Examples include multi-font optical character recognition and automated protein function prediction. In correlation-based nearest-neighbor classification, the maximin correlation approach (MCA) provides the worst-case optimal solution by minimizing the maximum misclassification risk through an iterative procedure. Despite the optimality, the original MCA has drawbacks that have limited its wide applicability in practice. That is, the MCA tends to be sensitive to outliers, cannot effectively handle nonlinearities in datasets, and suffers from having high computational complexity. To address these limitations, we propose an improved solution, named regularized maximin correlation approach (R-MCA). We first reformulate MCA as a quadratically constrained linear programming (QCLP) problem, incorporate regularization by introducing slack variables in the primal problem of the QCLP, and derive the corresponding Lagrangian dual. The dual formulation enables us to apply the kernel trick to R-MCA so that it can better handle nonlinearities. Our experimental results demonstrate that the regularization and kernelization make the proposed R-MCA more robust and accurate for various classification tasks than the original MCA. Furthermore, when the data size or dimensionality grows, R-MCA runs substantially faster by solving either the primal or dual (whichever has a smaller variable dimension) of the QCLP.

Multi-instance multilabel learning with weak-label for predicting protein function in electricigens.

Nature often brings several domains together to form multidomain and multifunctional proteins with a vast number of possibilities. In our previous study, we disclosed that the protein function prediction problem is naturally and inherently Multi-Instance Multilabel (MIML) learning tasks. Automated protein function prediction is typically implemented under the assumption that the functions of labeled proteins are complete; that is, there are no missing labels. In contrast, in practice just a subset of the functions of a protein are known, and whether this protein has other functions is unknown. It is evident that protein function prediction tasks suffer from weak-label problem; thus protein function prediction with incomplete annotation matches well with the MIML with weak-label learning framework. In this paper, we have applied the state-of-the-art MIML with weak-label learning algorithm MIMLwel for predicting protein functions in two typical real-world electricigens organisms which have been widely used in microbial fuel cells (MFCs) researches. Our experimental results validate the effectiveness of MIMLwel algorithm in predicting protein functions with incomplete annotation.

Evaluating a variety of text-mined features for automatic protein function prediction with GOstruct.

Most computational methods that predict protein function do not take advantage of the large amount of information contained in the biomedical literature. In this work we evaluate both ontology term co-mention and bag-of-words features mined from the biomedical literature and analyze their impact in the context of a structured output support vector machine model, GOstruct. We find that even simple literature based features are useful for predicting human protein function (F-max: Molecular Function =0.408, Biological Process =0.461, Cellular Component =0.608). One advantage of using literature features is their ability to offer easy verification of automated predictions. We find through manual inspection of misclassifications that some false positive predictions could be biologically valid predictions based upon support extracted from the literature. Additionally, we present a “medium-throughput” pipeline that was used to annotate a large subset of co-mentions; we suggest that this strategy could help to speed up the rate at which proteins are curated.Electronic supplementary materialThe online version of this article (doi:10.1186/s13326-015-0006-4) contains supplementary material, which is available to authorized users.

PFP/ESG: automated protein function prediction servers enhanced with Gene Ontology visualization tool.

Protein function prediction (PFP) is an automated function prediction method that predicts Gene Ontology (GO) annotations for a protein sequence using distantly related sequences and contextual associations of GO terms. Extended similarity group (ESG) is another GO prediction algorithm that makes predictions based on iterative sequence database searches. Here, we provide interactive web servers for the PFP and ESG algorithms that are equipped with an effective visualization of the GO predictions in a hierarchical topology. PFP/ESG servers are freely available at http://kiharalab.org/web/pfp.php and http://kiharalab.org/web/esg.php, or access both at http://kiharalab.org/pfp_esg.php. Supplementary data are available at Bioinformatics online.

Protein Function Prediction with Incomplete Annotations.

Automated protein function prediction is one of the grand challenges in computational biology. Multi-label learning is widely used to predict functions of proteins. Most of multi-label learning methods make prediction for unlabeled proteins under the assumption that the labeled proteins are completely annotated, i.e., without any missing functions. However, in practice, we may have a subset of the ground-truth functions for a protein, and whether the protein has other functions is unknown. To predict protein functions with incomplete annotations, we propose a Protein Function Prediction method with Weak-label Learning (ProWL) and its variant ProWL-IF. Both ProWL and ProWL-IF can replenish the missing functions of proteins. In addition, ProWL-IF makes use of the knowledge that a protein cannot have certain functions, which can further boost the performance of protein function prediction. Our experimental results on protein-protein interaction networks and gene expression benchmarks validate the effectiveness of both ProWL and ProWL-IF.

A novel method for functional annotation prediction based on combination of classification methods.

Automated protein function prediction defines the designation of functions of unknown protein functions by using computational methods. This technique is useful to automatically assign gene functional annotations for undefined sequences in next generation genome analysis (NGS). NGS is a popular research method since high-throughput technologies such as DNA sequencing and microarrays have created large sets of genes. These huge sequences have greatly increased the need for analysis. Previous research has been based on the similarities of sequences as this is strongly related to the functional homology. However, this study aimed to designate protein functions by automatically predicting the function of the genome by utilizing InterPro (IPR), which can represent the properties of the protein family and groups of the protein function. Moreover, we used gene ontology (GO), which is the controlled vocabulary used to comprehensively describe the protein function. To define the relationship between IPR and GO terms, three pattern recognition techniques have been employed under different conditions, such as feature selection and weighted value, instead of a binary one.