Protein Function Prediction Methods Research Articles

POLAT: Protein function prediction based on soft mask graph network and residue-Label ATtention

Motivation:Elucidating protein function is a central problem in biochemistry, genetics, and molecular biology. Developing computational methods for protein function prediction is critical due to the significant gap between sequence and functional data. Recent advances in protein structure prediction, which strongly correlates with function, make it feasible to use structure to predict function. However, current structure-based methods overlook the fact that individual residues may contribute differently to the protein’s function and do not take into account the correlation between protein residues and their functions. The challenge of effectively utilizing the relationship between protein residues and function-level information to predict protein function remains unsolved. Result:We proposed a protein function prediction method based on Soft Mask Graph Networks and Residue-Label Attention (POLAT), which could combine sequence features, predicted structure features, and function-level information to get an accurate prediction. We use soft mask graph networks to adaptively extract the residues relevant to functions. A residue-label attention mechanism is adopted to obtain the protein-level encoded features of a protein, which are then concatenated with a protein-level embedding and fed into a dense classifier to determine the probabilities of each function. POLAT achieves 0.670, 0.515, 0.578 Fmax and 0.677, 0.409, 0.507 AUPR on the PDB cdhit test set for the MFO, BPO, and CCO domains, respectively, outperforming the existing structure-based SOTA method GAT-GO (Fmax 0.633, 0.492, 0.547; AUPR 0.660, 0.381, 0.479). POLAT is also competitive in extensive experiments among sequence-based and multimodal methods and achieves the SOTA performance in three out of six metrics.

GO2Sum: generating human-readable functional summary of proteins from GO terms

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent a function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

Partial order relation-based gene ontology embedding improves protein function prediction.

Protein annotation has long been a challenging task in computational biology. Gene Ontology (GO) has become one of the most popular frameworks to describe protein functions and their relationships. Prediction of a protein annotation with proper GO terms demands high-quality GO term representation learning, which aims to learn a low-dimensional dense vector representation with accompanying semantic meaning for each functional label, also known as embedding. However, existing GO term embedding methods, which mainly take into account ancestral co-occurrence information, have yet to capture the full topological information in the GO-directed acyclic graph (DAG). In this study, we propose a novel GO term representation learning method, PO2Vec, to utilize the partial order relationships to improve the GO term representations. Extensive evaluations show that PO2Vec achieves better outcomes than existing embedding methods in a variety of downstream biological tasks. Based on PO2Vec, we further developed a new protein function prediction method PO2GO, which demonstrates superior performance measured in multiple metrics and annotation specificity as well as few-shot prediction capability in the benchmarks. These results suggest that the high-quality representation of GO structure is critical for diverse biological tasks including computational protein annotation.

When Protein Structure Embedding Meets Large Language Models.

Protein structure analysis is essential in various bioinformatics domains such as drug discovery, disease diagnosis, and evolutionary studies. Within structural biology, the classification of protein structures is pivotal, employing machine learning algorithms to categorize structures based on data from databases like the Protein Data Bank (PDB). To predict protein functions, embeddings based on protein sequences have been employed. Creating numerical embeddings that preserve vital information while considering protein structure and sequence presents several challenges. The existing literature lacks a comprehensive and effective approach that combines structural and sequence-based features to achieve efficient protein classification. While large language models (LLMs) have exhibited promising outcomes for protein function prediction, their focus primarily lies on protein sequences, disregarding the 3D structures of proteins. The quality of embeddings heavily relies on how well the geometry of the embedding space aligns with the underlying data structure, posing a critical research question. Traditionally, Euclidean space has served as a widely utilized framework for embeddings. In this study, we propose a novel method for designing numerical embeddings in Euclidean space for proteins by leveraging 3D structure information, specifically employing the concept of contact maps. These embeddings are synergistically combined with features extracted from LLMs and traditional feature engineering techniques to enhance the performance of embeddings in supervised protein analysis. Experimental results on benchmark datasets, including PDB Bind and STCRDAB, demonstrate the superior performance of the proposed method for protein function prediction.

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.

Current successes and remaining challenges in protein function prediction.

In recent years, improvements in protein function prediction methods have led to increased success in annotating protein sequences. However, the functions of over 30% of protein-coding genes remain unknown for many sequenced genomes. Protein functions vary widely, from catalyzing chemical reactions to binding DNA or RNA or forming structures in the cell, and some types of functions are challenging to predict due to the physical features associated with those functions. Other complications in understanding protein functions arise due to the fact that many proteins have more than one function or very small differences in sequence or structure that correspond to different functions. We will discuss some of the recent developments in predicting protein functions and some of the remaining challenges.

Bioinformatics Approach for Metabolism Pathways Curation: Carbohydrate Metabolism and TCA Cycle in the Archaeon Sulfolobus solfataricus P2

Background: Metabolic and genomic informatics integrations in organism-specific databases require comprehensive and intensive efforts. PathoLogic, a component of the Pathway Tools software package can create complete Pathway/Genome Databases (PGDBs) from genomic sequence and annotation files for any organism. This tool can predict the metabolic pathways using MetaCyc as a reference knowledge base. This work aimed to apply a bioinformatics approach to curate a PGDB created for the Crenarchaeon Sulfolobus solfataricus P2. This archaeon grows optimally at 80o C and pH 2-4. The complete genome of S. solfataricus P2 was released in 2001. Created PGDBs often need manual curations to fill in the metabolic gaps that the software failed to detect.
 Methods: We used Pathway Tools to create the PGDB for the Sulfolobus solfataricus P2. Bioinformatics curation for carbohydrate metabolism pathway (Entner-Doudoroff “ED”) and TCA cycle was carried out. Literature search as well as homology-, orthology- and context-based protein function prediction methods were followed for this curation using the Editors component of the Pathway Tools program.
 Results: Curation modified the number of the pathways in the database by adding extra pathways that have not been detected by the PathoLogic. New pathways such as semi-phosphorylated ED and a new variation of the TCA cycle were added to the PGDB of S. solfataricus P2. Filling in the metabolic holes (missing enzymes) in the pathways under study was also involved in the curation process.
 Conclusion: The bioinformatics curation of the PGDB of S. solfataricus P2 improved the database that can serve as a reference knowledge base for genomic annotations and metabolic pathway reconstructions of other organisms especially the closely related Archaea.

CFAGO: cross-fusion of network and attributes based on attention mechanism for protein function prediction.

Protein function annotation is fundamental to understanding biological mechanisms. The abundant genome-scale protein-protein interaction (PPI) networks, together with other protein biological attributes, provide rich information for annotating protein functions. As PPI networks and biological attributes describe protein functions from different perspectives, it is highly challenging to cross-fuse them for protein function prediction. Recently, several methods combine the PPI networks and protein attributes via the graph neural networks (GNNs). However, GNNs may inherit or even magnify the bias caused by noisy edges in PPI networks. Besides, GNNs with stacking of many layers may cause the over-smoothing problem of node representations. We develop a novel protein function prediction method, CFAGO, to integrate single-species PPI networks and protein biological attributes via a multi-head attention mechanism. CFAGO is first pre-trained with an encoder-decoder architecture to capture the universal protein representation of the two sources. It is then fine-tuned to learn more effective protein representations for protein function prediction. Benchmark experiments on human and mouse datasets show CFAGO outperforms state-of-the-art single-species network-based methods at least 7.59%, 6.90%, 11.68% in terms of m-AUPR, M-AUPR and Fmax, respectively, demonstrating cross-fusion by multi-head attention mechanism can greatly improve the protein function prediction. We further evaluate the quality of captured protein representations in terms of Davies Bouldin Score, whose results show cross-fused protein representations by multi-head attention mechanism is at least 2.7% better than that of original and concatenated representations. We believe CFAGO is an effective tool for protein function prediction. The source code of CFAGO and experiments data are available at: http://bliulab.net/CFAGO/. Supplementary data are available at Bioinformatics online.

ProFAB-open protein functional annotation benchmark.

As the number of protein sequences increases in biological databases, computational methods are required to provide accurate functional annotation with high coverage. Although several machine learning methods have been proposed for this purpose, there are still two main issues: (i) construction of reliable positive and negative training and validation datasets, and (ii) fair evaluation of their performances based on predefined experimental settings. To address these issues, we have developed ProFAB: Open Protein Functional Annotation Benchmark, which is a platform providing an infrastructure for a fair comparison of protein function prediction methods. ProFAB provides filtered and preprocessed protein annotation datasets and enables the training and evaluation of function prediction methods via several options. We believe that ProFAB will be useful for both computational and experimental researchers by enabling the utilization of ready-to-use datasets and machine learning algorithms for protein function prediction based on Gene Ontology terms and Enzyme Commission numbers. ProFAB is available at https://github.com/kansil/ProFAB and https://profab.kansil.org.

Encoding dynamical information of protein from normal mode analysis as multigraphs for function prediction by graph neural networks and highlighting functionally-critical residues.

Dynamics of proteins are crucial for its ability to perform its functions, but are often overlooked in the plethora of protein function prediction methods. However, the need for faster screening over sequence-structure-function spaces is ever growing due to the increase in number of known peptide sequences and structures without function annotations. Machine learning methods are commonly implemented to meet the latter need to moderate success, with graph neural networks (GNN) gaining traction in recent years due to its rather intuitive mapping to protein structures. On the other hand, encoding the dynamics of proteins is yet a critical outstanding issue. In our attempt to close this gap, we encode the dynamical information of modal shapes and frequencies, along with the protein contact map, into multigraphs to aid graph neural networks in their prediction. This reduction of mode shapes into graphs is done by calculating the correlation between pairwise residue movements, then weight-averaging the correlation across multiple mode shapes, taking into consideration the equipartition theorem. The anisotropic network model (ANM) and the torsional network model (TNM) are implemented for modal analysis, and the two network models are compared within our framework. The method is tested on various datasets with different sequence similarity cutoffs, and the results compared with existing methods. Furthermore, we are able to extract from our model the dynamically-critical residues, such as hydrogen-binding and ligand-binding sites, for each of the protein's functions. As such, the proposed model provides insight to critical mutation points, facilitating further investigation and understanding of the protein.

Availability of web servers significantly boosts citations rates of bioinformatics methods for protein function and disorder prediction.

Development of bioinformatics methods is a long, complex and resource-hungry process. Hundreds of these tools were released. While some methods are highly cited and used, many suffer relatively low citation rates. We empirically analyze a large collection of recently released methods in three diverse protein function and disorder prediction areas to identify key factors that contribute to increased citations. We show that provision of a working web server significantly boosts citation rates. On average, methods with working web servers generate three times as many citations compared to tools that are available as only source code, have no code and no server, or are no longer available. This observation holds consistently across different research areas and publication years. We also find that differences in predictive performance are unlikely to impact citation rates. Overall, our empirical results suggest that a relatively low-cost investment into the provision and long-term support of web servers would substantially increase the impact of bioinformatics tools.

An Ensemble Tf-Idf Based Approach to Protein Function Prediction via Sequence Segmentation.

This paper explores the use of variants of tf-idf-based descriptors, namely length-normalized-tf-idf and log-normalized-tf-idf, combined with a segmentation technique, for efficient modeling of variable-length protein sequences. The proposed solution, ProtVecGen-Ensemble, is an ensemble of three models trained on differently segmented datasets constructed from an input dataset containing complete protein sequences. Evaluations using biological process (BP) and molecular function (MF) datasets demonstrate that the proposed feature set is not only superior to its contemporaries but also produces more consistent results with respect to variation in sequence lengths. Improvements of +6.07% (BP) and +7.56% (MF) over state-of-the-art tf-idf-based MLDA feature set were obtained. The best results were achieved when ProtVecGen-Ensemble was combined with ProtVecGen-Plus - the state-of-the-art method for protein function prediction - resulting in improvements of +8.90% (BP) and +11.28% (MF) over MLDA and +1.49% (BP) and +2.07% (MF) over ProtVecGen-Plus+MLDA. To capture the performance consistency with respect to sequence lengths, we have defined a variance-based metric, with lower values indicating better performance. On this metric, the proposed ProtVecGen-Ensemble+ProtVecGen-Plus framework resulted in reductions of 56.85 percent (BP) and 56.08 percent (MF) over MLDA and 10.37 percent (BP) and 26.48 percent (MF) over ProtVecGenPlus+MLDA.

TALE-cmap: Protein function prediction based on a TALE-based architecture and the structure information from contact map

Protein function prediction is one of the most critical tasks in bioinformatics. The computational predictors that can accurately predict the protein functions from their sequences are highly desired. With the development of the protein structure prediction methods, it is interesting to explore a new approach to use the predicted protein structures to improve the predictive performance of protein function prediction. TALE is a successful sequence-based method for protein function prediction. Therefore, in this study, we employed the TALE-based architecture to integrate sequence embeddings, contact map embeddings, and GO label embeddings to predict protein functions. These embeddings represent the proteins at the sequence, structure, and function levels. The TALE-cmap predictor outperforms the other state-of-the-art methods, indicating that structural information is essential for protein function prediction.

ContactPFP: Protein Function Prediction Using Predicted Contact Information

Computational function prediction is one of the most important problems in bioinformatics as elucidating the function of genes is a central task in molecular biology and genomics. Most of the existing function prediction methods use protein sequences as the primary source of input information because the sequence is the most available information for query proteins. There are attempts to consider other attributes of query proteins. Among these attributes, the three-dimensional (3D) structure of proteins is known to be very useful in identifying the evolutionary relationship of proteins, from which functional similarity can be inferred. Here, we report a novel protein function prediction method, ContactPFP, which uses predicted residue-residue contact maps as input structural features of query proteins. Although 3D structure information is known to be useful, it has not been routinely used in function prediction because the 3D structure is not experimentally determined for many proteins. In ContactPFP, we overcome this limitation by using residue-residue contact prediction, which has become increasingly accurate due to rapid development in the protein structure prediction field. ContactPFP takes a query protein sequence as input and uses predicted residue-residue contact as a proxy for the 3D protein structure. To characterize how predicted contacts contribute to function prediction accuracy, we compared the performance of ContactPFP with several well-established sequence-based function prediction methods. The comparative study revealed the advantages and weaknesses of ContactPFP compared to contemporary sequence-based methods. There were many cases where it showed higher prediction accuracy. We examined factors that affected the accuracy of ContactPFP using several illustrative cases that highlight the strength of our method.

PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods

Bioinformatic annotation of protein function is essential but extremely sophisticated, which asks for extensive efforts to develop effective prediction method. However, the existing methods tend to amplify the representativeness of the families with large number of proteins by misclassifying the proteins in the families with small number of proteins. That is to say, the ability of the existing methods to annotate proteins in the ‘rare classes’ remains limited. Herein, a new protein function annotation strategy, PFmulDL, integrating multiple deep learning methods, was thus constructed. First, the recurrent neural network was integrated, for the first time, with the convolutional neural network to facilitate the function annotation. Second, a transfer learning method was introduced to the model construction for further improving the prediction performances. Third, based on the latest data of Gene Ontology, the newly constructed model could annotate the largest number of protein families comparing with the existing methods. Finally, this newly constructed model was found capable of significantly elevating the prediction performance for the ‘rare classes’ without sacrificing that for the ‘major classes’. All in all, due to the emerging requirements on improving the prediction performance for the proteins in ‘rare classes’, this new strategy would become an essential complement to the existing methods for protein function prediction. All the models and source codes are freely available and open to all users at: https://github.com/idrblab/PFmulDL.

Potential of deep representative learning features to interpret the sequence information in proteomics.

In molecular biology and proteomics, accurately predicting functions of proteins is a very critical step. However, it sinks a lot of time and resources to detect the protein functions through biological experiments. Therefore, it is necessary to develop an accurate and reliable computational method for this prediction purpose. Since a growing number of deep learning and natural language processing (NLP) models have been developed recently, they hold potential to assist in protein function problems. Therefore, Wang etal. applied them to extract the hidden features of protein sequences and improve the performance of protein function prediction. As a case study, they used their approach to develop a web-server namely prPred-DRLF to predict plant resistance proteins, which play important roles in the detection of pathogen invasion. Cross-validation and independent test results indicate that prPred-DRLF outperformed current state-of-the-art prediction methods on the same datasets. The excellent performance then shows that deep representative learning (using deep learning and NLP) is an accurate and reliable method for protein function prediction. This article is protected by copyright. All rights reserved.

On the design of a similarity function for sparse binary data with application on protein function annotation

Automatic protein function annotation is a challenging task that is fundamental in many medical applications. Indeed, the capability to predict whether a protein has a given function is a key step for disease understanding and drug design. For such reasons, many authors have proposed computational methods for protein function prediction. One key element that is present in many proposals is similarity functions. Such functions are often used to compute the pairwise similarity between two proteins. It is commonly accepted that proteins with similar structures share the same function. Nevertheless, no previous works have focused on proposing a similarity function that is specifically designed for protein function annotation. In this work, we analyze the best similarity functions for the protein function annotation task and propose a new one. We performed experiments in a simple pairwise similarity scenario and also using our proposal as part of a more complex protein function annotation method. Based on the results, we can state that our proposal is a valid alternative as a building block of many protein function annotation methods.

HPODNets: deep graph convolutional networks for predicting human protein-phenotype associations.

Deciphering the relationship between human genes/proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment against diseases. The Human Phenotype Ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human disorders. However, the current HPO annotations are still incomplete. Thus, it is necessary to computationally predict human protein-phenotype associations. In terms of current, cutting-edge computational methods for annotating proteins (such as functional annotation), three important features are (i) multiple network input, (ii) semi-supervised learning and (iii) deep graph convolutional network (GCN), whereas there are no methods with all these features for predicting HPO annotations of human protein. We develop HPODNets with all above three features for predicting human protein-phenotype associations. HPODNets adopts a deep GCN with eight layers which allows to capture high-order topological information from multiple interaction networks. Empirical results with both cross-validation and temporal validation demonstrate that HPODNets outperforms seven competing state-of-the-art methods for protein function prediction. HPODNets with the architecture of deep GCNs is confirmed to be effective for predicting HPO annotations of human protein and, more generally, node label ranking problem with multiple biomolecular networks input in bioinformatics. https://github.com/liulizhi1996/HPODNets. Supplementary data are available at Bioinformatics online.

MUNDO: protein function prediction embedded in a multispecies world.

Leveraging cross-species information in protein function prediction can add significant power to network-based protein function prediction methods, because so much functional information is conserved across at least close scales of evolution. We introduce MUNDO, a new cross-species co-embedding method that combines a single-network embedding method with a co-embedding method to predict functional annotations in a target species, leveraging also functional annotations in a model species network. Across a wide range of parameter choices, MUNDO performs best at predicting annotations in the mouse network, when trained on mouse and human protein-protein interaction (PPI) networks, in the human network, when trained on human and mouse PPIs, and in Baker's yeast, when trained on Fission and Baker's yeast, as compared to competitor methods. MUNDO also outperforms all the cross-species methods when predicting in Fission yeast when trained on Fission and Baker's yeast; however, in this single case, discarding the information from the other species and using annotations from the Fission yeast network alone usually performs best. All code is available and can be accessed here: github.com/v0rtex20k/MUNDO. Supplementary data are available at Bioinformatics Advances online. Additional experimental results are on our github site.

DeepGOWeb: fast and accurate protein function prediction on the (Semantic) Web.

Understanding the functions of proteins is crucial to understand biological processes on a molecular level. Many more protein sequences are available than can be investigated experimentally. DeepGOPlus is a protein function prediction method based on deep learning and sequence similarity. DeepGOWeb makes the prediction model available through a website, an API, and through the SPARQL query language for interoperability with databases that rely on Semantic Web technologies. DeepGOWeb provides accurate and fast predictions and ensures that predicted functions are consistent with the Gene Ontology; it can provide predictions for any protein and any function in Gene Ontology. DeepGOWeb is freely available at https://deepgo.cbrc.kaust.edu.sa/.