Computational prediction of protein functional annotations.

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

The large amounts of available protein structures emerges the need for computational methods for protein function prediction. Predicting protein function is mainly based on finding similarities between proteins with unknown function with already annotated proteins. This may be achieved using different protein characteristics: sequences, interactions, localization, structure and or psychochemical. A lot of review papers mainly focus on sequence and psychochemical features- based methods. This is because sequence and psychochemical data are easy to deal with and to interpret the results, and much available compared to protein structures. However, structure-based computational methods provide additional accuracy and reliability of protein function prediction. Therefore, unlike many review papers, this paper presents an up-to-date review on the structure-based protein function prediction. The aim was to provide a recent and comprehensive review of protein structure related topics: function aspects, structural classification, databases, tools and methods.

Automated assignment of protein function has received considerable attention in recent years for genome-wide study. With the rapid accumulation of genome sequencing data produced by high-throughput experimental techniques, the process of manually predicting functional properties of proteins has become increasingly cumbersome. Such large genomics data sets can only be annotated computationally. However, automated assignment of functions to unknown protein is challenging due to its inherent difficulty and complexity. Previous studies have revealed that solving problems involving complicated objects with multiple semantic meanings using the multi-instance multi-label (MIML) framework is effective. For the protein function prediction problems, each protein object in nature may associate with distinct structural units (instances) and multiple functional properties (class labels) where each unit is described by an instance and each functional property is considered as a class label. Thus, it is convenient and natural to tackle the protein function prediction problem by using the MIML framework. In this paper, we propose a sparse Markov chain-based semi-supervised MIML method, called Sparse-Markov. A sparse transductive probability graph is constructed to encode the affinity information of the data based on ensemble of Hausdorff distance metrics. Our goal is to exploit the affinity between protein objects in the sparse transductive probability graph to seek a sparse steady state probability of the Markov chain model to do protein function prediction, such that two proteins are given similar functional labels if they are close to each other in terms of an ensemble Hausdorff distance in the graph. Experimental results on seven real-world organism data sets covering three biological domains show that our proposed Sparse-Markov method is able to achieve better performance than four state-of-the-art MIML learning algorithms.

In recent years, significant effort has been given to predicting protein functions from protein interaction data generated from high throughput techniques. However, predicting protein functions correctly and reliably still remains a challenge. Recently, many computational methods have been proposed for predicting protein functions. Among these methods, clustering based methods are the most promising. The existing methods, however, mainly focus on protein relationship modeling and the prediction algorithms that statically predict functions from the clusters that are related to the unannotated proteins. In fact, the clustering itself is a dynamic process and the function prediction should take this dynamic feature of clustering into consideration. Unfortunately, this dynamic feature of clustering is ignored in the existing prediction methods. In this paper, we propose an innovative progressive clustering based prediction method to trace the functions of relevant annotated proteins across all clusters that are generated through the progressive clustering of proteins. A set of prediction criteria is proposed to predict functions of unannotated proteins from all relevant clusters and traced functions. The method was evaluated on real protein interaction datasets and the results demonstrated the effectiveness of the proposed method compared with representative existing methods.

Accurately predicting protein functions is critical for understanding disease mechanisms and discovering potential drug targets. Gene Ontology (GO), with its hierarchical and semantic information, provides valuable context that can be integrated to improve prediction accuracy. Recently, several existing methods have attempted to integrate GO knowledge with protein sequence features for function prediction. However, these methods ignore the fact that GO embeddings should be tailored to proteins to reflect protein-specific functional relevance. To address this limitation, we proposed DPGOK, a deep learning-based method that fused protein-aware GO representations with protein features for function prediction. DPGOK first learns GO semantic representations with a knowledge graph loss and further generates protein-aware GO embeddings under the guidance of protein features. Results show that DPGOK outperforms state-of-the-art methods across all GO domains. Additional experiments demonstrated that DPGOK is capable of discovering hierarchically deeper and more informative functions for target proteins. Ablation studies revealed that the knowledge graph loss we introduced contributes to more stable and semantically coherent GO representations across different domains. Finally, we find that the predictive performance can be further improved when DPGOK is combined with homology-based approaches.

Data mining methods were applying almost everywhere and it give benefits in commercial and scientific uses. In health care by providing decision support data-mining can help in saving human life. There are various methods in data mining which can be used for data sets analysis and prediction and the methods are Support vector machine, Decision Tree, Random Forest, ANN etc. As we all know that protein function prediction is very important and challenging area of bioinformatics field. We can also apply data-mining methods in bioinformatics field for protein function prediction as it is less time consuming and give approximately the correct result. In this paper we had compare the two methods i.e S.V.M and Random Forest of data-mining in predicting the protein function. Here we had taken the protein data sets on the basis of enzymes classification and found that the overall accuracy of SVM (88.49%) is better than the Random Forest (53.9%).

It is a hot research field to design an effective method for protein function prediction by integrating heterogeneous biological data. In this work, we proposed a novel non-Negative Matrix Factorisation-based method, namely PONMF-S to learn protein and GO features from different biological networks for protein function prediction. Additionally, we extend PONMF-S to other versions by considering the function influence of proteins' neighbours and GO terms' neighbours. We apply our methods and two state-of-the-art methods (UBiRW and NMFGO) to predict functions for proteins of Saccharomyces cerevisiae and Homo sapiens. The prediction results show that PONMF-S outperforms the other two existing methods when randomly removing a part of known function information. When predicting functions for the proteins that have not any known ahead functional information, PONMF-S improves the prediction performance of NMFGO significantly and is comparable with UBiRW. Besides, the extended version of PONMF-S can even outperform UBiRW in most function categories.

After reviewing the underlying framework required for computational function prediction in the previous chapter, we discuss two advanced sequence-based function prediction methods developed in our group, namely the Protein Function Prediction (PFP) method and the Extended Similarity Group (ESG) method. PFP extends the traditional homology search by incorporating functional associations between pairs of Gene Ontology terms based on the frequencies of co-occurrences in annotation of the same proteins in the database. PFP also considers very weakly similar sequences to the query, thereby increases its sensitivity and ability to predict low resolution functional terms. On the other hand, ESG recursively searches the sequence similarity space around the query to find consensus annotations in the neighborhood. The last part of the chapter discusses the network structure of gene functional space built by connecting proteins with functional similarity. Function annotation was enriched by predictions by PFP. Similarity to structures of protein-protein interaction networks and metabolic pathway networks is discussed.

Protein function prediction plays an important role in the field of biology. With the wide application of deep learning in the field of bioinformatics, more and more natural language processing (NLP) technologies are applied to the downstream tasks in the field of bioinformatics, and it has also shown excellent performance in protein function prediction. Protein-protein interaction (PPI) networks and other biological attributes contain rich information critical for annotating protein functions. However, existing deep learning networks still suffer from overfitting and noise issues, resulting in low accuracy in protein function prediction. Consequently, developing efficient models for protein function prediction remains a popular and challenging topic in the application of NLP in bioinformatics. In this study, we propose a novel protein function prediction model based on attention mechanisms, termed IMAGO. This model employs the Transformer pre-training process, integrating multi-head attention mechanisms and regularization techniques, and optimizes the loss function to effectively reduce overfitting and noise issues during training. It generates more robust embeddings, ultimately improving the accuracy of protein function prediction. Experimental results on human and mouse datasets indicate that our model surpasses other protein function prediction models across multiple metrics. Thus, this efficient, stable, and accurate deep learning model holds significant promise for protein function prediction.

StarFunc: Fusing Template-based and Deep Learning Approaches for Accurate Protein Function Prediction.

MotivationIn recent years, protein function prediction has broken through the bottleneck of sequence features, significantly improving prediction accuracy using high-precision protein structures predicted by AlphaFold2. While single-species protein function prediction methods have achieved remarkable success, multi-species approaches still face challenges such as difficulties in multi-source data integration and insufficient knowledge transfer between distantly-related species. How to integrate large-scale data and provide effective cross-species label propagation for species with sparse protein annotations remains a critical and unresolved challenge. To address this problem, we propose the MSNGO (Multi-species protein Structures and Network to predict GO terms) model, which integrates structural features and network propagation methods. Our validation shows that using structural features can significantly improve the accuracy of multi-species protein function prediction.ResultsWe employ graph representation learning techniques to extract amino acid representations from protein structure contact maps and train a structural model using a graph convolution pooling module to derive protein-level structural features. After incorporating the sequence features from ESM-2, we apply a network propagation algorithm to aggregate information and update node representations within a heterogeneous network. The results demonstrate that MSNGO outperforms previous multi-species protein function prediction methods that rely on sequence features and protein-protein networks.Availability and implementationhttps://github.com/blingbell/MSNGO.

Motivation: Computational approaches that can predict protein functions are essential to bridge the widening function annotation gap especially since <1.0% of all proteins in UniProtKB have been experimentally characterized. We present a domain-based method for protein function classification and prediction of functional sites that exploits functional sub-classification of CATH superfamilies. The superfamilies are sub-classified into functional families (FunFams) using a hierarchical clustering algorithm supervised by a new classification method, FunFHMMer.Results: FunFHMMer generates more functionally coherent groupings of protein sequences than other domain-based protein classifications. This has been validated using known functional information. The conserved positions predicted by the FunFams are also found to be enriched in known functional residues. Moreover, the functional annotations provided by the FunFams are found to be more precise than other domain-based resources. FunFHMMer currently identifies 110 439 FunFams in 2735 superfamilies which can be used to functionally annotate > 16 million domain sequences.Availability and implementation: All FunFam annotation data are made available through the CATH webpages (http://www.cathdb.info). The FunFHMMer webserver (http://www.cathdb.info/search/by_funfhmmer) allows users to submit query sequences for assignment to a CATH FunFam.Contact:sayoni.das.12@ucl.ac.ukSupplementary information:Supplementary data are available at Bioinformatics online.

BackgroundIn the current climate of high-throughput computational biology, the inference of a protein's function from related measurements, such as protein-protein interaction relations, has become a canonical task. Most existing technologies pursue this task as a classification problem, on a term-by-term basis, for each term in a database, such as the Gene Ontology (GO) database, a popular rigorous vocabulary for biological functions. However, ontology structures are essentially hierarchies, with certain top to bottom annotation rules which protein function predictions should in principle follow. Currently, the most common approach to imposing these hierarchical constraints on network-based classifiers is through the use of transitive closure to predictions.ResultsWe propose a probabilistic framework to integrate information in relational data, in the form of a protein-protein interaction network, and a hierarchically structured database of terms, in the form of the GO database, for the purpose of protein function prediction. At the heart of our framework is a factorization of local neighborhood information in the protein-protein interaction network across successive ancestral terms in the GO hierarchy. We introduce a classifier within this framework, with computationally efficient implementation, that produces GO-term predictions that naturally obey a hierarchical 'true-path' consistency from root to leaves, without the need for further post-processing.ConclusionA cross-validation study, using data from the yeast Saccharomyces cerevisiae, shows our method offers substantial improvements over both standard 'guilt-by-association' (i.e., Nearest-Neighbor) and more refined Markov random field methods, whether in their original form or when post-processed to artificially impose 'true-path' consistency. Further analysis of the results indicates that these improvements are associated with increased predictive capabilities (i.e., increased positive predictive value), and that this increase is consistent uniformly with GO-term depth. Additional in silico validation on a collection of new annotations recently added to GO confirms the advantages suggested by the cross-validation study. Taken as a whole, our results show that a hierarchical approach to network-based protein function prediction, that exploits the ontological structure of protein annotation databases in a principled manner, can offer substantial advantages over the successive application of 'flat' network-based methods.

The prediction of protein function is a difficult and important problem in computational biology. In this study, an efficient method is presented to predict protein function with sequence composition information. Four kinds of basic building blocks of protein sequences are investigated, including N-grams, binary profiles, PFAM domains and InterPro domains. The protein sequences are mapped into high-dimensional vectors by using the occurrence frequencies of each kind of building blocks. The resulting vectors are then taken as input to support vector machine to predict their function based on gene ontology. Experiments are conducted over the subset of GOA database. The experimental results show that the protein function can be predicted from primary sequence information. The method based on InterPro domains outperforms the other building blocks, and gets an overall accuracy of 0.87 and ROC score is 0.93. We also demonstrate that the use of feature extraction algorithms such as latent semantic analysis and nonnegative matrix factorization, can efficiently remove noise and improve the prediction efficiency without significantly degrading the performance. The results obtained here are helpful for the prediction of protein function by using only sequence information.

As one of the recalcitrant challenges in life sciences and biomedicine, protein function prediction suffers from a deluge of AI-designed proteins, particularly having to face multi-modal information in the era of big data. Importing the high-throughput neural-network-based prediction framework to replace the low-throughput biological experiments, a universal multi-modal method is straightforward in addressing the growing gap between known sequences and predicting functions. To bridge the gap, we propose ProtGO, a three-step framework for predicting protein function, which leverages the credible Gene Ontology (GO) knowledge base and integrates four common modalities. Specifically, we first introduce frontier pre-trained protein language models (PLMs) for representation learning of mainstay functional protein sequences. For the remaining multi-modal data, we design a text alignment module for explainable text descriptions, a taxonomy encoding module for species-specific taxonomy, and a GO graph embedding module for biological GO relations. Each module is independent and adaptive for the referenced modalities. By harnessing these four knowledge representations, ProtGO maximizes the potential of GO resources, enhancing the performance of vanilla PLMs and biological language models (LMs) in downstream GO prediction tasks. Extensive experiments demonstrate that ProtGO significantly advances the abilities of state-of-the-art PLMs to predict protein functions: approximately 8% to 27% increase in the maximum F1 measure (Fmax) compared to base models. These comprehensive studies confirm ProtGO's capability to deliver outstanding performance in protein function prediction by utilizing a rich blend of functional and evolutionary knowledge. Our source code and all the data are available at https://github.com/sunyatawang/ProtGO.