Protein Function Annotation Research Articles

Prediction of protein-ATP binding residues using multi-view feature learning via contextual-based co-attention network

Accurately predicting protein-ATP binding residues is critical for protein function annotation and drug discovery. Computational methods dedicated to the prediction of binding residues based on protein sequence information have exhibited notable advancements in predictive accuracy. Nevertheless, these methods continue to grapple with several formidable challenges, including limited means of extracting more discriminative features and inadequate algorithms for integrating protein and residue information. To address the problems, we propose ATP-Deep, a novel protein-ATP binding residues predictor. ATP-Deep harnesses the capabilities of unsupervised pre-trained language models and incorporates domain-specific evolutionary context information from homologous sequences. It further refines the embedding at the residue level through integration with corresponding protein-level information and employs a contextual-based co-attention mechanism to adeptly fuse multiple sources of features. The performance evaluation results on the benchmark datasets reveal that ATP-Deep achieves an AUC of 0.954 and 0.951, respectively, surpassing the performance of the state-of-the-art model. These findings underscore the effectiveness of assimilating protein-level information and deploying a contextual-based co-attention mechanism grounded in context to bolster the prediction performance of protein-ATP binding residues.

MSF-PFP: A Novel Multisource Feature Fusion Model for Protein Function Prediction.

Protein function prediction is essential for disease treatment and drug development; yet, traditional biological experimental methods are less efficient in annotating protein function, and existing automated methods fail to fully leverage protein multisource data. Here, we present MSF-PFP, a computational framework that fuses multisource data features to predict protein function with high accuracy. Our framework designs specific models for feature extraction based on the characteristics of various data sources, including a global-local-individual strategy for local location features. MSF-PFP then integrates extracted features through a multisource feature fusion model, ultimately categorizing protein functions. Experimental results demonstrate that MSF-PFP outperforms eight state-of-the-art models, achieving FMax scores of 0.542, 0.675, and 0.624 for the biological process (BP), molecular function (MF), and cellular component (CC), respectively. The source code and data set for MSF-PFP are available at https://swanhub.co/TianGua/MSF-PFP, facilitating further exploration and validation of the proposed framework. This study highlights the potential of multisource data fusion in enhancing protein function prediction, contributing to improved disease therapy and medication discovery strategies.

AnnoPRO: a strategy for protein function annotation based on multi-scale protein representation and a hybrid deep learning of dual-path encoding

Protein function annotation has been one of the longstanding issues in biological sciences, and various computational methods have been developed. However, the existing methods suffer from a serious long-tail problem, with a large number of GO families containing few annotated proteins. Herein, an innovative strategy named AnnoPRO was therefore constructed by enabling sequence-based multi-scale protein representation, dual-path protein encoding using pre-training, and function annotation by long short-term memory-based decoding. A variety of case studies based on different benchmarks were conducted, which confirmed the superior performance of AnnoPRO among available methods. Source code and models have been made freely available at: https://github.com/idrblab/AnnoPRO and https://zenodo.org/records/10012272

CRAFT: a web-integrated cavity prediction tool based on flow transfer algorithm

Numerous computational methods, including evolutionary-based, energy-based, and geometrical-based methods, are utilized to identify cavities inside proteins. Cavity information aids protein function annotation, drug design, poly-pharmacology, and allosteric site investigation. This article introduces “flow transfer algorithm” for rapid and effective identification of diverse protein cavities through multidimensional cavity scan. Initially, it identifies delimiter and susceptible tetrahedra to establish boundary regions and provide seed tetrahedra. Seed tetrahedron faces are precisely scanned using the maximum circle radius to transfer seed flow to neighboring tetrahedra. Seed flow continues until terminated by boundaries or forbidden faces, where a face is forbidden if the estimated maximum circle radius is less or equal to the user-defined maximum circle radius. After a seed scanning, tetrahedra involved in the flow are clustered to locate the cavity. The CRAFT web interface integrates this algorithm for protein cavity identification with enhanced user control. It supports proteins with cofactors, hydrogens, and ligands and provides comprehensive features such as 3D visualization, cavity physicochemical properties, percentage contribution graphs, and highlighted residues for each cavity. CRAFT can be accessed through its web interface at http://pitools.niper.ac.in/CRAFT, complemented by the command version available at https://github.com/PGlab-NIPER/CRAFT/.Scientific contributionFlow transfer algorithm is a novel geometric approach for accurate and reliable prediction of diverse protein cavities. This algorithm employs a distinct concept involving maximum circle radius within the 3D Delaunay triangulation to address diverse van der Waals radii while existing methods overlook atom specific van der Waals radii or rely on complex weighted geometric techniques.

CAFA-evaluator: a Python tool for benchmarking ontological classification methods.

https://pypi.org/project/cafaeval.

Software for Predicting Binding Free Energy of Protein-Protein Complexes and Their Mutants.

Protein-protein binding affinity prediction is important for understanding complex biochemical pathways and to uncover protein interaction networks. Quantitative estimation of the binding affinity changes caused by mutations can provide critical information for protein function annotation and genetic disease diagnoses. The binding free energies of protein-protein complexes can be predicted using several computational tools. This chapter is a summary of software developed for the prediction of binding free energies for protein-protein complexes and their mutants.

FRAGSITE2: A structure and fragment-based approach for virtual ligand screening.

Protein function annotation and drug discovery often involve finding small molecule binders. In the early stages of drug discovery, virtual ligand screening (VLS) is frequently applied to identify possible hits before experimental testing. While our recent ligand homology modeling (LHM)-machine learning VLS method FRAGSITE outperformed approaches that combined traditional docking to generate protein-ligand poses and deep learning scoring functions to rank ligands, a more robust approach that could identify a more diverse set of binding ligands is needed. Here, we describe FRAGSITE2 that shows significant improvement on protein targets lacking known small molecule binders and no confident LHM identified template ligands when benchmarked on two commonly used VLS datasets: For both the DUD-E set and DEKOIS2.0 set and ligands having a Tanimoto coefficient (TC) < 0.7 to the template ligands, the 1% enrichment factor (EF1% ) of FRAGSITE2 is significantly better than those for FINDSITEcomb2.0 , an earlier LHM algorithm. For the DUD-E set, FRAGSITE2 also shows better ROC enrichment factor and AUPR (area under the precision-recall curve) than the deep learning DenseFS scoring function. Comparison with the RF-score-VS on the 76 target subset of DEKOIS2.0 and a TC < 0.99 to training DUD-E ligands, FRAGSITE2 has double the EF1% . Its boosted tree regression method provides for more robust performance than a deep learning multiple layer perceptron method. When compared with the pretrained language model for protein target features, FRAGSITE2 also shows much better performance. Thus, FRAGSITE2 is a promising approach that can discover novel hits for protein targets. FRAGSITE2's web service is freely available to academic users at http://sites.gatech.edu/cssb/FRAGSITE2.

In silico protein function prediction: the rise of machine learning-based approaches.

Proteins function as integral actors in essential life processes, rendering the realm of protein research a fundamental domain that possesses the potential to propel advancements in pharmaceuticals and disease investigation. Within the context of protein research, an imperious demand arises to uncover protein functionalities and untangle intricate mechanistic underpinnings. Due to the exorbitant costs and limited throughput inherent in experimental investigations, computational models offer a promising alternative to accelerate protein function annotation. In recent years, protein pre-training models have exhibited noteworthy advancement across multiple prediction tasks. This advancement highlights a notable prospect for effectively tackling the intricate downstream task associated with protein function prediction. In this review, we elucidate the historical evolution and research paradigms of computational methods for predicting protein function. Subsequently, we summarize the progress in protein and molecule representation as well as feature extraction techniques. Furthermore, we assess the performance of machine learning-based algorithms across various objectives in protein function prediction, thereby offering a comprehensive perspective on the progress within this field.

GHGPR-PPIS: A graph convolutional network for identifying protein-protein interaction site using heat kernel with Generalized PageRank techniques and edge self-attention feature processing block

Accurately pinpointing protein-protein interaction site (PPIS) on the molecular level is of utmost significance for annotating protein function and comprehending the mechanisms underpinning various diseases. While numerous computational methods for predicting PPIS have emerged, they have indeed mitigated the labor and time constraints associated with traditional experimental methods. However, the predictive accuracy of these methods has yet to reach the desired threshold. In this context, we proposed a groundbreaking graph-based computational model called GHGPR-PPIS. This innovative model leveraged a graph convolutional network using heat kernel (GraphHeat) in conjunction with Generalized PageRank techniques (GHGPR) to predict PPIS. Additionally, building upon the GHGPR framework, we devised an edge self-attention feature processing block, further augmenting the performance of the model. Experimental findings conclusively demonstrated that GHGPR-PPIS surpassed all competing state-of-the-art models when evaluated on the benchmark test set. Impressively, on two distinct independent test sets and a specific protein chain, GHGPR-PPIS consistently demonstrated superior generalization performance and practical applicability compared to the comparative model, AGAT-PPIS. Lastly, leveraging the t-SNE dimensionality reduction algorithm and clustering visualization technique, we delved into an interpretability analysis of the effectiveness of GHGPR-PPIS by meticulously comparing the outputs from different stages of the model.

An Evolutionary-Based Mutation With Functional Annotation to Identify Protein Complexes Within PPI Networks

The research deals with an evolutionary-based mutation with functional annotation to identify protein complexes within PPI networks. An important field of research in computational biology is the difficult and fundamental challenge of revealing complexes in protein interaction networks. The complex detection models that have been developed to tackle challenges are mostly dependent on topological properties and rarely use the biological properties of PPI networks. This research aims to push the evolutionary algorithm to its maximum by employing gene ontology (GO) to communicate across proteins based on biological information similarity for direct genes. The outcomes show that the suggested method can be utilized to improve the predictability of the complexes identified. The GO functional annotation of proteins as a heuristic guide is injected into the framework of single-objective evolutionary algorithms (EAs), while the complex detection community score (CS) model works as a fitness function in EAs. In the experiments, we analyzed the performance of our proposed algorithm when applied to the publicly accessible yeast protein networks. The results show a considerable improvement in the detection ability of complexes in the PPI network.

DbAPIS: a database of anti-prokaryotic immune system genes.

Anti-prokaryotic immune system (APIS) proteins, typically encoded by phages, prophages, and plasmids, inhibit prokaryotic immune systems (e.g. restriction modification, toxin-antitoxin, CRISPR-Cas). A growing number of APIS genes have been characterized and dispersed in the literature. Here we developed dbAPIS (https://bcb.unl.edu/dbAPIS), as the first literature curated data repository for experimentally verified APIS genes and their associated protein families. The key features of dbAPIS include: (i) experimentally verified APIS genes with their protein sequences, functional annotation, PDB or AlphaFold predicted structures, genomic context, sequence and structural homologs from different microbiome/virome databases; (ii) classification of APIS proteins into sequence-based families and construction of hidden Markov models (HMMs); (iii) user-friendly web interface for data browsing by the inhibited immune system types or by the hosts, and functions for searching and batch downloading of pre-computed data; (iv) Inclusion of all types of APIS proteins (except for anti-CRISPRs) that inhibit a variety of prokaryotic defense systems (e.g. RM, TA, CBASS, Thoeris, Gabija). The current release of dbAPIS contains 41 verified APIS proteins and ∼4400 sequence homologs of 92 families and 38 clans. dbAPIS will facilitate the discovery of novel anti-defense genes and genomic islands in phages, by providing a user-friendly data repository and a web resource for an easy homology search against known APIS proteins.

Relative Abundance of Spermadhesin-1 in the Seminal Plasma of Young Nellore Bulls Is in Agreement with Reproductive Parameters.

This study aimed to evaluate the proteomic profile of seminal plasma from young Nellore bulls. We used 20 bulls aged between 19.8 and 22.7 months, divided into two groups according to the results of the Breeding Soundness Evaluation (BSE): approved (FIT n = 10) and not approved (UNFIT n = 10). The scrotal perimeter was measured and a semen collection was performed through electroejaculation. The percentage of sperm motility, mass motility, and sperm vigor were calculated using conventional microscopy, and the percentage of sperm abnormalities was calculated using phase-contrast microscopy of all ejaculates. Seminal plasma was separated from spermatozoa using centrifugation and processed for proteomic analysis by LC-MS/MS. Seminal plasma proteins were identified using MASCOT Daemon software v.2.4.0 and label-free quantification analysis was carried out by SCAFFOLD Q+ software v.4.0 using the Exponentially Modified Protein Abundance Index (emPAI) method. Functional classification of proteins was performed based on their genetic ontology terms using KOG. Functional cluster analysis was performed on DAVID. There were no differences in scrotal perimeter and physical semen characteristics between FIT and UNFIT groups of bulls. The percentage of sperm abnormalities was higher (p < 0.05) in the UNFIT group of bulls. A total of 297 proteins were identified for the two groups. There were a total of 11 differentially abundant proteins (p < 0.05), two of them more abundant in FIT bulls (Spermadhesin-1 and Ig gamma-1 chain C region) and nine in UNFIT bulls (Vasoactive intestinal peptide, Metalloproteinase inhibitor 2, Ig lambda-1 chain C regions, Protein FAM3C, Hemoglobin beta, Seminal ribonuclease, Spermadhesin 2, Seminal plasma protein BSP-30kDa, and Spermadhesin Z13). Spermadhesin-1 was the protein with the highest relative abundance (36.7%) in the seminal plasma among all bulls, corresponding to 47.7% for the FIT bulls and 25,7% for the UNFIT bulls. Posttranslational modification, protein turnover, and chaperones were the functional categories with the highest number of classified proteins. Protein functional annotation clusters were related to Phospholipid efflux, ATP binding, and chaperonin-containing T-complex. The differentially abundant proteins in the group of FIT bulls were related to sperm capacitation and protection against reactive species of oxygen. In contrast, differentially expressed proteins in the group of UNFIT bulls were related to motility inhibition, intramembrane cholesterol removal and oxidative stress. In conclusion, the proteomic profile of the seminal plasma of FIT bulls presents proteins with participation in several biological processes favorable to fertilization, while the proteins of the seminal plasma of UNFIT bulls indicate a series of alterations that can compromise the fertilizing capacity of the spermatozoa. In addition, the relative abundance of spermadhesin-1 found in the seminal plasma of young Nellore bulls could be studied as a reproductive parameter for selection.

Protein Function Prediction With Functional and Topological Knowledge of Gene Ontology.

Gene Ontology (GO) is a widely used bioinformatics resource for describing biological processes, molecular functions, and cellular components of proteins. It covers more than 5000 terms hierarchically organized into a directed acyclic graph and known functional annotations. Automatically annotating protein functions by using GO-based computational models has been an area of active research for a long time. However, due to the limited functional annotation information and complex topological structures of GO, existing models cannot effectively capture the knowledge representation of GO. To solve this issue, we present a method that fuses the functional and topological knowledge of GO to guide protein function prediction. This method employs a multi-view GCN model to extract a variety of GO representations from functional information, topological structure, and their combinations. To dynamically learn the significance weights of these representations, it adopts an attention mechanism to learn the final knowledge representation of GO. Furthermore, it uses a pre-trained language model (i.e., ESM-1b) to efficiently learn biological features for each protein sequence. Finally, it obtains all predicted scores by calculating the dot product of sequence features and GO representation. Our method outperforms other state-of-the-art methods, as demonstrated by the experimental results on datasets from three different species, namely Yeast, Human and Arabidopsis. Our proposed method's code can be accessed at: https://github.com/Candyperfect/Master.

HNetGO: protein function prediction via heterogeneous network transformer.

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

DeepSG2PPI: A Protein-Protein Interaction Prediction Method Based on Deep Learning.

Protein-protein interaction (PPI) plays an important role in almost all life activities. Many protein interaction sites have been confirmed by biological experiments, but these PPI site identification methods are time-consuming and expensive. In this study, a deep learning-based PPI prediction method, named DeepSG2PPI, is developed. Firstly, the protein sequence information is retrieved and the local context information of each amino acid residue is calculated. A two-dimensional convolutional neural network (2D-CNN) model is employed to extract features from a two-channel coding structure, in which an attention mechanism is embedded to assign higher weights to key features. Secondly, the global statistical information of each amino acid residue and the relationship graph between the protein and GO (Gene Ontology) function annotation are built, and the graph embedding vector is constructed to represent the biological features of the protein. Finally, a 2D-CNN model and two 1D-CNN models are combined for PPI prediction. The comparison analysis with existing algorithms shows that the DeepSG2PPI method has better performance. It provides more accurate and effective PPI site prediction, which will be helpful in reducing the cost and failure rate of biological experiments.

HiFun: homology independent protein function prediction by a novel protein-language self-attention model.

Protein function prediction based on amino acid sequence alone is an extremely challenging but important task, especially in metagenomics/metatranscriptomics field, in which novel proteins have been uncovered exponentially from new microorganisms. Many of them are extremely low homology to known proteins and cannot be annotated with homology-based or information integrative methods. To overcome this problem, we proposed a Homology Independent protein Function annotation method (HiFun) based on a unified deep-learning model by reassembling the sequence as protein language. The robustness of HiFun was evaluated using the benchmark datasets and metrics in the CAFA3 challenge. To navigate the utility of HiFun, we annotated 2 212 663 unknown proteins and discovered novel motifs in the UHGP-50 catalog. We proved that HiFun can extract latent function related structure features which empowers it ability to achieve function annotation for non-homology proteins. HiFun can substantially improve newly proteins annotation and expand our understanding of microorganisms' adaptation in various ecological niches. Moreover, we provided a free and accessible webservice at http://www.unimd.org/HiFun, requiring only protein sequences as input, offering researchers an efficient and practical platform for predicting protein functions.

Domain Architecture Based Methods for Comparative Functional Genomics Toward Therapeutic Drug Target Discovery.

Genes duplicate, mutate, recombine, fuse or fission to produce new genes, or when genes are formed from de novo, novel functions arise during evolution. Researchers have tried to quantify the causes of these molecular diversification processes to know how these genes increase molecular complexity over a period of time, for instance protein domain organization. In contrast to global sequence similarity, protein domain architectures can capture key structural and functional characteristics, making them better proxies for describing functional equivalence. In Prokaryotes and eukaryotes it has proven that, domain designs are retained over significant evolutionary distances. Protein domain architectures are now being utilized to categorize and distinguish evolutionarily related proteins and find homologs among species that are evolutionarily distant from one another. Additionally, structural information stored in domain structures has accelerated homology identification and sequence search methods. Tools for functional protein annotation have been developed to discover, protein domain content, domain order, domain recurrence, and domain position as all these contribute to the prediction of protein functional accuracy. In this review, an attempt is made to summarise facts and speculations regarding the use of protein domain architecture and modularity to identify possible therapeutic targets among cellular activities based on the understanding their linked biological processes.

Functional annotation of proteins for signaling network inference in non-model species

Molecular biology aims to understand cellular responses and regulatory dynamics in complex biological systems. However, these studies remain challenging in non-model species due to poor functional annotation of regulatory proteins. To overcome this limitation, we develop a multi-layer neural network that determines protein functionality directly from the protein sequence. We annotate kinases and phosphatases in Glycine max. We use the functional annotations from our neural network, Bayesian inference principles, and high resolution phosphoproteomics to infer phosphorylation signaling cascades in soybean exposed to cold, and identify Glyma.10G173000 (TOI5) and Glyma.19G007300 (TOT3) as key temperature regulators. Importantly, the signaling cascade inference does not rely upon known kinase motifs or interaction data, enabling de novo identification of kinase-substrate interactions. Conclusively, our neural network shows generalization and scalability, as such we extend our predictions to Oryza sativa, Zea mays, Sorghum bicolor, and Triticum aestivum. Taken together, we develop a signaling inference approach for non-model species leveraging our predicted kinases and phosphatases.

CoCoNat: a novel method based on deep learning for coiled-coil prediction.

Coiled-coil domains (CCD) are widespread in all organisms and perform several crucial functions. Given their relevance, the computational detection of CCD is very important for protein functional annotation. State-of-the-art prediction methods include the precise identification of CCD boundaries, the annotation of the typical heptad repeat pattern along the coiled-coil helices as well as the prediction of the oligomerization state. In this article, we describe CoCoNat, a novel method for predicting coiled-coil helix boundaries, residue-level register annotation, and oligomerization state. Our method encodes sequences with the combination of two state-of-the-art protein language models and implements a three-step deep learning procedure concatenated with a Grammatical-Restrained Hidden Conditional Random Field for CCD identification and refinement. A final neural network predicts the oligomerization state. When tested on a blind test set routinely adopted, CoCoNat obtains a performance superior to the current state-of-the-art both for residue-level and segment-level CCD. CoCoNat significantly outperforms the most recent state-of-the-art methods on register annotation and prediction of oligomerization states. CoCoNat web server is available at https://coconat.biocomp.unibo.it. Standalone version is available on GitHub at https://github.com/BolognaBiocomp/coconat.

Large-scale predicting protein functions through heterogeneous feature fusion.

As the volume of protein sequence and structure data grows rapidly, the functions of the overwhelming majority of proteins cannot be experimentally determined. Automated annotation of protein function at a large scale is becoming increasingly important. Existing computational prediction methods are typically based on expanding the relatively small number of experimentally determined functions to large collections of proteins with various clues, including sequence homology, protein-protein interaction, gene co-expression, etc. Although there has been some progress in protein function prediction in recent years, the development of accurate and reliable solutions still has a long way to go. Here we exploit AlphaFold predicted three-dimensional structural information, together with other non-structural clues, to develop a large-scale approach termed PredGO to annotate Gene Ontology (GO) functions for proteins. We use a pre-trained language model, geometric vector perceptrons and attention mechanisms to extract heterogeneous features of proteins and fuse these features for function prediction. The computational results demonstrate that the proposed method outperforms other state-of-the-art approaches for predicting GO functions of proteins in terms of both coverage and accuracy. The improvement of coverage is because the number of structures predicted by AlphaFold is greatly increased, and on the other hand, PredGO can extensively use non-structural information for functional prediction. Moreover, we show that over 205 000 ($\sim $100%) entries in UniProt for human are annotated by PredGO, over 186 000 ($\sim $90%) of which are based on predicted structure. The webserver and database are available at http://predgo.denglab.org/.