Query Protein Research Articles

Predicting protein synergistic effect in Arabidopsis using epigenome profiling

Histone modifications can regulate transcription epigenetically by marking specific genomic loci, which can be mapped using chromatin immunoprecipitation sequencing (ChIP-seq). Here we present QHistone, a predictive database of 1534 ChIP-seqs from 27 histone modifications in Arabidopsis, offering three key functionalities. Firstly, QHistone employs machine learning to predict the epigenomic profile of a query protein, characterized by its most associated histone modifications, and uses these modifications to infer the protein’s role in transcriptional regulation. Secondly, it predicts synergistic regulatory activities between two proteins by comparing their profiles. Lastly, it detects previously unexplored co-regulating protein pairs by screening all known proteins. QHistone accurately identifies histone modifications associated with specific known proteins, and allows users to computationally validate their results using gene expression data from various plant tissues. These functions demonstrate an useful approach to utilizing epigenome data for gene regulation analysis, making QHistone a valuable resource for the scientific community (https://qhistone.paoyang.ipmb.sinica.edu.tw).

Improving protein-protein interaction prediction using protein language model and protein network features

Interactions between proteins are ubiquitous in a wide variety of biological processes. Accurately identifying the protein-protein interaction (PPI) is of significant importance for understanding the mechanisms of protein functions and facilitating drug discovery. Although the wet-lab technological methods are the best way to identify PPI, their major constraints are their time-consuming nature, high cost, and labor-intensiveness. Hence, lots of efforts have been made towards developing computational methods to improve the performance of PPI prediction. In this study, we propose a novel hybrid computational method (called KSGPPI) that aims at improving the prediction performance of PPI via extracting the discriminative information from protein sequences and interaction networks. The KSGPPI model comprises two feature extraction modules. In the first feature extraction module, a large protein language model, ESM-2, is employed to exploit the global complex patterns concealed within protein sequences. Subsequently, feature representations are further extracted through CKSAAP, and a two-dimensional convolutional neural network (CNN) is utilized to capture local information. In the second feature extraction module, the query protein acquires its similar protein from the STRING database via the sequence alignment tool NW-align and then captures the graph embedding feature for the query protein in the protein interaction network of the similar protein using the algorithm of Node2vec. Finally, the features of these two feature extraction modules are efficiently fused; the fused features are then fed into the multilayer perceptron to predict PPI. The results of five-fold cross-validation on the used benchmarked datasets demonstrate that KSGPPI achieves an average prediction accuracy of 88.96 %. Additionally, the average Matthews correlation coefficient value (0.781) of KSGPPI is significantly higher than that of those state-of-the-art PPI prediction methods. The standalone package of KSGPPI is freely downloaded at https://github.com/rickleezhe/KSGPPI.

PPI3D: a web server for searching, analyzing and modeling protein-protein, protein-peptide and protein-nucleic acid interactions.

Structure-resolved protein interactions with other proteins, peptides and nucleic acids are key for understanding molecular mechanisms. The PPI3D web server enables researchers to query preprocessed and clustered structural data, analyze the results and make homology-based inferences for protein interactions. PPI3D offers three interaction exploration modes: (i) all interactions for proteins homologous to the query, (ii) interactions between two proteins or their homologsand (iii) interactions within a specific PDB entry. The server allows interactive analysis of the identified interactions in both summarized and detailed manner. This includes protein annotations, structures, the interface residues and the corresponding contact surface areas. In addition, users can make inferences about residues at the interaction interface for the query protein(s) from the sequence alignments and homology models. The weekly updated PPI3D database includes all the interaction interfaces and binding sites from PDB, clustered based on both protein sequence and structural similarity, yielding non-redundant datasets without loss of alternative interaction modes. Consequently, the PPI3D users avoid being flooded with redundant information, a typical situation for intensely studied proteins. Furthermore, PPI3D provides a possibility to download user-defined sets of interaction interfaces and analyze them locally. The PPI3D web server is available at https://bioinformatics.lt/ppi3d.

Prediction of interactions between cell surface proteins by machine learning.

Cells detect changes in their external environments or communicate with each other through proteins on their surfaces. These cell surface proteins form a complicated network of interactions in order to fulfill their functions. The interactions between cell surface proteins are highly dynamic and, thus, challenging to detect using traditional experimental techniques. Here, we tackle this challenge using a computational framework. The primary focus of the framework is to develop new tools to identify interactions between domains in the immunoglobulin (Ig) fold, which is the most abundant domain family in cell surface proteins. These interactions could be formed between ligands and receptors from different cells or between proteins on the same cell surface. In practice, we collected all structural data on Ig domain interactions and transformed them into an interface fragment pair library. A high-dimensional profile can then be constructed from the library for a given pair of query protein sequences. Multiple machine learning models were used to read this profile so that the probability of interaction between the query proteins could be predicted. We tested our models on an experimentally derived dataset that contains 564 cell surface proteins in humans. The cross-validation results show that we can achieve higher than 70% accuracy in identifying the PPIs within this dataset. We then applied this method to a group of 46 cell surface proteins in Caenorhabditis elegans. We screened every possible interaction between these proteins. Many interactions recognized by our machine learning classifiers have been experimentally confirmed in the literature. In conclusion, our computational platform serves as a useful tool to help identify potential new interactions between cell surface proteins in addition to current state-of-the-art experimental techniques. The tool is freely accessible for use by the scientific community. Moreover, the general framework of the machine learning classification can also be extended to study the interactions of proteins in other domain superfamilies.

ResCNNT-fold: Combining residual convolutional neural network and Transformer for protein fold recognition from language model embeddings

A comprehensive understanding of protein functions holds significant promise for disease research and drug development, and proteins with analogous tertiary structures tend to exhibit similar functions. Protein fold recognition stands as a classical approach in the realm of protein structure investigation. Despite significant advancements made by researchers in this field, the continuous updating of protein databases presents an ongoing challenge in accurately identifying protein fold types. In this study, we introduce a predictor, ResCNNT-fold, for protein fold recognition and employ the LE dataset for testing purpose. ResCNNT-fold leverages a pre-trained language model to obtain embedding representations for protein sequences, which are then processed by the ResCNNT feature extractor, a combination of residual convolutional neural network and Transformer, to derive fold-specific features. Subsequently, the query protein is paired with each protein whose structure is known in the template dataset. For each pair, the similarity score of their fold-specific features is calculated. Ultimately, the query protein is identified as the fold type of the template protein in the pair with the highest similarity score. To further validate the utility and efficacy of the proposed ResCNNT-fold predictor, we conduct a 2-fold cross-validation experiment on the fold level of the LE dataset. Remarkably, this rigorous evaluation yields an exceptional accuracy of 91.57%, which surpasses the best result among other state-of-the-art protein fold recognition methods by an approximate margin of 10%. The excellent performance unequivocally underscores the compelling advantages inherent to our proposed ResCNNT-fold predictor in the realm of protein fold recognition. The source code and data of ResCNNT-fold can be downloaded from https://github.com/Bioinformatics-Laboratory/ResCNNT-fold.

Optimal selection of suitable templates in protein interface prediction.

Molecular-level classification of protein-protein interfaces can greatly assist in functional characterization and rational drug design. The most accurate protein interface predictions rely on finding homologous proteins with known interfaces since most interfaces are conserved within the same protein family. The accuracy of these template-based prediction approaches depends on the correct choice of suitable templates. Choosing the right templates in the immunoglobulin superfamily (IgSF) is challenging because its members share low sequence identity and display a wide range of alternative binding sites despite structural homology. We present a new approach to predict protein interfaces. First, template-specific, informative evolutionary profiles are established using a mutual information-based approach. Next, based on the similarity of residue level conservation scores derived from the evolutionary profiles, a query protein is hierarchically clustered with all available template proteins in its superfamily with known interface definitions. Once clustered, a subset of the most closely related templates is selected, and an interface prediction is made. These initial interface predictions are subsequently refined by extensive docking. This method was benchmarked on 51 IgSF proteins and can predict nontrivial interfaces of IgSF proteins with an average and median F-score of 0.64 and 0.78, respectively. We also provide a way to assess the confidence of the results. The average and median F-scores increase to 0.8 and 0.81, respectively, if 27% of low confidence cases and 17% of medium confidence cases are removed. Lastly, we provide residue level interface predictions, protein complexes, and confidence measurements for singletons in the IgSF. Source code is freely available at: https://gitlab.com/fiserlab.org/interdct_with_refinement.

Identifying Metal Binding Sites in Proteins Using Homologous Structures, the MADE Approach.

In order to identify the locations of metal ions in the binding sites of proteins, we have developed a method named the MADE (MAcromolecular DEnsity and Structure Analysis) approach. The MADE approach represents an evolution of our previous toolset, the ProBiS H2O (MD) methodology, for the identification of conserved water molecules. Our method uses experimental structures of proteins homologous to a query, which are subsequently superimposed upon it. Areas with a particular species present in a similar location among many homologous protein structures are identified using a clustering algorithm. Dense clusters likely represent positions containing species important to the query protein structure or function. We analyze well-characterized apo protein structures and show that the MADE approach can identify clusters corresponding to the expected positions of metal ions in their binding sites. The greatest advantage of our method lies in its generality. It can in principle be applied to any species found in protein records; it is not only limited to metal ions. We additionally demonstrate that the MADE approach can be successfully applied to predict the location of cofactors in computer-modeled structures, e.g., via AlphaFold. We also conduct a careful protein superposition method comparison and find our methodology robust and the results largely independent of the selected protein superposition algorithm. We postulate that with increasing structural data availability, additional applications of the MADE approach will be possible such as non-protein systems, water network identification, protein binding site elaboration, and analysis of binding events, all in a dynamic manner. We have implemented the MADE approach as a plugin for the PyMOL molecular visualization tool. The MADE plugin is available free of charge at https://gitlab.com/Jukic/made_software.

NRPreTo: A Machine Learning-Based Nuclear Receptor and Subfamily Prediction Tool.

The nuclear receptor (NR) superfamily includes phylogenetically related ligand-activated proteins, which play a key role in various cellular activities. NR proteins are subdivided into seven subfamilies based on their function, mechanism, and nature of the interacting ligand. Developing robust tools to identify NR could give insights into their functional relationships and involvement in disease pathways. Existing NR prediction tools only use a few types of sequence-based features and are tested on relatively similar independent datasets; thus, they may suffer from overfitting when extended to new genera of sequences. To address this problem, we developed Nuclear Receptor Prediction Tool (NRPreTo), a two-level NR prediction tool with a unique training approach where in addition to the sequence-based features used by existing NR prediction tools, six additional feature groups depicting various physiochemical, structural, and evolutionary features of proteins were utilized. The first level of NRPreTo allows for the successful prediction of a query protein as NR or non-NR and further subclassifies the protein into one of the seven NR subfamilies in the second level. We developed Random Forest classifiers to test on benchmark datasets, as well as the entire human protein datasets from RefSeq and Human Protein Reference Database (HPRD). We observed that using additional feature groups improved the performance. We also observed that NRPreTo achieved high performance on the external datasets and predicted 59 novel NRs in the human proteome. The source code of NRPreTo is publicly available at https://github.com/bozdaglab/NRPreTo.

Fast and accurate protein structure search with Foldseek

As structure prediction methods are generating millions of publicly available protein structures, searching these databases is becoming a bottleneck. Foldseek aligns the structure of a query protein against a database by describing tertiary amino acid interactions within proteins as sequences over a structural alphabet. Foldseek decreases computation times by four to five orders of magnitude with 86%, 88% and 133% of the sensitivities of Dali, TM-align and CE, respectively.

PrePPI: A Structure Informed Proteome-wide Database of Protein–Protein Interactions

We present an updated version of the Predicting Protein-Protein Interactions (PrePPI) webserver which predicts PPIs on a proteome-wide scale. PrePPI combines structural and non-structural evidence within a Bayesian framework to compute a likelihood ratio (LR) for essentially every possible pair of proteins in a proteome; the current database is for the human interactome. The structural modeling (SM) component is derived from template-based modeling and its application on a proteome-wide scale is enabled by a unique scoring function used to evaluate a putative complex. The updated version of PrePPI leverages AlphaFold structures that are parsed into individual domains. As has been demonstrated in earlier applications, PrePPI performs extremely well as measured by receiver operating characteristic curves derived from testing on E. coli and human protein–protein interaction (PPI) databases. A PrePPI database of ∼1.3 million human PPIs can be queried with a webserver application that comprises multiple functionalities for examining query proteins, template complexes, 3D models for predicted complexes, and related features (https://honiglab.c2b2.columbia.edu/PrePPI). PrePPI is a state-of-the-art resource that offers an unprecedented structure-informed view of the human interactome.

PrePCI: A structure- and chemical similarity-informed database of predicted protein compound interactions.

We describe the Predicting Protein-Compound Interactions (PrePCI) database which comprises over 5 billion predicted interactions between 6.8 million chemical compounds and 19,797 human proteins. PrePCI relies on a proteome-wide database of structural models based on both traditional modeling techniques and the AlphaFold Protein Structure Database. Sequence- and structural similarity-based metrics are established between template proteins, T, in the Protein Data Bank that bind compounds, C, and query proteins in the model database, Q. When the metrics exceed threshold values, it is assumed that C also binds to Q with a likelihood ratio (LR) derived from machine learning. If the relationship is based on structural similarity, the LR is based on a scoring function that measures the extent to which C is compatible with the binding site of Q as described in the LT-scanner algorithm. For every predicted complex derived in this way, chemical similarity based on the Tanimoto coefficient identifies other small molecules that may bind to Q. An overall LR for the binding of C to Q is obtained from Naive Bayesian statistics. The PrePCI database can be queried by entering a UniProt ID or gene name for a protein to obtain a list of compounds predicted to bind to it along with associated LRs. Alternatively, entering an identifier for the compound outputs a list of proteins it is predicted to bind. Specific applications of the database to lead discovery, elucidation of drug mechanism of action, and biological function annotation are described.

Using evolutionary data to make sense of macromolecules with a "face-lifted" ConSurf.

The ConSurf web-sever for the analysis of proteins, RNA, and DNA provides a quick and accurate estimate of the per-site evolutionary rate among homologues. The analysis reveals functionally important regions, such as catalytic and ligand-binding sites, which often evolve slowly. Since the last report in 2016, ConSurf has been improved in multiple ways. It now has a user-friendly interface that makes it easier to perform the analysis and to visualize the results. Evolutionary rates are calculated based on a set of homologous sequences, collected using hidden Markov model-based search tools, recently embedded in the pipeline. Using these, and following the removal of redundancy, ConSurf assembles a representative set of effective homologues for protein and nucleic acid queries to enable informative analysis of the evolutionary patterns. The analysis is particularly insightful when the evolutionary rates are mapped on the macromolecule structure. In this respect, the availability of AlphaFold model structures of essentially all UniProt proteins makes ConSurf particularly relevant to the research community. The UniProt ID of a query protein with an available AlphaFold model can now be used to start a calculation. Another important improvement is the Python re-implementation of the entire computational pipeline, making it easier to maintain. This Python pipeline is now available for download as a standalone version. We demonstrate some of ConSurf's key capabilities by the analysis of caveolin-1, the main protein of membrane invaginations called caveolae.

Improving DNA-Binding Protein Prediction Using Three-Part Sequence-Order Feature Extraction and a Deep Neural Network Algorithm.

Identification of the DNA-binding protein (DBP) helps dig out information embedded in the DNA-protein interaction, which is significant to understanding the mechanisms of DNA replication, transcription, and repair. Although existing computational methods for predicting the DBPs based on protein sequences have obtained great success, there is still room for improvement since the sequence-order information is not fully mined in these methods. In this study, a new three-part sequence-order feature extraction (called TPSO) strategy is developed to extract more discriminative information from protein sequences for predicting the DBPs. For each query protein, TPSO first divides its primary sequence features into N- and C-terminal fragments and then extracts the numerical pseudo features of three parts including the full sequence and these two fragments, respectively. Based on TPSO, a novel deep learning-based method, called TPSO-DBP, is proposed, which employs the sequence-based single-view features, the bidirectional long short-term memory (BiLSTM) and fully connected (FC) neural networks to learn the DBP prediction model. Empirical outcomes reveal that TPSO-DBP can achieve an accuracy of 87.01%, covering 85.30% of all DBPs, while achieving a Matthew's correlation coefficient value (0.741) that is significantly higher than most existing state-of-the-art DBP prediction methods. Detailed data analyses have indicated that the advantages of TPSO-DBP lie in the utilization of TPSO, which helps extract more concealed prominent patterns, and the deep neural network framework composed of BiLSTM and FC that learns the nonlinear relationships between input features and DBPs. The standalone package and web server of TPSO-DBP are freely available at https://jun-csbio.github.io/TPSO-DBP/.

Structome: a tool for the rapid assembly of datasets for structural phylogenetics.

Protein structures carry signal of common ancestry and can therefore aid in reconstructing their evolutionary histories. To expedite the structure-informed inference process, a web server, Structome, has been developed that allows users to rapidly identify protein structures similar to a query protein and to assemble datasets useful for structure-based phylogenetics. Structome was created by clustering of the structures in RCSB PDB using 90% sequence identity and representing each cluster by a centroid structure. Structure similarity between centroid proteins was calculated, and annotations from PDB, SCOP, and CATH were integrated. To illustrate utility, an H3 histone was used as a query, and results show that the protein structures returned by Structome span both sequence and structural diversity of the histone fold. Additionally, the pre-computed nexus-formatted distance matrix, provided by Structome, enables analysis of evolutionary relationships between proteins not identifiable using searches based on sequence similarity alone. Our results demonstrate that, beginning with a single structure, Structome can be used to rapidly generate a dataset of structural neighbours and allows deep evolutionary history of proteins to be studied. Structome is available at: https://structome.bii.a-star.edu.sg.

Contact-Assisted Threading in Low-Homology Protein Modeling.

The ability to successfully predict the three-dimensional structure of a protein from its amino acid sequence has made considerable progress in the recent past. The progress is propelled by the improved accuracy of deep learning-based inter-residue contact map predictors coupled with the rising growth of protein sequence databases. Contact map encodes interatomic interaction information that can be exploited for highly accurate prediction of protein structures via contact map threading even for the query proteins that are not amenable to direct homology modeling. As such, contact-assisted threading has garnered considerable research effort. In this chapter, we provide an overview of existing contact-assisted threading methods while highlighting the recent advances and discussing some of the current limitations and future prospects in the application of contact-assisted threading for improving the accuracy of low-homology protein modeling.

CyanoMapDB: a database integrating experimentally validated protein-protein interactions in cyanobacteria.

As one of the essential life forms in the biosphere, research on cyanobacteria has been growing remarkably for decades. Biological functions in organisms are often accomplished through protein-protein interactions (PPIs), which help to regulate interacting proteins or organize them into an integral machine. However, the study of PPIs in cyanobacteria falls far behind that in mammals and has not been integrated for ease of use. Thus, we built CyanoMapDB (http://www.cyanomapdb.msbio.pro/), a database providing cyanobacterial PPIs with experimental evidence, consisting of 52,304 PPIs among 6,789 proteins from 23 cyanobacterial species. We collected available data in UniProt, STRING, and IntAct, and mined numerous PPIs from co-fractionation MS data in cyanobacteria. The integrated data are accessible in CyanoMapDB (http://www.cyanomapdb.msbio.pro/), enabling users to easily query proteins of interest, investigate interacting proteins with evidence from different sources, and acquire a visual network of the target protein. We believe that CyanoMapDB will promote research involved with cyanobacteria and plants.

Protein-DNA Binding Residue Prediction via Bagging Strategy and Sequence-Based Cube-Format Feature.

Protein-DNA interactions play an important role in diverse biological processes. Accurately identifying protein-DNA binding residues is a critical but challenging task for protein function annotations and drug design. Although wet-lab experimental methods are the most accurate way to identify protein-DNA binding residues, they are time consuming and labor intensive. There is an urgent need to develop computational methods to rapidly and accurately predict protein-DNA binding residues. In this study, we propose a novel sequence-based method, named PredDBR, for predicting DNA-binding residues. In PredDBR, for each query protein, its position-specific frequency matrix (PSFM), predicted secondary structure (PSS), and predicted probabilities of ligand-binding residues (PPLBR) are first generated as three feature sources. Secondly, for each feature source, the sliding window technique is employed to extract the matrix-format feature of each residue. Then, we design two strategies, i.e., square root (SR) and average (AVE), to separately transform PSFM-based and two predicted feature source-based, i.e., PSS-based and PPLBR-based, matrix-format features of each residue into three corresponding cube-format features. Finally, after serially combining the three cube-format features, the ensemble classifier is generated via applying bagging strategy to multiple base classifiers built by the framework of 2D convolutional neural network. The computational experimental results demonstrate that the proposed PredDBR achieves an average overall accuracy of 93.7% and a Mathew's correlation coefficient of 0.405 on two independent validation datasets and outperforms several state-of-the-art sequenced-based protein-DNA binding residue predictors. The PredDBR web-server is available at https://jun-csbio.github.io/PredDBR/.

ProBiS-Fold Approach for Annotation of Human Structures from the AlphaFold Database with No Corresponding Structure in the PDB to Discover New Druggable Binding Sites.

ProBiS (Protein Binding Sites), a local structure-based comparison algorithm, is used in the new ProBiS-Fold web server to annotate human structures from the AlphaFold database without a corresponding structure in the Protein Data Bank (PDB) to discover new druggable binding sites. The ProBiS algorithm is used to compare each query protein structure predicted by the AlphaFold approach with the protein structures from the PDB to identify similarities between known binding sites found in the PDB and yet unknown binding sites in the AlphaFold database. Ligands bound in these identified similar PDB sites are then transferred to each query protein from the AlphaFold database, and binding sites are identified as ligand clusters on an AlphaFold protein. Small molecule binding sites are assigned druggability scores based on the similarity of their ligands to known drugs, allowing them to be ranked according to their perceived and actual potential for drug development. ProBiS-Fold provides interactive and downloadable binding sites for the entire human structural proteome, including more than 3000 new druggable binding sites that have no corresponding structure in the PDB, taking into account AlphaFold's model quality, to enable protein structure-function relationship studies and pharmaceutical drug discovery research. The web server is freely accessible to academic users at http://probis-fold.insilab.org.

In silico tools to assess the potential allergenicity of shiitake mushrooms (Lentinula edodes).

Computational tools may have an edge over conventional methods for the preliminary evaluation of food allergenicity. In this study, the allergenic potential of Lentinula edodes was evaluated and validated using in silico tools. The potential cross-reactivity of mushroom proteins with fungal allergens was determined using sequence alignment - the Fast Alignment(FASTA) and Basic Local Alignment Search Tool (BLAST) algorithm. Eight L. edodes proteins were cross-reactive with allergens from fungal origin, showing 52%-89% sequence identity using FASTA algorithm-based alignment. The BLAST data were corroborated by percentage identity and query coverage. Physico-chemical property-based allergenicity was deciphered by AlgPred, Allermatch, and AllergenFP software, which predicted six out of eight proteins as potential allergens. Sequence alignment showed 66%-86% conservancy between mushroom protein and known fungal allergens. Secondary structure and amino acid composition supported structural affinity between query and fungal proteins. Three-dimensional structures of five mushroom proteins were generated, quality assessed, and superimposed with fungal allergens, suggesting possible allergenicity of mushroom proteins. An enzyme-linked immunosorbent assay (ELISA) demonstrated immunoglobulin E (IgE) binding in 13 out of 21 food-hypersensitive patients' sera. In silico tools provide preliminary indications about the potential allergenicity and cross-reactivity of mushroom proteins. This approach may be used for the prelusive allergenicity assessment of allergen sources. © 2022 Society of Chemical Industry.

Learning Protein Embedding to Improve Protein Fold Recognition Using Deep Metric Learning.

Protein fold recognition refers to predicting the most likely fold type of the query protein and is a critical step of protein structure and function prediction. With the popularity of deep learning in bioinformatics, protein fold recognition has obtained impressive progress. In this study, to extract the fold-specific feature to improve protein fold recognition, we proposed a unified deep metric learning framework based on a joint loss function, termed NPCFold. In addition, we also proposed an integrated machine learning model based on the similarity of proteins in various properties, termed NPCFoldpro. Benchmark experiments show both NPCFold and NPCFoldpro outperform existing protein fold recognition methods at the fold level, indicating that our proposed strategies of fusing loss functions and fusing features could improve the fold recognition level.