Prediction Of Functional Sites Research Articles

Assessment of the Performances of the Protein Modeling Techniques Participating in CASP15 Using a Structure-Based Functional Site Prediction Approach: ResiRole.

Model quality assessments via computational methods which entail comparisons of the modeled structures to the experimentally determined structures are essential in the field of protein structure prediction. The assessments provide means to benchmark the accuracies of the modeling techniques and to aid with their development. We previously described the ResiRole method to gauge model quality principally based on the preservation of the structural characteristics described in SeqFEATURE functional site prediction models. We apply ResiRole to benchmark modeling group performances in the Critical Assessment of Structure Prediction experiment, round 15. To gauge model quality, a normalized Predicted Functional site Similarity Score (PFSS) was calculated as the average of one minus the absolute values of the differences of the functional site prediction probabilities, as found for the experimental structures versus those found at the corresponding sites in the structure models. The average PFSS per modeling group (gPFSS) correlates with standard quality metrics, and can effectively be used to rank the accuracies of the groups. For the free modeling (FM) category, correlation coefficients of the Local Distance Difference Test (LDDT) and Global Distance Test-Total Score (GDT-TS) metrics with gPFSS were 0.98239 and 0.87691, respectively. An example finding for a specific group is that the gPFSS for EMBER3D was higher than expected based on the predictive relationship between gPFSS and LDDT. We infer the result is due to the use of constraints imprinted by function that are a part of the EMBER3D methodology. Also, we find functional site predictions that may guide further functional characterizations of the respective proteins. The gPFSS metric provides an effective means to assess and rank the performances of the structure prediction techniques according to their abilities to accurately recount the structural features at predicted functional sites.

COLLAPSE: A representation learning framework for identification and characterization of protein structural sites.

The identification and characterization of the structural sites which contribute to protein function are crucial for understanding biological mechanisms, evaluating disease risk, and developing targeted therapies. However, the quantity of known protein structures is rapidly outpacing our ability to functionally annotate them. Existing methods for function prediction either do not operate on local sites, suffer from high false positive or false negative rates, or require large site-specific training datasets, necessitating the development of new computational methods for annotating functional sites at scale. We present COLLAPSE (Compressed Latents Learned from Aligned Protein Structural Environments), a framework for learning deep representations of protein sites. COLLAPSE operates directly on the 3D positions of atoms surrounding a site and uses evolutionary relationships between homologous proteins as a self-supervision signal, enabling learned embeddings to implicitly capture structure-function relationships within each site. Our representations generalize across disparate tasks in a transfer learning context, achieving state-of-the-art performance on standardized benchmarks (protein-protein interactions and mutation stability) and on the prediction of functional sites from the Prosite database. We use COLLAPSE to search for similar sites across large protein datasets and to annotate proteins based on a database of known functional sites. These methods demonstrate that COLLAPSE is computationally efficient, tunable, and interpretable, providing a general-purpose platform for computational protein analysis.

Alignment-free estimation of sequence conservation for identifying functional sites using protein sequence embeddings.

Protein language modeling is a fast-emerging deep learning method in bioinformatics with diverse applications such as structure prediction and protein design. However, application toward estimating sequence conservation for functional site prediction has not been systematically explored. Here, we present a method for the alignment-free estimation of sequence conservation using sequence embeddings generated from protein language models. Comprehensive benchmarks across publicly available protein language models reveal that ESM2 models provide the best performance to computational cost ratio for conservation estimation. Applying our method to full-length protein sequences, we demonstrate that embedding-based methods are not sensitive to the order of conserved elements-conservation scores can be calculated for multidomain proteins in a single run, without the need to separate individual domains. Our method can also identify conserved functional sites within fast-evolving sequence regions (such as domain inserts), which we demonstrate through the identification of conserved phosphorylation motifs in variable insert segments in protein kinases. Overall, embedding-based conservation analysis is a broadly applicable method for identifying potential functional sites in any full-length protein sequence and estimating conservation in an alignment-free manner. To run this on your protein sequence of interest, try our scripts at https://github.com/esbgkannan/kibby.

ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction.

Predicting the functional sites of a protein from its structure, such as the binding sites of small molecules, other proteins or antibodies, sheds light on its function in vivo. Currently, two classes of methods prevail: machine learning models built on top of handcrafted features and comparative modeling. They are, respectively, limited by the expressivity of the handcrafted features and the availability of similar proteins. Here, we introduce ScanNet, an end-to-end, interpretable geometric deep learning model that learns features directly from 3D structures. ScanNet builds representations of atoms and amino acids based on the spatio-chemical arrangement of their neighbors. We train ScanNet for detecting protein-protein and protein-antibody binding sites, demonstrate its accuracy-including for unseen protein folds-and interpret the filters learned. Finally, we predict epitopes of the SARS-CoV-2 spike protein, validating known antigenic regions and predicting previously uncharacterized ones. Overall, ScanNet is a versatile, powerful and interpretable model suitable for functional site prediction tasks. A webserver for ScanNet is available from http://bioinfo3d.cs.tau.ac.il/ScanNet/ .

IPseU-TWSVM: Identification of RNA pseudouridine sites based on TWSVM.

Biological sequence analysis is an important basic research work in the field of bioinformatics. With the explosive growth of data, machine learning methods play an increasingly important role in biological sequence analysis. By constructing a classifier for prediction, the input sequence feature vector is predicted and evaluated, and the knowledge of gene structure, function and evolution is obtained from a large amount of sequence information, which lays a foundation for researchers to carry out in-depth research. At present, many machine learning methods have been applied to biological sequence analysis such as RNA gene recognition and protein secondary structure prediction. As a biological sequence, RNA plays an important biological role in the encoding, decoding, regulation and expression of genes. The analysis of RNA data is currently carried out from the aspects of structure and function, including secondary structure prediction, non-coding RNA identification and functional site prediction. Pseudouridine (У) is the most widespread and rich RNA modification and has been discovered in a variety of RNAs. It is highly essential for the study of related functional mechanisms and disease diagnosis to accurately identify У sites in RNA sequences. At present, several computational approaches have been suggested as an alternative to experimental methods to detect У sites, but there is still potential for improvement in their performance. In this study, we present a model based on twin support vector machine (TWSVM) for У site identification. The model combines a variety of feature representation techniques and uses the max-relevance and min-redundancy methods to obtain the optimum feature subset for training. The independent testing accuracy is improved by 3.4% in comparison to current advanced У site predictors. The outcomes demonstrate that our model has better generalization performance and improves the accuracy of У site identification. iPseU-TWSVM can be a helpful tool to identify У sites.

Purification, characterization and functional site prediction of the vaccinia-related kinase 2A small transmembrane domain

Vaccinia-related kinases (VRK) are serine-threonine kinases that regulate several signaling pathways. The isoform-VRK2A of one such kinase VRK2 controls cell stress response by interacting with TAK1, a mitogen-activated protein 3 kinase (MAP3K), via its partly cytosolic C-terminal transmembrane domain (VTMD). To establish the driving force and identify the key residues of the VRK2A-TAK1 interaction, we expressed and purified the standalone 3.6 kDa VTMD in the bacterial system using a unique and atypical two-step approach, when the effort to obtain full-length VRK2A remained unsuccessful. Characterization of biophysical properties demonstrated that VTMD domain maintains its structural integrity. Furthermore, dissecting the VRK2A-TAK1 binding interface using in silico tools provided important cues toward engineering the VRK2A-TAK1 interface to modulate its functions with desired characteristics. Most importantly, this novel purification strategy demonstrates its universal applicability in protein biochemistry research by serving as a model system for obtaining difficult-to-purify small proteins or domains.•VRK2A is a highly disordered transmembrane (TM) kinase, whose TM domain interacts with TAK1 (transforming growth factor-β-activated kinase).•The standalone VRK2A-TM domain (VTMD) was purified using affinity chromatography followed by two-step centricon based approach.•Biophysical and in silico analyses confirmed structural integrity of the domain.

InDeep: 3D fully convolutional neural networks to assist in silico drug design on protein-protein interactions.

MotivationProtein–protein interactions (PPIs) are key elements in numerous biological pathways and the subject of a growing number of drug discovery projects including against infectious diseases. Designing drugs on PPI targets remains a difficult task and requires extensive efforts to qualify a given interaction as an eligible target. To this end, besides the evident need to determine the role of PPIs in disease-associated pathways and their experimental characterization as therapeutics targets, prediction of their capacity to be bound by other protein partners or modulated by future drugs is of primary importance.ResultsWe present InDeep, a tool for predicting functional binding sites within proteins that could either host protein epitopes or future drugs. Leveraging deep learning on a curated dataset of PPIs, this tool can proceed to enhanced functional binding site predictions either on experimental structures or along molecular dynamics trajectories. The benchmark of InDeep demonstrates that our tool outperforms state-of-the-art ligandable binding sites predictors when assessing PPI targets but also conventional targets. This offers new opportunities to assist drug design projects on PPIs by identifying pertinent binding pockets at or in the vicinity of PPI interfaces.Availability and implementationThe tool is available on GitLab at https://gitlab.pasteur.fr/InDeep/InDeep.Supplementary information Supplementary data are available at Bioinformatics online.

TFBSPred: A functional transcription factor binding site prediction webtool for humans and mice

Transcription factors (TFs) play a major role in the regulation of gene expression. Discovering the TFs which bind to the regulatory regions of each gene has been long‑term focus of research. Since the experimental verification of TF binding sites (TFBSs) is a complex process, webtools that perform predictions have been developed. However, the majority of the tools do not provide a user‑friendly environment for data input and a number of these tools produce a large number of false‑positive results. The present study introduces TFBSPred, a TFBS prediction webtool that utilises hidden Markov model‑based TF flexible models (TFFM) for predicting binding sites while providing an automated and minimal input user interface. TFBSPred uses DNAse I hypersensitivity data from ENCODE to identify open chromatin regions and takes advantage of the conservation between <em>Homo sapiens</em> and <em>Mus musculus</em>, by using Ensembl Compara pairwise alignments, to increase the true positive rate of the prediction. The users input a gene name or genomic location of a human or mouse genome, select the cell types of interest and TFBSPred outputs the conserved open chromatin region of the selected regulatory sequences and cell types as a pairwise alignment and displays the predicted TFBSs. The present study benchmarked TFBSPred and several similar functioning webtools using experimentally verified TFBSs. TFBSPred exhibited the optimal trade‑off between sensitivity and specificity in the case of the well‑studied IFNB1 enhanceosome, while outperforming the other web tools in subsequent use‑cases. TFBSPred may thus prove to be a valuable tool for TFBS prediction and for the provision of hypotheses for experimental validation. TFBSPred also has the potential for further improvement with future updates of TFFM data. TFBSPred is freely available at: https://www.michalopoulos.net/tfbspred/.

CATH functional families predict functional sites in proteins.

Identification of functional sites in proteins is essential for functional characterization, variant interpretation and drug design. Several methods are available for predicting either a generic functional site, or specific types of functional site. Here, we present FunSite, a machine learning predictor that identifies catalytic, ligand-binding and protein-protein interaction functional sites using features derived from protein sequence and structure, and evolutionary data from CATH functional families (FunFams). FunSite's prediction performance was rigorously benchmarked using cross-validation and a holdout dataset. FunSite outperformed other publicly available functional site prediction methods. We show that conserved residues in FunFams are enriched in functional sites. We found FunSite's performance depends greatly on the quality of functional site annotations and the information content of FunFams in the training data. Finally, we analyze which structural and evolutionary features are most predictive for functional sites. https://github.com/UCL/cath-funsite-predictor. Supplementary data are available at Bioinformatics online.

The ResiRole server to enable assessments of structure prediction techniques using functional site predictions

The ResiRole server to enable assessments of structure prediction techniques using functional site predictions

ResiRole: residue-level functional site predictions to gauge the accuracies of protein structure prediction techniques.

MotivationMethods to assess the quality of protein structure models are needed for user applications. To aid with the selection of structure models and further inform the development of structure prediction techniques, we describe the ResiRole method for the assessment of the quality of structure models.ResultsStructure prediction techniques are ranked according to the results of round-robin, head-to-head comparisons using difference scores. Each difference score was defined as the absolute value of the cumulative probability for a functional site prediction made with the FEATURE program for the reference structure minus that for the structure model. Overall, the difference scores correlate well with other model quality metrics; and based on benchmarking studies with NaïveBLAST, they are found to detect additional local structural similarities between the structure models and reference structures.Availabilityand implementationAutomated analyses of models addressed in CAMEO are available via the ResiRole server, URL http://protein.som.geisinger.edu/ResiRole/. Interactive analyses with user-provided models and reference structures are also enabled. Code is available at github.com/wamclaughlin/ResiRole.Supplementary information Supplementary data are available at Bioinformatics online.

An Evolutionary Trace method defines functionally important bases and sites common to RNA families.

Functional non-coding (fnc)RNAs are nucleotide sequences of varied lengths, structures, and mechanisms that ubiquitously influence gene expression and translation, genome stability and dynamics, and human health and disease. Here, to shed light on their functional determinants, we seek to exploit the evolutionary record of variation and divergence read from sequence comparisons. The approach follows the phylogenetic Evolutionary Trace (ET) paradigm, first developed and extensively validated on proteins. We assigned a relative rank of importance to every base in a study of 1070 functional RNAs, including the ribosome, and observed evolutionary patterns strikingly similar to those seen in proteins, namely, (1) the top-ranked bases clustered in secondary and tertiary structures. (2) In turn, these clusters mapped functional regions for catalysis, binding proteins and drugs, post-transcriptional modification, and deleterious mutations. (3) Moreover, the quantitative quality of these clusters correlated with the identification of functional regions. (4) As a result of this correlation, smoother structural distributions of evolutionary important nucleotides improved functional site predictions. Thus, in practice, phylogenetic analysis can broadly identify functional determinants in RNA sequences and functional sites in RNA structures, and reveal details on the basis of RNA molecular functions. As example of application, we report several previously undocumented and potentially functional ET nucleotide clusters in the ribosome. This work is broadly relevant to studies of structure-function in ribonucleic acids. Additionally, this generalization of ET shows that evolutionary constraints among sequence, structure, and function are similar in structured RNA and proteins. RNA ET is currently available as part of the ET command-line package, and will be available as a web-server.

PIRSitePredict for protein functional site prediction using position-specific rules.

Methods focused on predicting ‘global’ annotations for proteins (such as molecular function, biological process and presence of domains or membership in a family) have reached a relatively mature stage. Methods to provide fine-grained ‘local’ annotation of functional sites (at the level of individual amino acid) are now coming to the forefront, especially in light of the rapid accumulation of genetic variant data. We have developed a computational method and workflow that predicts functional sites within proteins using position-specific conditional template annotation rules (namely PIR Site Rules or PIRSRs for short). Such rules are curated through review of known protein structural and other experimental data by structural biologists and are used to generate high-quality annotations for the UniProt Knowledgebase (UniProtKB) unreviewed section. To share the PIRSR functional site prediction method with the broader scientific community, we have streamlined our workflow and developed a stand-alone Java software package named PIRSitePredict. We demonstrate the use of PIRSitePredict for functional annotation of de novo assembled genome/transcriptome by annotating uncharacterized proteins from Trinity RNA-seq assembly of embryonic transcriptomes of the following three cartilaginous fishes: Leucoraja erinacea (Little Skate), Scyliorhinus canicula (Small-spotted Catshark) and Callorhinchus milii (Elephant Shark). On average about 1200 lines of annotations were predicted for each species.

Factor cooperation for chromosome discrimination in Drosophila.

Transcription regulators select their genomic binding sites from a large pool of similar, non-functional sequences. Although general principles that allow such discrimination are known, the complexity of DNA elements often precludes a prediction of functional sites. The process of dosage compensation in Drosophila allows exploring the rules underlying binding site selectivity. The male-specific-lethal (MSL) Dosage Compensation Complex (DCC) selectively binds to some 300 X chromosomal ‘High Affinity Sites’ (HAS) containing GA-rich ‘MSL recognition elements’ (MREs), but disregards thousands of other MRE sequences in the genome. The DNA-binding subunit MSL2 alone identifies a subset of MREs, but fails to recognize most MREs within HAS. The ‘Chromatin-linked adaptor for MSL proteins’ (CLAMP) also interacts with many MREs genome-wide and promotes DCC binding to HAS. Using genome-wide DNA-immunoprecipitation we describe extensive cooperativity between both factors, depending on the nature of the binding sites. These are explained by physical interaction between MSL2 and CLAMP. In vivo, both factors cooperate to compete with nucleosome formation at HAS. The male-specific MSL2 thus synergises with a ubiquitous GA-repeat binding protein for refined X/autosome discrimination.

Applying Knowledge of Enzyme Biochemistry to the Prediction of Functional Sites for Aiding Drug Discovery.

Enzymes are biological catalysts that play an important role in determining the patterns of chemical transformations pertaining to life. Many milestones have been achieved in unraveling the mechanisms in which the enzymes orchestrate various cellular processes using experimental and computational approaches. Experimental studies generating nearly all possible mutations of target enzymes have been aided by rapid computational approaches aiming at enzyme functional classification, understanding domain organization, functional site identification. The functional architecture, essentially, is involved in binding or interaction with ligands including substrates, products, cofactors, inhibitors, providing for their function, such as in catalysis, ligand mediated cell signaling, allosteric regulation and post-translational modifications. With the increasing availability of enzyme information and advances in algorithm development, computational approaches have now become more capable of providing precise inputs for enzyme engineering, and in the process also making it more efficient. This has led to interesting findings, especially in aberrant enzyme interactions, such as hostpathogen interactions in infection, neurodegenerative diseases, cancer and diabetes. This review aims to summarize in retrospection - the mined knowledge, vivid perspectives and challenging strides in using available experimentally validated enzyme information for characterization. An analytical outlook is presented on the scope of exploring future directions.

A comprehensive software suite for protein family construction and functional site prediction.

In functionally diverse protein families, conservation in short signature regions may outperform full-length sequence comparisons for identifying proteins that belong to a subgroup within which one specific aspect of their function is conserved. The SIMBAL workflow (Sites Inferred by Metabolic Background Assertion Labeling) is a data-mining procedure for finding such signature regions. It begins by using clues from genomic context, such as co-occurrence or conserved gene neighborhoods, to build a useful training set from a large number of uncharacterized but mutually homologous proteins. When training set construction is successful, the YES partition is enriched in proteins that share function with the user’s query sequence, while the NO partition is depleted. A selected query sequence is then mined for short signature regions whose closest matches overwhelmingly favor proteins from the YES partition. High-scoring signature regions typically contain key residues critical to functional specificity, so proteins with the highest sequence similarity across these regions tend to share the same function. The SIMBAL algorithm was described previously, but significant manual effort, expertise, and a supporting software infrastructure were required to prepare the requisite training sets. Here, we describe a new, distributable software suite that speeds up and simplifies the process for using SIMBAL, most notably by providing tools that automate training set construction. These tools have broad utility for comparative genomics, allowing for flexible collection of proteins or protein domains based on genomic context as well as homology, a capability that can greatly assist in protein family construction. Armed with this new software suite, SIMBAL can serve as a fast and powerful in silico alternative to direct experimentation for characterizing proteins and their functional interactions.

Designing and in Silico Analysis of PorB Protein from Chlamydia Trachomatis for Developing a Vaccine Candidate.

Bakground: Chlamydia trachomatis is an obligate, intracellular, gram-negative bacterium that causes sexually transmitted infections. The outer membrane protein PorB is a conserved chlamydial protein that functions as a porin and is a target for neutralizing antibodies (Abs); thus, making it important for vaccine development. Methods: We used an in silico strategy and homology modeling algorithms and focused on PorB of C. trachomatis and explained its characterization with the help of bioinformatic tools to introduce it as a candidate for novel drug and vaccine design. In this study, physicochemical characterization, secondary and 3D structure, and functional site prediction were investigated. Then, a B cell epitope was analyzed using Immune Epitope Database, which predicts the target region and helps in vaccine development. Results: PorB is a surface-exposed protein comprising 340 amino acids and frequently appears (61.76%) as a random coiled structure. PorB was present outside the cell and the maximum length of the predicted epitope was from amino acids 91-108, i. e., 18 amino acids long. This epitope can be considered for designing Abs and vaccines against C. trachomatis. Conclusion: Although many attempts have been made to develop a vaccine against C. trachomatis, no protective vaccines are available to date. More detailed studies focusing on PorB should be performed to design vaccines against C. trachomatis because of the presence of different immunization protocols and requirement of different protective mechanisms.

Evaluation of free modeling targets in CASP11 and ROLL.

We present an assessment of 'template-free modeling' (FM) in CASP11and ROLL. Community-wide server performance suggested the use of automated scores similar to previous CASPs would provide a good system of evaluating performance, even in the absence of comprehensive manual assessment. The CASP11 FM category included several outstanding examples, including successful prediction by the Baker group of a 256-residue target (T0806-D1) that lacked sequence similarity to any existing template. The top server model prediction by Zhang's Quark, which was apparently selected and refined by several manual groups, encompassed the entire fold of target T0837-D1. Methods from the same two groups tended to dominate overall CASP11 FM and ROLL rankings. Comparison of top FM predictions with those from the previous CASP experiment revealed progress in the category, particularly reflected in high prediction accuracy for larger protein domains. FM prediction models for two cases were sufficient to provide functional insights that were otherwise not obtainable by traditional sequence analysis methods. Importantly, CASP11 abstracts revealed that alignment-based contact prediction methods brought about much of the CASP11 progress, producing both of the functionally relevant models as well as several of the other outstanding structure predictions. These methodological advances enabled de novo modeling of much larger domain structures than was previously possible and allowed prediction of functional sites. Proteins 2016; 84(Suppl 1):51-66. © 2015 Wiley Periodicals, Inc.

Protein Functional Site Prediction Using a Conservative Grade and a Proximate Grade

So far, in order to predict important sites of a protein, many computational methods have been developed. In the era of big-data, it is required for improvements and sophistication of existing methods by integrating sequence data in the structural data. In this paper, we aim at two things: improving sequence-based methods and developing a new method using both sequence and structural data. Therefore, we developed an originally modified evolutionary trace method, in which we defined conservative grades calculated from a given multiple sequence alignment and a proximate grade in order to evaluate predicted active sites from a viewpoint of protein-ion, protein-ligand, protein-nucleic acid, proteinprotein interaction by use of three-dimensional structures. In other words, the proximate grade also can evaluate an amino acid residue. When we applied our method to translation elongation factor Tu/1A proteins, it showed that the conservative grades are evaluated accurately by the proximate grade. Consequently, our idea indicated two advantages. One is that we can take into account various cocrystal structures for evaluation. Another one is that, by calculating the fitness between the given conservative grade and the proximate grade, we can select the best conservative grade.

Functional classification of CATH superfamilies: a domain-based approach for protein function annotation.

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.