Using a neural network and spatial clustering to predict the location of active sites in enzymes

Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites

Annotating active sites in enzymes is crucial for advancing multiple fields including drug discovery, disease research, enzyme engineering, and synthetic biology. Despite the development of numerous automated annotation algorithms, a significant trade-off between speed and accuracy limits their large-scale practical applications. We introduce EasIFA, an enzyme active site annotation algorithm that fuses latent enzyme representations from the Protein Language Model and 3D structural encoder, and then aligns protein-level information with the knowledge of enzymatic reactions using a multi-modal cross-attention framework. EasIFA outperforms BLASTp with a 10-fold speed increase and improved recall, precision, f1 score, and MCC by 7.57%, 13.08%, 9.68%, and 0.1012, respectively. It also surpasses empirical-rule-based algorithm and other state-of-the-art deep learning annotation method based on PSSM features, achieving a speed increase ranging from 650 to 1400 times while enhancing annotation quality. This makes EasIFA a suitable replacement for conventional tools in both industrial and academic settings. EasIFA can also effectively transfer knowledge gained from coarsely annotated enzyme databases to smaller, high-precision datasets, highlighting its ability to model sparse and high-quality databases. Additionally, EasIFA shows potential as a catalytic site monitoring tool for designing enzymes with desired functions beyond their natural distribution.

Enzyme function and evolution through the lens of bioinformatics

Enzymes have been shaped by evolution over billions of years to catalyse the chemical reactions that support life on earth. Dispersed in the literature, or organised in online databases, knowledge about enzymes can be structured in distinct dimensions, either related to their quality as biological macromolecules, such as their sequence and structure, or related to their chemical functions, such as the catalytic site, kinetics, mechanism, and overall reaction. The evolution of enzymes can only be understood when each of these dimensions is considered. In addition, many of the properties of enzymes only make sense in the light of evolution. We start this review by outlining the main paradigms of enzyme evolution, including gene duplication and divergence, convergent evolution, and evolution by recombination of domains. In the second part, we overview the current collective knowledge about enzymes, as organised by different types of data and collected in several databases. We also highlight some increasingly powerful computational tools that can be used to close gaps in understanding, in particular for types of data that require laborious experimental protocols. We believe that recent advances in protein structure prediction will be a powerful catalyst for the prediction of binding, mechanism, and ultimately, chemical reactions. A comprehensive mapping of enzyme function and evolution may be attainable in the near future.

A Highly Sensitive Model Based on Graph Neural Networks for Enzyme Key Catalytic Residue Prediction

Determining the catalytic site of enzymes is a great help for understanding the relationship between protein sequence, structure, and function, which provides the basis and targets for designing, modifying, and enhancing enzyme activity. The unique local spatial configuration bound to the substrate at the active center of the enzyme determines the catalytic ability of enzymes and plays an important role in the catalytic site prediction. As a suitable tool, the graph neural network can better understand and identify the residue sites with unique local spatial configurations due to its remarkable ability to characterize the three-dimensional structural features of proteins. Consequently, a novel model for predicting enzyme catalytic sites has been developed, which incorporates a uniquely designed adaptive edge-gated graph attention neural network (AEGAN). This model is capable of effectively handling sequential and structural characteristics of proteins at various levels, and the extracted features enable an accurate description of the local spatial configuration of the enzyme active site by sampling the local space around candidate residues and special design of amino acid physical and chemical properties. To evaluate its performance, the model was compared with existing catalytic site prediction models using different benchmark datasets and achieved the best results on each benchmark dataset. The model exhibited a sensitivity of 0.9659, accuracy of 0.9226, and area under the precision-recall curve (AUPRC) of 0.9241 on the independent test set constructed for evaluation. Furthermore, the F1-score of this model is nearly four times higher than that of the best-performing similar model in previous studies. This research can serve as a valuable tool to help researchers understand protein sequence-structure-function relationships while facilitating the characterization of novel enzymes of unknown function.

Irregular Shaped Small Nodule Detection Using a Robust Scan Statistic

The spatial scan statistics based on the Poisson and binomial models are the most common methods to detect spatial clusters in disease surveillance. These models rely on Monte-Carlo simulation which are time consuming. Moreover, frequently, datasets present over-dispersion which cannot be handled by them. Thus, we have the following goals. First, we propose irregularly shaped spatial scan for the Bell, Poisson, and binomial. The Bell distribution has just one parameter but it is capable of handling over-dispersed datasets. Second, we apply these scan statistics to big maps. A fast version, without Monte-Carlo simulation, for the proposed Poisson and binomial scans is introduced. Intensive simulation studies are carried out to assess the quality of the proposals. In addition, we show the time improvement of the fast scan versions over their traditional ones. Finally, we end the paper with an application on the detection of irregular shape small nodules in a medical image.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12561-022-09353-7.

A multilayer dynamic perturbation analysis method for predicting ligand-protein interactions

BACKGROUND

Ligand-protein interactions play a key role in defining protein function, and detecting natural ligands for a given protein is thus a very important bioengineering task. In particular, with the rapid development of AI-based structure prediction algorithms, batch structural models with high reliability and accuracy can be obtained at low cost, giving rise to the urgent requirement for the prediction of natural ligands based on protein structures. In recent years, although several structure-based methods have been developed to predict ligand-binding pockets and ligand-binding sites, accurate and rapid methods are still lacking, especially for the prediction of ligand-binding regions and the spatial extension of ligands in the pockets.

RESULTS

In this paper, we proposed a multilayer dynamics perturbation analysis (MDPA) method for predicting ligand-binding regions based solely on protein structure, which is an extended version of our previously developed fast dynamic perturbation analysis (FDPA) method. In MDPA/FDPA, ligand binding tends to occur in regions that cause large changes in protein conformational dynamics. MDPA, examined using a standard validation dataset of ligand-protein complexes, yielded an averaged ligand-binding site prediction Matthews coefficient of 0.40, with a prediction precision of at least 50% for 71% of the cases. In particular, for 80% of the cases, the predicted ligand-binding region overlaps the natural ligand by at least 50%. The method was also compared with other state-of-the-art structure-based methods.

CONCLUSIONS

MDPA is a structure-based method to detect ligand-binding regions on protein surface. Our calculations suggested that a range of spaces inside the protein pockets has subtle interactions with the protein, which can significantly impact on the overall dynamics of the protein. This work provides a valuable tool as a starting point upon which further docking and analysis methods can be used for natural ligand detection in protein functional annotation. The source code of MDPA method is freely available at: https://github.com/mingdengming/mdpa .

Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field

Proteins are some of the most fascinating and challenging molecules in the universe, and they pose a big challenge for artificial intelligence. The implementation of machine learning/AI in protein science gives rise to a world of knowledge adventures in the workhorse of the cell and proteome homeostasis, which are essential for making life possible. This opens up epistemic horizons thanks to a coupling of human tacit-explicit knowledge with machine learning power, the benefits of which are already tangible, such as important advances in protein structure prediction. Moreover, the driving force behind the protein processes of self-organization, adjustment, and fitness requires a space corresponding to gigabytes of life data in its order of magnitude. There are many tasks such as novel protein design, protein folding pathways, and synthetic metabolic routes, as well as protein-aggregation mechanisms, pathogenesis of protein misfolding and disease, and proteostasis networks that are currently unexplored or unrevealed. In this systematic review and biochemical meta-analysis, we aim to contribute to bridging the gap between what we call binomial artificial intelligence (AI) and protein science (PS), a growing research enterprise with exciting and promising biotechnological and biomedical applications. We undertake our task by exploring "the state of the art" in AI and machine learning (ML) applications to protein science in the scientific literature to address some critical research questions in this domain, including What kind of tasks are already explored by ML approaches to protein sciences? What are the most common ML algorithms and databases used? What is the situational diagnostic of the AI-PS inter-field? What do ML processing steps have in common? We also formulate novel questions such as Is it possible to discover what the rules of protein evolution are with the binomial AI-PS? How do protein folding pathways evolve? What are the rules that dictate the folds? What are the minimal nuclear protein structures? How do protein aggregates form and why do they exhibit different toxicities? What are the structural properties of amyloid proteins? How can we design an effective proteostasis network to deal with misfolded proteins? We are a cross-functional group of scientists from several academic disciplines, and we have conducted the systematic review using a variant of the PICO and PRISMA approaches. The search was carried out in four databases (PubMed, Bireme, OVID, and EBSCO Web of Science), resulting in 144 research articles. After three rounds of quality screening, 93 articles were finally selected for further analysis. A summary of our findings is as follows: regarding AI applications, there are mainly four types: 1) genomics, 2) protein structure and function, 3) protein design and evolution, and 4) drug design. In terms of the ML algorithms and databases used, supervised learning was the most common approach (85%). As for the databases used for the ML models, PDB and UniprotKB/Swissprot were the most common ones (21 and 8%, respectively). Moreover, we identified that approximately 63% of the articles organized their results into three steps, which we labeled pre-process, process, and post-process. A few studies combined data from several databases or created their own databases after the pre-process. Our main finding is that, as of today, there are no research road maps serving as guides to address gaps in our knowledge of the AI-PS binomial. All research efforts to collect, integrate multidimensional data features, and then analyze and validate them are, so far, uncoordinated and scattered throughout the scientific literature without a clear epistemic goal or connection between the studies. Therefore, our main contribution to the scientific literature is to offer a road map to help solve problems in drug design, protein structures, design, and function prediction while also presenting the "state of the art" on research in the AI-PS binomial until February 2021. Thus, we pave the way toward future advances in the synthetic redesign of novel proteins and protein networks and artificial metabolic pathways, learning lessons from nature for the welfare of humankind. Many of the novel proteins and metabolic pathways are currently non-existent in nature, nor are they used in the chemical industry or biomedical field.

Capturing the geometry, function, and evolution of enzymes with 3D templates

Structural templates are 3D signatures representing protein functional sites, such as ligand binding cavities, metal coordination motifs, or catalytic sites. Here we explore methods to generate template libraries and algorithms to query structures for conserved 3D motifs. Applications of templates are discussed, as well as some exemplar cases for examining evolutionary links in enzymes. We also introduce the concept of using more than one template per structure to represent flexible sites, as an approach to better understand catalysis through snapshots captured in enzyme structures. Functional annotation from structure is an important topic that has recently resurfaced due to the new more accurate methods of protein structure prediction. Therefore, we anticipate that template-based functional site detection will be a powerful tool in the task of characterizing a vast number of new protein models.

Catalytic and binding sites prediction in globular proteins through discrete Markov chains and network centrality measures

In this work we use a discrete Markov chain approach combined with network centrality measures to identify and predict the location of active sites in globular proteins. To accomplish this, we use a three-dimensional network of proteinC_αatoms as nodes connected through weighted edges which represent the varying interaction degree between protein's atoms. We compute the mean first passage time matrixH= {H_ji} for this Markov chain and evaluate the averaged number of steps ⟨H_j⟩ to reach single noden_jin order to identify such residues that, on the average, are at the least distant from every other node. We also carry out a graph theory analysis to evaluate closeness centralityC_c, betweenness centralityC_band eigenvector centralityC_emeasures which provide relevant information about the connectivity structure and topology of theC_αprotein networks. Finally we also performed an analysis of equivalent random and regular networks of the same sizeNin terms of the average path lengthLand the average clustering coefficient⟨C⟩comparing these with the corresponding values forC_αprotein networks. Our results show that the mean-first passage time matrixHand its related quantity ⟨H_j⟩ together withC_c,C_bandC_ecan not only predict with relative high accuracy the location of active sites in globular proteins but also exhibit a high feasibility to use them to predict the existence of new regions in protein's structure to identify new potential binding or catalytic activity or, in some cases, the presence of new allosteric pathways.

Machine learning for enzyme engineering, selection and design

Machine learning is a useful computational tool for large and complex tasks such as those in the field of enzyme engineering, selection and design. In this review, we examine enzyme-related applications of machine learning. We start by comparing tools that can identify the function of an enzyme and the site responsible for that function. Then we detail methods for optimizing important experimental properties, such as the enzyme environment and enzyme reactants. We describe recent advances in enzyme systems design and enzyme design itself. Throughout we compare and contrast the data and algorithms used for these tasks to illustrate how the algorithms and data can be best used by future designers.

Predicting binding sites from unbound versus bound protein structures

We present the application of seven binding-site prediction algorithms to a meticulously curated dataset of ligand-bound and ligand-free crystal structures for 304 unique protein sequences (2528 crystal structures). We probe the influence of starting protein structures on the results of binding-site prediction, so the dataset contains a minimum of two ligand-bound and two ligand-free structures for each protein. We use this dataset in a brief survey of five geometry-based, one energy-based, and one machine-learning-based methods: Surfnet, Ghecom, LIGSITE_csc, Fpocket, Depth, AutoSite, and Kalasanty. Distributions of the F scores and Matthew’s correlation coefficients for ligand-bound versus ligand-free structure performance show no statistically significant difference in structure type versus performance for most methods. Only Fpocket showed a statistically significant but low magnitude enhancement in performance for holo structures. Lastly, we found that most methods will succeed on some crystal structures and fail on others within the same protein family, despite all structures being relatively high-quality structures with low structural variation. We expected better consistency across varying protein conformations of the same sequence. Interestingly, the success or failure of a given structure cannot be predicted by quality metrics such as resolution, Cruickshank Diffraction Precision index, or unresolved residues. Cryptic sites were also examined.

Analyses on clustering of the conserved residues at protein-RNA interfaces and its application in binding site identification

Background

The maintenance of protein structural stability requires the cooperativity among spatially neighboring residues. Previous studies have shown that conserved residues tend to occur clustered together within enzyme active sites and protein-protein/DNA interfaces. It is possible that conserved residues form one or more local clusters in protein tertiary structures as it can facilitate the formation of functional motifs. In this work, we systematically investigate the spatial distributions of conserved residues as well as hot spot ones within protein-RNA interfaces.

Results

The analysis of 191 polypeptide chains from 160 complexes shows the polypeptides interacting with tRNAs evolve relatively rapidly. A statistical analysis of residues in different regions shows that the interface residues are often more conserved, while the most conserved ones are those occurring at protein interiors which maintain the stability of folded polypeptide chains. Additionally, we found that 77.8% of the interfaces have the conserved residues clustered within the entire interface regions. Appling the clustering characteristics to the identification of the real interface, there are 31.1% of cases where the real interfaces are ranked in top 10% of 1000 randomly generated surface patches. In the conserved clusters, the preferred residues are the hydrophobic (Leu, Ile, Met), aromatic (Tyr, Phe, Trp) and interestingly only one positively charged Arg residues. For the hot spot residues, 51.5% of them are situated in the conserved residue clusters, and they are largely consistent with the preferred residue types in the conserved clusters.

Conclusions

The protein-RNA interface residues are often more conserved than non-interface surface ones. The conserved interface residues occur more spatially clustered relative to the entire interface residues. The high consistence of hot spot residue types and the preferred residue types in the conserved clusters has important implications for the experimental alanine scanning mutagenesis study. This work deepens the understanding of the residual organization at protein-RNA interface and is of potential applications in the identification of binding site and hot spot residues.

HEMEsPred: Structure-Based Ligand-Specific Heme Binding Residues Prediction by Using Fast-Adaptive Ensemble Learning Scheme

Heme is an essential biomolecule that widely exists in numerous extant organisms. Accurately identifying heme binding residues (HEMEs) is of great importance in disease progression and drug development. In this study, a novel predictor named HEMEsPred was proposed for predicting HEMEs. First, several sequence- and structure-based features, including amino acid composition, motifs, surface preferences, and secondary structure, were collected to construct feature matrices. Second, a novel fast-adaptive ensemble learning scheme was designed to overcome the serious class-imbalance problem as well as to enhance the prediction performance. Third, we further developed ligand-specific models considering that different heme ligands varied significantly in their roles, sizes, and distributions. Statistical test proved the effectiveness of ligand-specific models. Experimental results on benchmark datasets demonstrated good robustness of our proposed method. Furthermore, our method also showed good generalization capability and outperformed many state-of-art predictors on two independent testing datasets. HEMEsPred web server was available at http://www.inforstation.com/HEMEsPred/ for free academic use.

Effects of Mutations on Replicative Fitness and Major Histocompatibility Complex Class I Binding Affinity Are Among the Determinants Underlying Cytotoxic-T-Lymphocyte Escape of HIV-1 Gag Epitopes

Certain “protective” major histocompatibility complex class I (MHC-I) alleles, such as B*57 and B*27, are associated with long-term control of HIV-1 in vivo mediated by the CD8⁺ cytotoxic-T-lymphocyte (CTL) response. However, the mechanism of such superior protection is not fully understood. Here we combined high-throughput fitness profiling of mutations in HIV-1 Gag, in silico prediction of MHC-peptide binding affinity, and analysis of intraperson virus evolution to systematically compare differences with respect to CTL escape mutations between epitopes targeted by protective MHC-I alleles and those targeted by nonprotective MHC-I alleles. We observed that the effects of mutations on both viral replication and MHC-I binding affinity are among the determinants of CTL escape. Mutations in Gag epitopes presented by protective MHC-I alleles are associated with significantly higher fitness cost and lower reductions in binding affinity with respect to MHC-I. A linear regression model accounting for the effect of mutations on both viral replicative capacity and MHC-I binding can explain the protective efficacy of MHC-I alleles. Finally, we found a consistent pattern in the evolution of Gag epitopes in long-term nonprogressors versus progressors. Overall, our results suggest that certain protective MHC-I alleles allow superior control of HIV-1 by targeting epitopes where mutations typically incur high fitness costs and small reductions in MHC-I binding affinity.

Understanding the mechanism of viral control achieved in long-term nonprogressors with protective HLA alleles provides insights for developing functional cure of HIV infection. Through the characterization of CTL escape mutations in infected persons, previous researchers hypothesized that protective alleles target epitopes where escape mutations significantly reduce viral replicative capacity. However, these studies were usually limited to a few mutations observed in vivo. Here we utilized our recently developed high-throughput fitness profiling method to quantitatively measure the fitness of mutations across the entirety of HIV-1 Gag. The data enabled us to integrate the results with in silico prediction of MHC-peptide binding affinity and analysis of intraperson virus evolution to systematically determine the differences in CTL escape mutations between epitopes targeted by protective HLA alleles and those targeted by nonprotective HLA alleles. We observed that the effects of Gag epitope mutations on HIV replicative fitness and MHC-I binding affinity are among the major determinants of CTL escape.

Normal Modes Expose Active Sites in Enzymes

Accurate prediction of active sites is an important tool in bioinformatics. Here we present an improved structure based technique to expose active sites that is based on large changes of solvent accessibility accompanying normal mode dynamics. The technique which detects EXPOsure of active SITes through normal modEs is named EXPOSITE. The technique is trained using a small 133 enzyme dataset and tested using a large 845 enzyme dataset, both with known active site residues. EXPOSITE is also tested in a benchmark protein ligand dataset (PLD) comprising 48 proteins with and without bound ligands. EXPOSITE is shown to successfully locate the active site in most instances, and is found to be more accurate than other structure-based techniques. Interestingly, in several instances, the active site does not correspond to the largest pocket. EXPOSITE is advantageous due to its high precision and paves the way for structure based prediction of active site in enzymes.

In this paper, we present an improved technique to predict active sites in enzymes. Our technique is based on changes of solvent accessibility that accompany normal mode dynamics. We assert the technique strength using several enzyme datasets with known catalytic residues. We show the technique successfully locates the active site in most cases, and consistently surpasses the accuracy of other techniques. We show how the technique is advantageous and paves the way for high precision prediction of active sites.

CRHunter: integrating multifaceted information to predict catalytic residues in enzymes

A variety of algorithms have been developed for catalytic residue prediction based on either feature- or template-based methodology. However, no studies have systematically compared these two strategies and further considered whether their combination could improve the prediction performance. Herein, we developed an integrative algorithm named CRHunter by simultaneously using the complementarity between feature- and template-based methodologies and that between structural and sequence information. Several novel structural features were generated by the Delaunay triangulation and Laplacian transformation of enzyme structures. Combining these features with traditional descriptors, we invented two support vector machine feature predictors based on both structural and sequence information. Furthermore, we established two template predictors using structure and profile alignments. Evaluated on datasets with different levels of homology, our feature predictors achieve relatively stable performance, whereas our template predictors yield poor results when the homological relationships become weak. Nevertheless, the hybrid algorithm CRHunter consistently achieves optimal performance among all our predictors. We also illustrate that our methodology can be applied to the predicted structures of enzymes. Compared with state-of-the-art methods, CRHunter yields comparable or better performance on various datasets. Finally, the application of this algorithm to structural genomics targets sheds light on solved protein structures with unknown functions.

Active Site Characterization of Proteases Sequences from Different Species of Aspergillus

A total of 129 proteases sequences comprising 43 serine proteases, 36 aspartic proteases, 24 cysteine protease, 21 metalloproteases, and 05 neutral proteases from different Aspergillus species were analyzed for the catalytically active site residues using MEROPS database and various bioinformatics tools. Different proteases have predominance of variable active site residues. In case of 24 cysteine proteases of Aspergilli, the predominant active site residues observed were Gln193, Cys199, His364, Asn384 while for 43 serine proteases, the active site residues namely Asp164, His193, Asn284, Ser349 and Asp325, His357, Asn454, Ser519 were frequently observed. The analysis of 21 metalloproteases of Aspergilli revealed Glu298 and Glu388, Tyr476 as predominant active site residues. In general, Aspergilli species-specific active site residues were observed for different types of protease sequences analyzed. The phylogenetic analysis of these 129 proteases sequences revealed 14 different clans representing different types of proteases with diverse active site residues.

Cutoff lensing: predicting catalytic sites in enzymes

Predicting function-related amino acids in proteins with unknown function or unknown allosteric binding sites in drug-targeted proteins is a task of paramount importance in molecular biomedicine. In this paper we introduce a simple, light and computationally inexpensive structure-based method to identify catalytic sites in enzymes. Our method, termed cutoff lensing, is a general procedure consisting in letting the cutoff used to build an elastic network model increase to large values. A validation of our method against a large database of annotated enzymes shows that optimal values of the cutoff exist such that three different structure-based indicators allow one to recover a maximum of the known catalytic sites. Interestingly, we find that the larger the structures the greater the predictive power afforded by our method. Possible ways to combine the three indicators into a single figure of merit and into a specific sequential analysis are suggested and discussed with reference to the classic case of HIV-protease. Our method could be used as a complement to other sequence- and/or structure-based methods to narrow the results of large-scale screenings.

An overview of the prediction of protein DNA-binding sites

Interactions between proteins and DNA play an important role in many essential biological processes such as DNA replication, transcription, splicing, and repair. The identification of amino acid residues involved in DNA-binding sites is critical for understanding the mechanism of these biological activities. In the last decade, numerous computational approaches have been developed to predict protein DNA-binding sites based on protein sequence and/or structural information, which play an important role in complementing experimental strategies. At this time, approaches can be divided into three categories: sequence-based DNA-binding site prediction, structure-based DNA-binding site prediction, and homology modeling and threading. In this article, we review existing research on computational methods to predict protein DNA-binding sites, which includes data sets, various residue sequence/structural features, machine learning methods for comparison and selection, evaluation methods, performance comparison of different tools, and future directions in protein DNA-binding site prediction. In particular, we detail the meta-analysis of protein DNA-binding sites. We also propose specific implications that are likely to result in novel prediction methods, increased performance, or practical applications.

Biochemical functional predictions for protein structures of unknown or uncertain function

With the exponential growth in the determination of protein sequences and structures via genome sequencing and structural genomics efforts, there is a growing need for reliable computational methods to determine the biochemical function of these proteins. This paper reviews the efforts to address the challenge of annotating the function at the molecular level of uncharacterized proteins. While sequence- and three-dimensional-structure-based methods for protein function prediction have been reviewed previously, the recent trends in local structure-based methods have received less attention. These local structure-based methods are the primary focus of this review. Computational methods have been developed to predict the residues important for catalysis and the local spatial arrangements of these residues can be used to identify protein function. In addition, the combination of different types of methods can help obtain more information and better predictions of function for proteins of unknown function. Global initiatives, including the Enzyme Function Initiative (EFI), COMputational BRidges to EXperiments (COMBREX), and the Critical Assessment of Function Annotation (CAFA), are evaluating and testing the different approaches to predicting the function of proteins of unknown function. These initiatives and global collaborations will increase the capability and reliability of methods to predict biochemical function computationally and will add substantial value to the current volume of structural genomics data by reducing the number of absent or inaccurate functional annotations.

Methods for predicting protein-ligand binding sites

Ligand binding is required for many proteins to function properly. A large number of bioinformatics tools have been developed to predict ligand binding sites as a first step in understanding a protein's function or to facilitate docking computations in virtual screening based drug design. The prediction usually requires only the three-dimensional structure (experimentally determined or computationally modeled) of the target protein to be searched for ligand binding site(s), and Web servers have been built, allowing the free and simple use of prediction tools. In this chapter, we review the underlying concepts of the methods used by various tools, and discuss their different features and the related issues of ligand binding site prediction. Some cautionary notes about the use of these tools are also provided.

A survey of computational intelligence techniques in protein function prediction

During the past, there was a massive growth of knowledge of unknown proteins with the advancement of high throughput microarray technologies. Protein function prediction is the most challenging problem in bioinformatics. In the past, the homology based approaches were used to predict the protein function, but they failed when a new protein was different from the previous one. Therefore, to alleviate the problems associated with homology based traditional approaches, numerous computational intelligence techniques have been proposed in the recent past. This paper presents a state-of-the-art comprehensive review of various computational intelligence techniques for protein function predictions using sequence, structure, protein-protein interaction network, and gene expression data used in wide areas of applications such as prediction of DNA and RNA binding sites, subcellular localization, enzyme functions, signal peptides, catalytic residues, nuclear/G-protein coupled receptors, membrane proteins, and pathway analysis from gene expression datasets. This paper also summarizes the result obtained by many researchers to solve these problems by using computational intelligence techniques with appropriate datasets to improve the prediction performance. The summary shows that ensemble classifiers and integration of multiple heterogeneous data are useful for protein function prediction.

Functional evolution of PLP-dependent enzymes based on active-site structural similarities

Families of distantly related proteins typically have very low sequence identity, which hinders evolutionary analysis and functional annotation. Slowly evolving features of proteins, such as an active site, are therefore valuable for annotating putative and distantly related proteins. To date, a complete evolutionary analysis of the functional relationship of an entire enzyme family based on active-site structural similarities has not yet been undertaken. Pyridoxal-5'-phosphate (PLP) dependent enzymes are primordial enzymes that diversified in the last universal ancestor. Using the comparison of protein active site structures (CPASS) software and database, we show that the active site structures of PLP-dependent enzymes can be used to infer evolutionary relationships based on functional similarity. The enzymes successfully clustered together based on substrate specificity, function, and three-dimensional-fold. This study demonstrates the value of using active site structures for functional evolutionary analysis and the effectiveness of CPASS.

Predicting protein-ligand binding site using support vector machine with protein properties

Identification of protein-ligand binding site is an important task in structure-based drug design and docking algorithms. In the past two decades, different approaches have been developed to predict the binding site, such as the geometric, energetic, and sequence-based methods. When scores are calculated from these methods, the algorithm for doing classification becomes very important and can affect the prediction results greatly. In this paper, the support vector machine (SVM) is used to cluster the pockets that are most likely to bind ligands with the attributes of geometric characteristics, interaction potential, offset from protein, conservation score, and properties surrounding the pockets. Our approach is compared to LIGSITE, LIGSITE(CSC), SURFNET, Fpocket, PocketFinder, Q-SiteFinder, ConCavity, and MetaPocket on the data set LigASite and 198 drug-target protein complexes. The results show that our approach improves the success rate from 60 to 80 percent at AUC measure and from 61 to 66 percent at top 1 prediction. Our method also provides more comprehensive results than the others.

Accounting for epistatic interactions improves the functional analysis of protein structures

Motivation: The constraints under which sequence, structure and function coevolve are not fully understood. Bringing this mutual relationship to light can reveal the molecular basis of binding, catalysis and allostery, thereby identifying function and rationally guiding protein redesign. Underlying these relationships are the epistatic interactions that occur when the consequences of a mutation to a protein are determined by the genetic background in which it occurs. Based on prior data, we hypothesize that epistatic forces operate most strongly between residues nearby in the structure, resulting in smooth evolutionary importance across the structure.

Methods and Results: We find that when residue scores of evolutionary importance are distributed smoothly between nearby residues, functional site prediction accuracy improves. Accordingly, we designed a novel measure of evolutionary importance that focuses on the interaction between pairs of structurally neighboring residues. This measure that we term pair-interaction Evolutionary Trace yields greater functional site overlap and better structure-based proteome-wide functional predictions.

Conclusions: Our data show that the structural smoothness of evolutionary importance is a fundamental feature of the coevolution of sequence, structure and function. Mutations operate on individual residues, but selective pressure depends in part on the extent to which a mutation perturbs interactions with neighboring residues. In practice, this principle led us to redefine the importance of a residue in terms of the importance of its epistatic interactions with neighbors, yielding better annotation of functional residues, motivating experimental validation of a novel functional site in LexA and refining protein function prediction.

Contact:lichtarge@bcm.edu

Supplementary information:Supplementary data are available at Bioinformatics online.

Prediction of temperature factors from protein sequence

Protein flexibility is useful in structural and functional aspect of proteins. We have analyzed the local primary protein sequence features that in combination can predict the B-value of amino acid residues directly from the protein sequence. We have also analyzed the distribution of B-value in different regions of protein three dimensional structures. On an average, the normalized Bvalue decreases by 0.1055 with every 0.5Å increase in the distance of the residue from protein surface. The residues in the loop regions have higher B-values as compared to the residues present in other regular secondary structural elements. Buried residues which are present in the protein core are more rigid (lower B-values) than the residues present on the protein surface. Similarly, the hydrophobic residues which tend to be present in the protein core have lower average B-value than the polar residues. Finally, we have proposed the method based on Support Vector Regression (SVR) to predict the B-value from protein primary sequence. Our result shows that, the SVR model achieved the correlation coefficient of 0.47 which is comparable to existing methods.

Identification of catalytic residues using a novel feature that integrates the microenvironment and geometrical location properties of residues

Enzymes play a fundamental role in almost all biological processes and identification of catalytic residues is a crucial step for deciphering the biological functions and understanding the underlying catalytic mechanisms. In this work, we developed a novel structural feature called MEDscore to identify catalytic residues, which integrated the microenvironment (ME) and geometrical properties of amino acid residues. Firstly, we converted a residue's ME into a series of spatially neighboring residue pairs, whose likelihood of being located in a catalytic ME was deduced from a benchmark enzyme dataset. We then calculated an ME-based score, termed as MEscore, by summing up the likelihood of all residue pairs. Secondly, we defined a parameter called Dscore to measure the relative distance of a residue to the center of the protein, provided that catalytic residues are typically located in the center of the protein structure. Finally, we defined the MEDscore feature based on an effective nonlinear integration of MEscore and Dscore. When evaluated on a well-prepared benchmark dataset using five-fold cross-validation tests, MEDscore achieved a robust performance in identifying catalytic residues with an AUC1.0 of 0.889. At a ≤ 10% false positive rate control, MEDscore correctly identified approximately 70% of the catalytic residues. Remarkably, MEDscore achieved a competitive performance compared with the residue conservation score (e.g. CONscore), the most informative singular feature predominantly employed to identify catalytic residues. To the best of our knowledge, MEDscore is the first singular structural feature exhibiting such an advantage. More importantly, we found that MEDscore is complementary with CONscore and a significantly improved performance can be achieved by combining CONscore with MEDscore in a linear manner. As an implementation of this work, MEDscore has been made freely accessible at http://protein.cau.edu.cn/mepi/.

The use of evolutionary patterns in protein annotation

With genomic data skyrocketing, their biological interpretation remains a serious challenge. Diverse computational methods address this problem by pointing to the existence of recurrent patterns among sequence, structure, and function. These patterns emerge naturally from evolutionary variation, natural selection, and divergence--the defining features of biological systems--and they identify molecular events and shapes that underlie specificity of function and allosteric communication. Here we review these methods, and the patterns they identify in case studies and in proteome-wide applications, to infer and rationally redesign function.

L1pred: a sequence-based prediction tool for catalytic residues in enzymes with the L1-logreg classifier

To understand enzyme functions, identifying the catalytic residues is a usual first step. Moreover, knowledge about catalytic residues is also useful for protein engineering and drug-design. However, to experimentally identify catalytic residues remains challenging for reasons of time and cost. Therefore, computational methods have been explored to predict catalytic residues. Here, we developed a new algorithm, L1pred, for catalytic residue prediction, by using the L1-logreg classifier to integrate eight sequence-based scoring functions. We tested L1pred and compared it against several existing sequence-based methods on carefully designed datasets Data604 and Data63. With ten-fold cross-validation, L1pred showed the area under precision-recall curve (AUPR) and the area under ROC curve (AUC) of 0.2198 and 0.9494 on the training dataset, Data604, respectively. In addition, on the independent test dataset, Data63, it showed the AUPR and AUC values of 0.2636 and 0.9375, respectively. Compared with other sequence-based methods, L1pred showed the best performance on both datasets. We also analyzed the importance of each attribute in the algorithm, and found that all the scores contributed more or less equally to the L1pred performance.

Ligand-binding site prediction using ligand-interacting and binding site-enriched protein triangles

MOTIVATION

Knowledge about the site at which a ligand binds provides an important clue for predicting the function of a protein and is also often a prerequisite for performing docking computations in virtual drug design and screening. We have previously shown that certain ligand-interacting triangles of protein atoms, called protein triangles, tend to occur more frequently at ligand-binding sites than at other parts of the protein.

RESULTS

In this work, we describe a new ligand-binding site prediction method that was developed based on binding site-enriched protein triangles. The new method was tested on 2 benchmark datasets and on 19 targets from two recent community-based studies of such predictions, and excellent results were obtained. Where comparisons were made, the success rates for the new method for the first predicted site were significantly better than methods that are not a meta-predictor. Further examination showed that, for most of the unsuccessful predictions, the pocket of the ligand-binding site was identified, but not the site itself, whereas for some others, the failure was not due to the method itself but due to the use of an incorrect biological unit in the structure examined, although using correct biological units would not necessarily improve the prediction success rates. These results suggest that the new method is a valuable new addition to a suite of existing structure-based bioinformatics tools for studies of molecular recognition and related functions of proteins in post-genomics research.

AVAILABILITY

The executable binaries and a web server for our method are available from http://sourceforge.net/projects/msdock/ and http://lise.ibms.sinica.edu.tw, respectively, free for academic users.

Sequence-based enzyme catalytic domain prediction using clustering and aggregated mutual information content

Characterizing enzyme sequences and identifying their active sites is a very important task. The current experimental methods are too expensive and labor intensive to handle the rapidly accumulating protein sequences and structure data. Thus accurate, high-throughput in silico methods for identifying catalytic residues and enzyme function prediction are much needed. In this paper, we propose a novel sequence-based catalytic domain prediction method using a sequence clustering and an information-theoretic approaches. The first step is to perform the sequence clustering analysis of enzyme sequences from the same functional category (those with the same EC label). The clustering analysis is used to handle the problem of widely varying sequence similarity levels in enzyme sequences. The clustering analysis constructs a sequence graph where nodes are enzyme sequences and edges are a pair of sequences with a certain degree of sequence similarity, and uses graph properties, such as biconnected components and articulation points, to generate sequence segments common to the enzyme sequences. Then amino acid subsequences in the common shared regions are aligned and then an information theoretic approach called aggregated column related scoring scheme is performed to highlight potential active sites in enzyme sequences. The aggregated information content scoring scheme is shown to be effective to highlight residues of active sites effectively. The proposed method of combining the clustering and the aggregated information content scoring methods was successful in highlighting known catalytic sites in enzymes of Escherichia coli K12 in terms of the Catalytic Site Atlas database. Our method is shown to be not only accurate in predicting potential active sites in the enzyme sequences but also computationally efficient since the clustering approach utilizes two graph properties that can be computed in linear to the number of edges in the sequence graph and computation of mutual information does not require much time. We believe that the proposed method can be useful for identifying active sites of enzyme sequences from many genome projects.

Using shifts in amino acid frequency and substitution rate to identify latent structural characters in base-excision repair enzymes

Protein evolution includes the birth and death of structural motifs. For example, a zinc finger or a salt bridge may be present in some, but not all, members of a protein family. We propose that such transitions are manifest in sequence phylogenies as concerted shifts in substitution rates of amino acids that are neighbors in a representative structure. First, we identified rate shifts in a quartet from the Fpg/Nei family of base excision repair enzymes using a method developed by Xun Gu and coworkers. We found the shifts to be spatially correlated, more precisely, associated with a flexible loop involved in bacterial Fpg substrate specificity. Consistent with our result, sequences and structures provide convincing evidence that this loop plays a very different role in other family members. Second, then, we developed a method for identifying latent protein structural characters (LSC) given a set of homologous sequences based on Gu's method and proximity in a high-resolution structure. Third, we identified LSC and assigned states of LSC to clades within the Fpg/Nei family of base excision repair enzymes. We describe seven LSC; an accompanying Proteopedia page (http://proteopedia.org/wiki/index.php/Fpg_Nei_Protein_Family) describes these in greater detail and facilitates 3D viewing. The LSC we found provided a surprisingly complete picture of the interaction of the protein with the DNA capturing familiar examples, such as a Zn finger, as well as more subtle interactions. Their preponderance is consistent with an important role as phylogenetic characters. Phylogenetic inference based on LSC provided convincing evidence of independent losses of Zn fingers. Structural motifs may serve as important phylogenetic characters and modeling transitions involving structural motifs may provide a much deeper understanding of protein evolution.

AADS--an automated active site identification, docking, and scoring protocol for protein targets based on physicochemical descriptors

We report here a robust automated active site detection, docking, and scoring (AADS) protocol for proteins with known structures. The active site finder identifies all cavities in a protein and scores them based on the physicochemical properties of functional groups lining the cavities in the protein. The accuracy realized on 620 proteins with sizes ranging from 100 to 600 amino acids with known drug active sites is 100% when the top ten cavity points are considered. These top ten cavity points identified are then submitted for an automated docking of an input ligand/candidate molecule. The docking protocol uses an all atom energy based Monte Carlo method. Eight low energy docked structures corresponding to different locations and orientations of the candidate molecule are stored at each cavity point giving 80 docked structures overall which are then ranked using an effective free energy function and top five structures are selected. The predicted structure and energetics of the complexes agree quite well with experiment when tested on a data set of 170 protein-ligand complexes with known structures and binding affinities. The AADS methodology is implemented on an 80 processor cluster and presented as a freely accessible, easy to use tool at http://www.scfbio-iitd.res.in/dock/ActiveSite_new.jsp .

Structure-based identification of catalytic residues

The identification of catalytic residues is an essential step in functional characterization of enzymes. We present a purely structural approach to this problem, which is motivated by the difficulty of evolution-based methods to annotate structural genomics targets that have few or no homologs in the databases. Our approach combines a state-of-the-art support vector machine (SVM) classifier with novel structural features that augment structural clues by spatial averaging and Z scoring. Special attention is paid to the class imbalance problem that stems from the overwhelming number of non-catalytic residues in enzymes compared to catalytic residues. This problem is tackled by: (1) optimizing the classifier to maximize a performance criterion that considers both Type I and Type II errors in the classification of catalytic and non-catalytic residues; (2) under-sampling non-catalytic residues before SVM training; and (3) during SVM training, penalizing errors in learning catalytic residues more than errors in learning non-catalytic residues. Tested on four enzyme datasets, one specifically designed by us to mimic the structural genomics scenario and three previously evaluated datasets, our structure-based classifier is never inferior to similar structure-based classifiers and comparable to classifiers that use both structural and evolutionary features. In addition to the evaluation of the performance of catalytic residue identification, we also present detailed case studies on three proteins. This analysis suggests that many false positive predictions may correspond to binding sites and other functional residues. A web server that implements the method, our own-designed database, and the source code of the programs are publicly available at http://www.cs.bgu.ac.il/∼meshi/functionPrediction.

Macromolecular complexes in crystals and solutions

This paper presents a discussion of existing methods for the analysis of macromolecular interactions and complexes in crystal packing. Typical situations and conditions where wrong answers may be obtained in the course of ordinary procedures are presented and discussed. The more general question of what the relationship is between natural (in-solvent) and crystallized assemblies is discussed and researched. A computational analysis suggests that weak interactions with K(d) ≥ 100 µM have a considerable chance of being lost during the course of crystallization. In such instances, crystal packing misrepresents macromolecular complexes and interactions. For as many as 20% of protein dimers in the PDB the likelihood of misrepresentation is estimated to be higher than 50%. Given that weak macromolecular interactions play an important role in many biochemical processes, these results suggest that a complementary noncrystallographic study should be always conducted when inferring structural aspects of weakly bound complexes.

Novel feature for catalytic protein residues reflecting interactions with other residues

Owing to their potential for systematic analysis, complex networks have been widely used in proteomics. Representing a protein structure as a topology network provides novel insight into understanding protein folding mechanisms, stability and function. Here, we develop a new feature to reveal correlations between residues using a protein structure network. In an original attempt to quantify the effects of several key residues on catalytic residues, a power function was used to model interactions between residues. The results indicate that focusing on a few residues is a feasible approach to identifying catalytic residues. The spatial environment surrounding a catalytic residue was analyzed in a layered manner. We present evidence that correlation between residues is related to their distance apart most environmental parameters of the outer layer make a smaller contribution to prediction and ii catalytic residues tend to be located near key positions in enzyme folds. Feature analysis revealed satisfactory performance for our features, which were combined with several conventional features in a prediction model for catalytic residues using a comprehensive data set from the Catalytic Site Atlas. Values of 88.6 for sensitivity and 88.4 for specificity were obtained by 10fold crossvalidation. These results suggest that these features reveal the mutual dependence of residues and are promising for further study of structurefunction relationship.

Evolutionary approach to predicting the binding site residues of a protein from its primary sequence

Protein binding site residues, especially catalytic residues, play a central role in protein function. Because more than 99% of the ∼ 12 million protein sequences in the nonredundant protein database have no structural information, it is desirable to develop methods to predict the binding site residues of a protein from its primary sequence. This task is highly challenging, because the binding site residues constitute only a small portion of a protein. However, the binding site residues of a protein are clustered in its functional pocket(s), and their spatial patterns tend to be conserved in evolution. To take advantage of these evolutionary and structural principles, we constructed a database of ∼ 50,000 templates (called the pocket-containing segment database), each of which includes not only a sequence segment that contains a functional pocket but also the structural attributes of the pocket. To use this database, we designed a template-matching technique, termed residue-matching profiling, and established a criterion for selecting templates for a query sequence. Finally, we developed a probabilistic model for assigning spatial scores to matched residues between the template and query sequence in local alignments using a set of selected scoring matrices and for computing the binding likelihood of each matched residue in the query sequence. From the likelihoods, one can predict the binding site residues in the query sequence. An automated computational pipeline was developed for our method. A performance evaluation shows that our method achieves a 70% precision in predicting binding site residues at 60% sensitivity.

Catalytic residues in hydrolases: analysis of methods designed for ligand-binding site prediction

The comparison of eight tools applicable to ligand-binding site prediction is presented. The methods examined cover three types of approaches: the geometrical (CASTp, PASS, Pocket-Finder), the physicochemical (Q-SiteFinder, FOD) and the knowledge-based (ConSurf, SuMo, WebFEATURE). The accuracy of predictions was measured in reference to the catalytic residues documented in the Catalytic Site Atlas. The test was performed on a set comprising selected chains of hydrolases. The results were analysed with regard to size, polarity, secondary structure, accessible solvent area of predicted sites as well as parameters commonly used in machine learning (F-measure, MCC). The relative accuracies of predictions are presented in the ROC space, allowing determination of the optimal methods by means of the ROC convex hull. Additionally the minimum expected cost analysis was performed. Both advantages and disadvantages of the eight methods are presented. Characterization of protein chains in respect to the level of difficulty in the active site prediction is introduced. The main reasons for failures are discussed. Overall, the best performance offers SuMo followed by FOD, while Pocket-Finder is the best method among the geometrical approaches.

Efficient design of bio-basis function to predict protein functional sites using kernel-based classifiers

In order to apply the powerful kernel-based pattern recognition algorithms such as support vector machines to predict functional sites in proteins, amino acids need encoding prior to input. In this regard, a new string kernel function, termed as the modified bio-basis function, is proposed that maps a nonnumerical sequence space to a numerical feature space. The proposed string kernel function is developed based on the conventional bio-basis function and needs a bio-basis string as a support like conventional kernel function. The concept of zone of influence of a bio-basis string is introduced in the proposed kernel function to take into account the influence of each bio-basis string in nonnumerical sequence space. An efficient method is described to select a set of bio-basis strings for the proposed kernel function, integrating the Fisher ratio and a novel concept of degree of resemblance. The integration enables the method to select a reduced set of relevant and nonredundant bio-basis strings.

Sequence and structure continuity of evolutionary importance improves protein functional site discovery and annotation

Protein functional sites control most biological processes and are important targets for drug design and protein engineering. To characterize them, the evolutionary trace (ET) ranks the relative importance of residues according to their evolutionary variations. Generally, top-ranked residues cluster spatially to define evolutionary hotspots that predict functional sites in structures. Here, various functions that measure the physical continuity of ET ranks among neighboring residues in the structure, or in the sequence, are shown to inform sequence selection and to improve functional site resolution. This is shown first, in 110 proteins, for which the overlap between top-ranked residues and actual functional sites rose by 8% in significance. Then, on a structural proteomic scale, optimized ET led to better 3D structure-function motifs (3D templates) and, in turn, to enzyme function prediction by the Evolutionary Trace Annotation (ETA) method with better sensitivity of (40% to 53%) and positive predictive value (93% to 94%). This suggests that the similarity of evolutionary importance among neighboring residues in the sequence and in the structure is a universal feature of protein evolution. In practice, this yields a tool for optimizing sequence selections for comparative analysis and, via ET, for better predictions of functional site and function. This should prove useful for the efficient mutational redesign of protein function and for pharmaceutical targeting.

Structure-based kernels for the prediction of catalytic residues and their involvement in human inherited disease

MOTIVATION

Enzyme catalysis is involved in numerous biological processes and the disruption of enzymatic activity has been implicated in human disease. Despite this, various aspects of catalytic reactions are not completely understood, such as the mechanics of reaction chemistry and the geometry of catalytic residues within active sites. As a result, the computational prediction of catalytic residues has the potential to identify novel catalytic pockets, aid in the design of more efficient enzymes and also predict the molecular basis of disease.

RESULTS

We propose a new kernel-based algorithm for the prediction of catalytic residues based on protein sequence, structure and evolutionary information. The method relies upon explicit modeling of similarity between residue-centered neighborhoods in protein structures. We present evidence that this algorithm evaluates favorably against established approaches, and also provides insights into the relative importance of the geometry, physicochemical properties and evolutionary conservation of catalytic residue activity. The new algorithm was used to identify known mutations associated with inherited disease whose molecular mechanism might be predicted to operate specifically though the loss or gain of catalytic residues. It should, therefore, provide a viable approach to identifying the molecular basis of disease in which the loss or gain of function is not caused solely by the disruption of protein stability. Our analysis suggests that both mechanisms are actively involved in human inherited disease.

AVAILABILITY AND IMPLEMENTATION

Source code for the structural kernel is available at www.informatics.indiana.edu/predrag/.

Conserved residue clusters at protein-protein interfaces and their use in binding site identification

BACKGROUND

Biological evolution conserves protein residues that are important for structure and function. Both protein stability and function often require a certain degree of structural co-operativity between spatially neighboring residues and it has previously been shown that conserved residues occur clustered together in protein tertiary structures, enzyme active sites and protein-DNA interfaces. Residues comprising protein interfaces are often more conserved compared to those occurring elsewhere on the protein surface. We investigate the extent to which conserved residues within protein-protein interfaces are clustered together in three-dimensions.

RESULTS

Out of 121 and 392 interfaces in homodimers and heterocomplexes, 96.7 and 86.7%, respectively, have the conserved positions clustered within the overall interface region. The significance of this clustering was established in comparison to what is seen for the subsets of the same size of randomly selected residues from the interface. Conserved residues occurring in larger interfaces could often be sub-divided into two or more distinct sub-clusters. These structural cluster(s) comprising conserved residues indicate functionally important regions within the protein-protein interface that can be targeted for further structural and energetic analysis by experimental scanning mutagenesis. Almost 60% of experimental hot spot residues (with DeltaDeltaG > 2 kcal/mol) were localized to these conserved residue clusters. An analysis of the residue types that are enriched within these conserved subsets compared to the overall interface showed that hydrophobic and aromatic residues are favored, but charged residues (both positive and negative) are less common. The potential use of this method for discriminating binding sites (interfaces) versus random surface patches was explored by comparing the clustering of conserved residues within each of these regions--in about 50% cases the true interface is ranked among the top 10% of all surface patches.

CONCLUSIONS

Protein-protein interaction sites are much larger than small molecule biding sites, but still conserved residues are not randomly distributed over the whole interface and are distinctly clustered. The clustered nature of evolutionarily conserved residues within interfaces as compared to those within other surface patches not involved in binding has important implications for the identification of protein-protein binding sites and would have applications in docking studies.