Gene structure prediction by spliced alignment of genomic DNA with protein sequences: increased accuracy by differential splice site scoring

Gene identification in genomic DNA from eukaryotes is complicated by the vast combinatorial possibilities of potential exon assemblies. If the gene encodes a protein that is closely related to known proteins, gene identification is aided by matching similarity of potential translation products to those target proteins. The genomic DNA and protein sequences can be aligned directly by scoring the implied residues of in-frame nucleotide triplets against the protein residues in conventional ways, while allowing for long gaps in the alignment corresponding to introns in the genomic DNA. We describe a novel method for such spliced alignment. The method derives an optimal alignment based on scoring for both sequence similarity of the predicted gene product to the protein sequence and intrinsic splice site strength of the predicted introns. Application of the method to a representative set of 50 known genes from Arabidopsis thaliana showed significant improvement in prediction accuracy compared to previous spliced alignment methods. The method is also more accurate than ab initio gene prediction methods, provided sufficiently close target proteins are available. In view of the fast growth of public sequence repositories, we argue that close targets will be available for the majority of novel genes, making spliced alignment an excellent practical tool for high-throughput automated genome annotation.     

Residue-level prediction of DNA-binding sites and its application on DNA-binding protein predictions

Protein-DNA interactions are crucial to many cellular activities such as expression-control and DNA-repair. These interactions between amino acids and nucleotides are highly specific and any aberrance at the binding site can render the interaction completely incompetent. In this study, we have three aims focusing on DNA-binding residues on the protein surface: to develop an automated approach for fast and reliable recognition of DNA-binding sites; to improve the prediction by distance-dependent refinement; use these predictions to identify DNA-binding proteins. We use a support vector machines (SVM)-based approach to harness the features of the DNA-binding residues to distinguish them from non-binding residues. Features used for distinction include the residue's identity, charge, solvent accessibility, average potential, the secondary structure it is embedded in, neighboring residues, and location in a cationic patch. These features collected from 50 proteins are used to train SVM. Testing is then performed on another set of 37 proteins, much larger than any testing set used in previous studies. The testing set has no more than 20% sequence identity not only among its pairs, but also with the proteins in the training set, thus removing any undesired redundancy due to homology. This set also has proteins with an unseen DNA-binding structural class not present in the training set. With the above features, an accuracy of 66% with balanced sensitivity and specificity is achieved without relying on homology or evolutionary information. We then develop a post-processing scheme to improve the prediction using the relative location of the predicted residues. Balanced success is then achieved with average sensitivity, specificity and accuracy pegged at 71.3%, 69.3% and 70.5%, respectively. Average net prediction is also around 70%. Finally, we show that the number of predicted DNA-binding residues can be used to differentiate DNA-binding proteins from non-DNA-binding proteins with an accuracy of 78%. Results presented here demonstrate that machine-learning can be applied to automated identification of DNA-binding residues and that the success rate can be ameliorated as more features are added. Such functional site prediction protocols can be useful in guiding consequent works such as site-directed mutagenesis and macromolecular docking.     

Coupling dynamics and evolutionary information with structure to identify protein regulatory and functional binding sites

Binding sites in proteins can be either specifically functional binding sites (active sites) that bind specific substrates with high affinity or regulatory binding sites (allosteric sites), that modulate the activity of functional binding sites through effector molecules. Owing to their significance in determining protein function, the identification of protein functional and regulatory binding sites is widely acknowledged as an important biological problem. In this work, we present a novel binding site prediction method, Active and Regulatory site Prediction (AR-Pred), which supplements protein geometry, evolutionary, and physicochemical features with information about protein dynamics to predict putative active and allosteric site residues. As the intrinsic dynamics of globular proteins plays an essential role in controlling binding events, we find it to be an important feature for the identification of protein binding sites. We train and validate our predictive models on multiple balanced training and validation sets with random forest machine learning and obtain an ensemble of discrete models for each prediction type. Our models for active site prediction yield a median area under the curve (AUC) of 91% and Matthews correlation coefficient (MCC) of 0.68, whereas the less well-defined allosteric sites are predicted at a lower level with a median AUC of 80% and MCC of 0.48. When tested on an independent set of proteins, our models for active site prediction show comparable performance to two existing methods and gains compared to two others, while the allosteric site models show gains when tested against three existing prediction methods. AR-Pred is available as a free downloadable package at https://github.com/sambitmishra0628/AR-PRED_source .     

Probabilistic protein function prediction from heterogeneous genome-wide data

Dramatic improvements in high throughput sequencing technologies have led to a staggering growth in the number of predicted genes. However, a large fraction of these newly discovered genes do not have a functional assignment. Fortunately, a variety of novel high-throughput genome-wide functional screening technologies provide important clues that shed light on gene function. The integration of heterogeneous data to predict protein function has been shown to improve the accuracy of automated gene annotation systems. In this paper, we propose and evaluate a probabilistic approach for protein function prediction that integrates protein-protein interaction (PPI) data, gene expression data, protein motif information, mutant phenotype data, and protein localization data. First, functional linkage graphs are constructed from PPI data and gene expression data, in which an edge between nodes (proteins) represents evidence for functional similarity. The assumption here is that graph neighbors are more likely to share protein function, compared to proteins that are not neighbors. The functional linkage graph model is then used in concert with protein domain, mutant phenotype and protein localization data to produce a functional prediction. Our method is applied to the functional prediction of Saccharomyces cerevisiae genes, using Gene Ontology (GO) terms as the basis of our annotation. In a cross validation study we show that the integrated model increases recall by 18%, compared to using PPI data alone at the 50% precision. We also show that the integrated predictor is significantly better than each individual predictor. However, the observed improvement vs. PPI depends on both the new source of data and the functional category to be predicted. Surprisingly, in some contexts integration hurts overall prediction accuracy. Lastly, we provide a comprehensive assignment of putative GO terms to 463 proteins that currently have no assigned function.     

Assignment of protein function and discovery of novel nucleolar proteins based on automatic analysis of MEDLINE

Attribution of the most probable functions to proteins identified by proteomics is a significant challenge that requires extensive literature analysis. We have developed a system for automated prediction of implicit and explicit biologically meaningful functions for a proteomics study of the nucleolus. This approach uses a set of vocabulary terms to map and integrate the information from the entire MEDLINE database. Based on a combination of cross-species sequence homology searches and the corresponding literature, our approach facilitated the direct association between sequence data and information from biological texts describing function. Comparison of our automated functional assignment to manual annotation demonstrated our method to be highly effective. To establish the sensitivity, we defined the functional subtleties within a family containing a highly conserved sequence. Clustering of the DEAD-box protein family of RNA helicases confirmed that these proteins shared similar morphology although functional subfamilies were accurately identified by our approach. We visualized the nucleolar proteome in terms of protein functions using multi-dimensional scaling, showing functional associations between nucleolar proteins that were not previously realized. Finally, by clustering the functional properties of the established nucleolar proteins, we predicted novel nucleolar proteins. Subsequently, nonproteomics studies confirmed the predictions of previously unidentified nucleolar proteins.     

Assigning function to yeast proteins by integration of technologies

Interpreting genome sequences requires the functional analysis of thousands of predicted proteins, many of which are uncharacterized and without obvious homologs. To assess whether the roles of large sets of uncharacterized genes can be assigned by targeted application of a suite of technologies, we used four complementary protein-based methods to analyze a set of 100 uncharacterized but essential open reading frames (ORFs) of the yeast Saccharomyces cerevisiae. These proteins were subjected to affinity purification and mass spectrometry analysis to identify copurifying proteins, two-hybrid analysis to identify interacting proteins, fluorescence microscopy to localize the proteins, and structure prediction methodology to predict structural domains or identify remote homologies. Integration of the data assigned function to 48 ORFs using at least two of the Gene Ontology (GO) categories of biological process, molecular function, and cellular component; 77 ORFs were annotated by at least one method. This combination of technologies, coupled with annotation using GO, is a powerful approach to classifying genes.     

Identification of functional subclasses in the DJ-1 superfamily proteins

Genomics has posed the challenge of determination of protein function from sequence and/or 3-D structure. Functional assignment from sequence relationships can be misleading, and structural similarity does not necessarily imply functional similarity. Proteins in the DJ-1 family, many of which are of unknown function, are examples of proteins with both sequence and fold similarity that span multiple functional classes. THEMATICS (theoretical microscopic titration curves), an electrostatics-based computational approach to functional site prediction, is used to sort proteins in the DJ-1 family into different functional classes. Active site residues are predicted for the eight distinct DJ-1 proteins with available 3-D structures. Placement of the predicted residues onto a structural alignment for six of these proteins reveals three distinct types of active sites. Each type overlaps only partially with the others, with only one residue in common across all six sets of predicted residues. Human DJ-1 and YajL from Escherichia coli have very similar predicted active sites and belong to the same probable functional group. Protease I, a known cysteine protease from Pyrococcus horikoshii, and PfpI/YhbO from E. coli, a hypothetical protein of unknown function, belong to a separate class. THEMATICS predicts a set of residues that is typical of a cysteine protease for Protease I; the prediction for PfpI/YhbO bears some similarity. YDR533Cp from Saccharomyces cerevisiae, of unknown function, and the known chaperone Hsp31 from E. coli constitute a third group with nearly identical predicted active sites. While the first four proteins have predicted active sites at dimer interfaces, YDR533Cp and Hsp31 both have predicted sites contained within each subunit. Although YDR533Cp and Hsp31 form different dimers with different orientations between the subunits, the predicted active sites are superimposable within the monomer structures. Thus, the three predicted functional classes form four different types of quaternary structures. The computational prediction of the functional sites for protein structures of unknown function provides valuable clues for functional classification.     

Analysis and prediction of functional sub-types from protein sequence alignments

The increasing number and diversity of protein sequence families requires new methods to define and predict details regarding function. Here, we present a method for analysis and prediction of functional sub-types from multiple protein sequence alignments. Given an alignment and set of proteins grouped into sub-types according to some definition of function, such as enzymatic specificity, the method identifies positions that are indicative of functional differences by comparison of sub-type specific sequence profiles, and analysis of positional entropy in the alignment. Alignment positions with significantly high positional relative entropy correlate with those known to be involved in defining sub-types for nucleotidyl cyclases, protein kinases, lactate/malate dehydrogenases and trypsin-like serine proteases. We highlight new positions for these proteins that suggest additional experiments to elucidate the basis of specificity. The method is also able to predict sub-type for unclassified sequences. We assess several variations on a prediction method, and compare them to simple sequence comparisons. For assessment, we remove close homologues to the sequence for which a prediction is to be made (by a sequence identity above a threshold). This simulates situations where a protein is known to belong to a protein family, but is not a close relative of another protein of known sub-type. Considering the four families above, and a sequence identity threshold of 30 %, our best method gives an accuracy of 96 % compared to 80 % obtained for sequence similarity and 74 % for BLAST. We describe the derivation of a set of sub-type groupings derived from an automated parsing of alignments from PFAM and the SWISSPROT database, and use this to perform a large-scale assessment. The best method gives an average accuracy of 94 % compared to 68 % for sequence similarity and 79 % for BLAST. We discuss implications for experimental design, genome annotation and the prediction of protein function and protein intra-residue distances.     

A tool for the prediction of functionally important sites in proteins using a library of functional templates

Understanding and characterizing the biochemical and evolutionary information within the wealth of protein sequence and structural data, particularly at functionally important sites, is very important. A comprehensive analysis of physico-chemical properties and evolutionary conservation patterns at the molecular and biological function level is expected to yield important clues for identifying similar sites in as-yet uncharacterized proteins. We present a library of protein functional templates (PFTs) designed to represent the compositional and evolutionary conservation patterns of functional sites at the molecular and biological function level. Subsequently we developed LIMACS (LInear MAtching of Conservation Scores), a software tool that uses the template library for the prediction of functionally important sites in a multiple sequence alignment, transferring the molecular function annotation from the most-similar functional site in the template library to a predicted site.     

HotPatch: a statistical approach to finding biologically relevant features on protein surfaces

We describe a fully automated algorithm for finding functional sites on protein structures. Our method finds surface patches of unusual physicochemical properties on protein structures, and estimates the patches' probability of overlapping functional sites. Other methods for predicting the locations of specific types of functional sites exist, but in previous analyses, it has been difficult to compare methods when they are applied to different types of sites. Thus, we introduce a new statistical framework that enables rigorous comparisons of the usefulness of different physicochemical properties for predicting virtually any kind of functional site. The program's statistical models were trained for 11 individual properties (electrostatics, concavity, hydrophobicity, etc.) and for 15 neural network combination properties, all optimized and tested on 15 diverse protein functions. To simulate what to expect if the program were run on proteins of unknown function, as might arise from structural genomics, we tested it on 618 proteins of diverse mixed functions. In the higher-scoring top half of all predictions, a functional residue could typically be found within the first 1.7 residues chosen at random. The program may or may not use partial information about the protein's function type as an input, depending on which statistical model the user chooses to employ. If function type is used as an additional constraint, prediction accuracy usually increases, and is particularly good for enzymes, DNA-interacting sites, and oligomeric interfaces. The program can be accessed online (at http://hotpatch.mbi.ucla.edu).     

Predicting reliable regions in protein alignments from sequence profiles

For applications such as comparative modelling one major issue is the reliability of sequence alignments. Reliable regions in alignments can be predicted using sub-optimal alignments of the same pair of sequences. Here we show that reliable regions in alignments can also be predicted from multiple sequence profile information alone.Alignments were created for a set of remotely related pairs of proteins using five different test methods. Structural alignments were used to assess the quality of the alignments and the aligned positions were scored using information from the observed frequencies of amino acid residues in sequence profiles pre-generated for each template structure. High-scoring regions of these profile-derived alignment scores were a good predictor of reliably aligned regions.These profile-derived alignment scores are easy to obtain and are applicable to any alignment method. They can be used to detect those regions of alignments that are reliably aligned and to help predict the quality of an alignment. For those residues within secondary structure elements, the regions predicted as reliably aligned agreed with the structural alignments for between 92% and 97.4% of the residues. In loop regions just under 92% of the residues predicted to be reliable agreed with the structural alignments. The percentage of residues predicted as reliable ranged from 32.1% for helix residues to 52.8% for strand residues.This information could also be used to help predict conserved binding sites from sequence alignments. Residues in the template that were identified as binding sites, that aligned to an identical amino acid residue and where the sequence alignment agreed with the structural alignment were in highly conserved, high scoring regions over 80% of the time. This suggests that many binding sites that are present in both target and template sequences are in sequence-conserved regions and that there is the possibility of translating reliability to binding site prediction.     

Piecing together the structure-function puzzle: experiences in structure-based functional annotation of hypothetical proteins

The combination of genomic sequencing with structural genomics has provided a wealth of new structures for previously uncharacterized ORFs, more commonly referred to as hypothetical proteins. This rapid growth has been the direct result of high-throughput, automated approaches in both the identification of new ORFs and the determination of high-resolution 3-D protein structures. A significant bottleneck is reached, however, at the stage of functional annotation in that the assignment of function is not readily automatable. It is often the case that the initial structural analysis at best indicates a functional family for a given hypothetical protein, but further identification of a relevant ligand or substrate is impeded by the diversity of function in a particular structural classification of proteins family, a highly selective and specific ligand-binding site, or the identification of a novel protein fold. Our approach to the functional annotation of hypothetical proteins relies on the combination of structural information with additional bioinformatics evidence garnered from operon prediction, loose functional information of additional operon members, conservation of catalytic residues, as well as cocrystallization trials and virtual ligand screening. The synthesis of all available information for each protein has permitted the functional annotation of several hypothetical proteins from Escherichia coli and each assignment has been confirmed through generally accepted biochemical methods.     

An accurate,sensitive, and scalable method to identify functional sites in protein structures

Functional sites determine the activity and interactions of proteins and as such constitute the targets of most drugs. However, the exponential growth of sequence and structure data far exceeds the ability of experimental techniques to identify their locations and key amino acids. To fill this gap we developed a computational Evolutionary Trace method that ranks the evolutionary importance of amino acids in protein sequences. Studies show that the best-ranked residues form fewer and larger structural clusters than expected by chance and overlap with functional sites, but until now the significance of this overlap has remained qualitative. Here, we use 86 diverse protein structures, including 20 determined by the structural genomics initiative, to show that this overlap is a recurrent and statistically significant feature. An automated ET correctly identifies seven of ten functional sites by the least favorable statistical measure, and nine of ten by the most favorable one. These results quantitatively demonstrate that a large fraction of functional sites in the proteome may be accurately identified from sequence and structure. This should help focus structure-function studies, rational drug design, protein engineering, and functional annotation to the relevant regions of a protein.     

Evaluation of features for catalytic residue prediction in novel folds

Structural genomics projects are determining the three-dimensional structure of proteins without full characterization of their function. A critical part of the annotation process involves appropriate knowledge representation and prediction of functionally important residue environments. We have developed a method to extract features from sequence, sequence alignments, three-dimensional structure, and structural environment conservation, and used support vector machines to annotate homologous and nonhomologous residue positions based on a specific training set of residue functions. In order to evaluate this pipeline for automated protein annotation, we applied it to the challenging problem of prediction of catalytic residues in enzymes. We also ranked the features based on their ability to discriminate catalytic from noncatalytic residues. When applying our method to a well-annotated set of protein structures, we found that top-ranked features were a measure of sequence conservation, a measure of structural conservation, a degree of uniqueness of a residue's structural environment, solvent accessibility, and residue hydrophobicity. We also found that features based on structural conservation were complementary to those based on sequence conservation and that they were capable of increasing predictor performance. Using a family nonredundant version of the ASTRAL 40 v1.65 data set, we estimated that the true catalytic residues were correctly predicted in 57.0% of the cases, with a precision of 18.5%. When testing on proteins containing novel folds not used in training, the best features were highly correlated with the training on families, thus validating the approach to nonhomologous catalytic residue prediction in general. We then applied the method to 2781 coordinate files from the structural genomics target pipeline and identified both highly ranked and highly clustered groups of predicted catalytic residues.     

Protein function annotation by local binding site surface similarity

Hundreds of protein crystal structures exist for proteins whose function cannot be confidently determined from sequence similarity. Surflex‐PSIM, a previously reported surface‐based protein similarity algorithm, provides an alternative method for hypothesizing function for such proteins. The method now supports fully automatic binding site detection and is fast enough to screen comprehensive databases of protein binding sites. The binding site detection methodology was validated on apo/holo cognate protein pairs, correctly identifying 91% of ligand binding sites in holo structures and 88% in apo structures where corresponding sites existed. For correctly detected apo binding sites, the cognate holo site was the most similar binding site 87% of the time. PSIM was used to screen a set of proteins that had poorly characterized functions at the time of crystallization, but were later biochemically annotated. Using a fully automated protocol, this set of 8 proteins was screened against ～60,000 ligand binding sites from the PDB. PSIM correctly identified functional matches that predated query protein biochemical annotation for five out of the eight query proteins. A panel of 12 currently unannotated proteins was also screened, resulting in a large number of statistically significant binding site matches, some of which suggest likely functions for the podorly characterized proteins. Proteins 2014; 82:679–694. © 2013 Wiley Periodicals, Inc.     

Computational method for prediction of protein functional sites using specificity determinants

The current available data on protein sequences largely exceeds the experimental capabilities to annotate their function. So annotation in silico, i.e. using computational methods becomes increasingly important. This annotation is inevitably a prediction, but it can be an important starting point for further experimental studies. Here we present a method for prediction of protein functional sites, SDPsite, based on the identification of protein specificity determinants. Taking as an input a protein sequence alignment and a phylogenetic tree, the algorithm predicts conserved positions and specificity determinants, maps them onto the protein's 3D structure, and searches for clusters of the predicted positions. Comparison of the obtained predictions with experimental data and data on performance of several other methods for prediction of functional sites reveals that SDPsite agrees well with the experiment and outperforms most of the previously available methods. SDPsite is publicly available under http://bioinf.fbb.msu.ru/SDPsite.     

Prediction of catalytic residues using Support Vector Machine with selected protein sequence and structural properties

Background  

The number of protein sequences deriving from genome sequencing projects is outpacing our knowledge about the function of these proteins. With the gap between experimentally characterized and uncharacterized proteins continuing to widen, it is necessary to develop new computational methods and tools for functional prediction. Knowledge of catalytic sites provides a valuable insight into protein function. Although many computational methods have been developed to predict catalytic residues and active sites, their accuracy remains low, with a significant number of false positives. In this paper, we present a novel method for the prediction of catalytic sites, using a carefully selected, supervised machine learning algorithm coupled with an optimal discriminative set of protein sequence conservation and structural properties.     

Functional classification of protein 3D structures from predicted local interaction sites

A new approach to the functional classification of protein 3D structures is described with application to some examples from structural genomics. This approach is based on functional site prediction with THEMATICS and POOL. THEMATICS employs calculated electrostatic potentials of the query structure. POOL is a machine learning method that utilizes THEMATICS features and has been shown to predict accurate, precise, highly localized interaction sites. Extension to the functional classification of structural genomics proteins is now described. Predicted functionally important residues are structurally aligned with those of proteins with previously characterized biochemical functions. A 3D structure match at the predicted local functional site then serves as a more reliable predictor of biochemical function than an overall structure match. Annotation is confirmed for a structural genomics protein with the ribulose phosphate binding barrel (RPBB) fold. A putative glucoamylase from Bacteroides fragilis (PDB ID 3eu8) is shown to be in fact probably not a glucoamylase. Finally a structural genomics protein from Streptomyces coelicolor annotated as an enoyl-CoA hydratase (PDB ID 3g64) is shown to be misannotated. Its predicted active site does not match the well-characterized enoyl-CoA hydratases of similar structure but rather bears closer resemblance to those of a dehalogenase with similar fold.