Comparing protein sequence-based and predicted secondary structure-based methods for identification of remote homologs.

We have compared a novel sequence-structure matching technique, FORESST, for detecting remote homologs to three existing sequence based methods, including local amino acid sequence similarity by BLASTP, hidden Markov models (HMMs) of sequences of protein families using SAM, HMMs based on sequence motifs identified using meta-MEME. FORESST compares predicted secondary structures to a library of structural families of proteins, using HMMs. Altogether 45 proteins from nine structural families in the database CATH were used in a cross-validated test of the fold assignment accuracy of each method. Local sequence similarity of a query sequence to a protein family is measured by the highest segment pair (HSP) score. Each of the HMM-based approaches (FORESST, MEME, amino acid sequence-based HMM) yielded log-odds score for the query sequence. In order to make a fair comparison among these methods, the scores for each method were converted to Z-scores in a uniform way by comparing the raw scores of a query protein with the corresponding scores for a set of unrelated proteins. Z-Scores were analyzed as a function of the maximum pairwise sequence identity (MPSID) of the query sequence to sequences used in training the model. For MPSID above 20%, the Z-scores increase linearly with MPSID for the sequence-based methods but remain roughly constant for FORESST. Below 15%, average Z-scores are close to zero for the sequence-based methods, whereas the FORESST method yielded average Z-scores of 1.8 and 1.1, using observed and predicted secondary structures, respectively. This demonstrates the advantage of the sequence-structure method for detecting remote homologs.     

A robust method to detect structural and functional remote homologues

With currently available sequence data, it is feasible to conduct extensive comparisons among large sets of protein sequences. It is still a much more challenging task to partition the protein space into structurally and functionally related families solely based on sequence comparisons. The ProtoNet system automatically generates a treelike classification of the whole protein space. It stands to reason that this classification reflects evolutionary relationships, both close and remote. In this article, we examine this hypothesis. We present a semiautomatic procedure that singles out certain inner nodes in the ProtoNet tree that should ideally correspond to structurally and functionally defined protein families. We compare the performance of this method against several expert systems. Some of the competing methods incorporate additional extraneous information on protein structure or on enzymatic activities. The ProtoNet-based method performs at least as well as any of the methods with which it was compared. This article illustrates the ProtoNet-based method on several evolutionarily diverse families. Using this new method, an evolutionary divergence scheme can be proposed for a large number of structural and functional related superfamilies.     

An efficient algorithm for large-scale detection of protein families

Detection of protein families in large databases is one of the principal research objectives in structural and functional genomics. Protein family classification can significantly contribute to the delineation of functional diversity of homologous proteins, the prediction of function based on domain architecture or the presence of sequence motifs as well as comparative genomics, providing valuable evolutionary insights. We present a novel approach called TRIBE-MCL for rapid and accurate clustering of protein sequences into families. The method relies on the Markov cluster (MCL) algorithm for the assignment of proteins into families based on precomputed sequence similarity information. This novel approach does not suffer from the problems that normally hinder other protein sequence clustering algorithms, such as the presence of multi-domain proteins, promiscuous domains and fragmented proteins. The method has been rigorously tested and validated on a number of very large databases, including SwissProt, InterPro, SCOP and the draft human genome. Our results indicate that the method is ideally suited to the rapid and accurate detection of protein families on a large scale. The method has been used to detect and categorise protein families within the draft human genome and the resulting families have been used to annotate a large proportion of human proteins.     

Structural similarity to link sequence space: new potential superfamilies and implications for structural genomics

The current pace of structural biology now means that protein three-dimensional structure can be known before protein function, making methods for assigning homology via structure comparison of growing importance. Previous research has suggested that sequence similarity after structure-based alignment is one of the best discriminators of homology and often functional similarity. Here, we exploit this observation, together with a merger of protein structure and sequence databases, to predict distant homologous relationships. We use the Structural Classification of Proteins (SCOP) database to link sequence alignments from the SMART and Pfam databases. We thus provide new alignments that could not be constructed easily in the absence of known three-dimensional structures. We then extend the method of Murzin (1993b) to assign statistical significance to sequence identities found after structural alignment and thus suggest the best link between diverse sequence families. We find that several distantly related protein sequence families can be linked with confidence, showing the approach to be a means for inferring homologous relationships and thus possible functions when proteins are of known structure but of unknown function. The analysis also finds several new potential superfamilies, where inspection of the associated alignments and superimpositions reveals conservation of unusual structural features or co-location of conserved amino acids and bound substrates. We discuss implications for Structural Genomics initiatives and for improvements to sequence comparison methods.     

Predicting protein structure classes from function predictions

MOTIVATION: We introduce a new approach to using the information contained in sequence-to-function prediction data in order to recognize protein template classes, a critical step in predicting protein structure. The data on which our method is based comprise probabilities of functional categories; for given query sequences these probabilities are obtained by a neural net that has previously been trained on a variety of functionally important features. On a training set of sequences we assess the relevance of individual functional categories for identifying a given structural family. Using a combination of the most relevant categories, the likelihood of a query sequence to belong to a specific family can be estimated. RESULTS: The performance of the method is evaluated using cross-validation. For a fixed structural family and for every sequence, a score is calculated that measures the evidence for family membership. Even for structural families of small size, family members receive significantly higher scores. For some examples, we show that the relevant functional features identified by this method are biologically meaningful. The proposed approach can be used to improve existing sequence-to-structure prediction methods. AVAILABILITY: Matlab code is available on request from the authors. The data are available at http://www.mpisb.mpg.de/~sommer/Fun2Struc/     

FSSA: a novel method for identifying functional signatures from structural alignments

MOTIVATION: It is commonly believed that sequence determines structure, which in turn determines function. However, the presence of many proteins with the same structural fold but different functions suggests that global structure and function do not always correlate well. RESULTS: We propose a method for accurate functional annotation, based on identification of functional signatures from structural alignments (FSSA) using the Structural Classification of Proteins (SCOP) database. The FSSA method is superior at function discrimination and classification compared with several methods that directly inherit functional annotation information from homology inference, such as Smith-Waterman, PSI-BLAST, hidden Markov models and structure comparison methods, for a large number of structural fold families. Our results indicate that the contributions of amino acid residue types and positions to structure and function are largely separable for proteins in multi-functional fold families.     

In Silico Characterization of Proteins: UniProt,InterPro and Integr8

Nucleic acid sequences from genome sequencing projects are submitted as raw data, from which biologists attempt to elucidate the function of the predicted gene products. The protein sequences are stored in public databases, such as the UniProt Knowledgebase (UniProtKB), where curators try to add predicted and experimental functional information. Protein function prediction can be done using sequence similarity searches, but an alternative approach is to use protein signatures, which classify proteins into families and domains. The major protein signature databases are available through the integrated InterPro database, which provides a classification of UniProtKB sequences. As well as characterization of proteins through protein families, many researchers are interested in analyzing the complete set of proteins from a genome (i.e. the proteome), and there are databases and resources that provide non-redundant proteome sets and analyses of proteins from organisms with completely sequenced genomes. This article reviews the tools and resources available on the web for single and large-scale protein characterization and whole proteome analysis.     

SVM-Prot: Web-based support vector machine software for functional classification of a protein from its primary sequence

Prediction of protein function is of significance in studying biological processes. One approach for function prediction is to classify a protein into functional family. Support vector machine (SVM) is a useful method for such classification, which may involve proteins with diverse sequence distribution. We have developed a web-based software, SVMProt, for SVM classification of a protein into functional family from its primary sequence. SVMProt classification system is trained from representative proteins of a number of functional families and seed proteins of Pfam curated protein families. It currently covers 54 functional families and additional families will be added in the near future. The computed accuracy for protein family classification is found to be in the range of 69.1-99.6%. SVMProt shows a certain degree of capability for the classification of distantly related proteins and homologous proteins of different function and thus may be used as a protein function prediction tool that complements sequence alignment methods. SVMProt can be accessed at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.     

Identification of homology in protein structure classification.

Structural biology and structural genomics are expected to produce many three-dimensional protein structures in the near future. Each new structure raises questions about its function and evolution. Correct functional and evolutionary classification of a new structure is difficult for distantly related proteins and error-prone using simple statistical scores based on sequence or structure similarity. Here we present an accurate numerical method for the identification of evolutionary relationships (homology). The method is based on the principle that natural selection maintains structural and functional continuity within a diverging protein family. The problem of different rates of structural divergence between different families is solved by first using structural similarities to produce a global map of folds in protein space and then further subdividing fold neighborhoods into superfamilies based on functional similarities. In a validation test against a classification by human experts (SCOP), 77% of homologous pairs were identified with 92% reliability. The method is fully automated, allowing fast, self-consistent and complete classification of large numbers of protein structures. In particular, the discrimination between analogy and homology of close structural neighbors will lead to functional predictions while avoiding overprediction.     

Identification of functionally conserved residues with the use of entropy-variability plots

We introduce sequence entropy-variability plots as a method of analyzing families of protein sequences, and demonstrate this for three well-known sequence families: globins, ras-like proteins, and serine-proteases. The location of an aligned residue position in the entropy-variability plot correlates with structural characteristics, and with known facts about the roles of individual amino acids in the function of these proteins. The large numbers of known sequences in these families allowed us to introduce new filtering methods for variability patterns. The results are discussed in terms of a simple evolutionary model for functional proteins.     

Quick selection of representative protein chain sets based on customizable requirements

MOTIVATION: Protein structure classification has been recognized as one of the most important research issues in protein structure analysis. A substantial number of methods for the classification have been proposed, and several databases have been constructed using these methods. Since some proteins with very similar sequences may exhibit structural diversities, we have proposed PDB-REPRDB: a database of representative protein chains from the Protein Data Bank (PDB), which strategy of selection is based not only on sequence similarity but also on structural similarity. Forty-eight representative sets whose similarity criteria were predetermined were made available over the World Wide Web (WWW). However, the sets were insufficient in number to satisfy users researching protein structures by various methods. RESULT: We have improved the system for PDB-REPRDB so that the user may obtain a quick selection of representative chains from PDB. The selection of representative chains can be dynamically configured according to the user's requirement. The WWW interface provides a large degree of freedom in setting parameters, such as cut-off scores of sequence and structural similarity. This paper describes the method we use to classify chains and select the representatives in the system. We also describe the interface used to set the parameters.     

Structure-based functional inference in structural genomics

The dramatically increasing number of new protein sequences arising from genomics 4 proteomics requires the need for methods to rapidly and reliably infer the molecular and cellular functions of these proteins. One such approach, structural genomics, aims to delineate the total repertoire of protein folds in nature, thereby providing three-dimensional folding patterns for all proteins and to infer molecular functions of the proteins based on the combined information of structures and sequences. The goal of obtaining protein structures on a genomic scale has motivated the development of high throughput technologies and protocols for macromolecular structure determination that have begun to produce structures at a greater rate than previously possible. These new structures have revealed many unexpected functional inferences and evolutionary relationships that were hidden at the sequence level. Here, we present samples of structures determined at Berkeley Structural Genomics Center and collaborators laboratories to illustrate how structural information provides and complements sequence information to deduce the functional inferences of proteins with unknown molecular functions.Two of the major premises of structural genomics are to discover a complete repertoire of protein folds in nature and to find molecular functions of the proteins whose functions are not predicted from sequence comparison alone. To achieve these objectives on a genomic scale, new methods, protocols, and technologies need to be developed by multi-institutional collaborations worldwide. As part of this effort, the Protein Structure Initiative has been launched in the United States (PSI; www.nigms.nih.gov/funding/psi.html). Although infrastructure building and technology development are still the main focus of structural genomics programs [1–6], a considerable number of protein structures have already been produced, some of them coming directly out of semi-automated structure determination pipelines [6–10]. The Berkeley Structural Genomics Center (BSGC) has focused on the proteins of Mycoplasma or their homologues from other organisms as its structural genomics targets because of the minimal genome size of the Mycoplasmas as well as their relevance to human and animal pathogenicity (http://www.strgen.org). Here we present several protein examples encompassing a spectrum of functional inferences obtainable from their three-dimensional structures in five situations, where the inferences are new and testable, and are not predictable from protein sequence information alone.     

Structural Alphabets for Protein Structure Classification: A Comparison Study

Finding structural similarities between proteins often helps reveal shared functionality, which otherwise might not be detected by native sequence information alone. Such similarity is usually detected and quantified by protein structure alignment. Determining the optimal alignment between two protein structures, however, remains a hard problem. An alternative approach is to approximate each three-dimensional protein structure using a sequence of motifs derived from a structural alphabet. Using this approach, structure comparison is performed by comparing the corresponding motif sequences or structural sequences. In this article, we measure the performance of such alphabets in the context of the protein structure classification problem. We consider both local and global structural sequences. Each letter of a local structural sequence corresponds to the best matching fragment to the corresponding local segment of the protein structure. The global structural sequence is designed to generate the best possible complete chain that matches the full protein structure. We use an alphabet of 20 letters, corresponding to a library of 20 motifs or protein fragments having four residues. We show that the global structural sequences approximate well the native structures of proteins, with an average coordinate root mean square of 0.69 Å over 2225 test proteins. The approximation is best for all α-proteins, while relatively poorer for all β-proteins. We then test the performance of four different sequence representations of proteins (their native sequence, the sequence of their secondary-structure elements, and the local and global structural sequences based on our fragment library) with different classifiers in their ability to classify proteins that belong to five distinct folds of CATH. Without surprise, the primary sequence alone performs poorly as a structure classifier. We show that addition of either secondary-structure information or local information from the structural sequence considerably improves the classification accuracy. The two fragment-based sequences perform better than the secondary-structure sequence but not well enough at this stage to be a viable alternative to more computationally intensive methods based on protein structure alignment.     

Multiple Profile Models Extract Features from Protein Sequence Data and Resolve Functional Diversity of Very Different Protein Families

Functional classification of proteins from sequences alone has become a critical bottleneck in understanding the myriad of protein sequences that accumulate in our databases. The great diversity of homologous sequences hides, in many cases, a variety of functional activities that cannot be anticipated. Their identification appears critical for a fundamental understanding of the evolution of living organisms and for biotechnological applications. ProfileView is a sequence-based computational method, designed to functionally classify sets of homologous sequences. It relies on two main ideas: the use of multiple profile models whose construction explores evolutionary information in available databases, and a novel definition of a representation space in which to analyze sequences with multiple profile models combined together. ProfileView classifies protein families by enriching known functional groups with new sequences and discovering new groups and subgroups. We validate ProfileView on seven classes of widespread proteins involved in the interaction with nucleic acids, amino acids and small molecules, and in a large variety of functions and enzymatic reactions. ProfileView agrees with the large set of functional data collected for these proteins from the literature regarding the organization into functional subgroups and residues that characterize the functions. In addition, ProfileView resolves undefined functional classifications and extracts the molecular determinants underlying protein functional diversity, showing its potential to select sequences towards accurate experimental design and discovery of novel biological functions. On protein families with complex domain architecture, ProfileView functional classification reconciles domain combinations, unlike phylogenetic reconstruction. ProfileView proves to outperform the functional classification approach PANTHER, the two k-mer-based methods CUPP and eCAMI and a neural network approach based on Restricted Boltzmann Machines. It overcomes time complexity limitations of the latter.     

Mismatch string kernels for discriminative protein classification

MOTIVATION: Classification of proteins sequences into functional and structural families based on sequence homology is a central problem in computational biology. Discriminative supervised machine learning approaches provide good performance, but simplicity and computational efficiency of training and prediction are also important concerns. RESULTS: We introduce a class of string kernels, called mismatch kernels, for use with support vector machines (SVMs) in a discriminative approach to the problem of protein classification and remote homology detection. These kernels measure sequence similarity based on shared occurrences of fixed-length patterns in the data, allowing for mutations between patterns. Thus, the kernels provide a biologically well-motivated way to compare protein sequences without relying on family-based generative models such as hidden Markov models. We compute the kernels efficiently using a mismatch tree data structure, allowing us to calculate the contributions of all patterns occurring in the data in one pass while traversing the tree. When used with an SVM, the kernels enable fast prediction on test sequences. We report experiments on two benchmark SCOP datasets, where we show that the mismatch kernel used with an SVM classifier performs competitively with state-of-the-art methods for homology detection, particularly when very few training examples are available. Examination of the highest-weighted patterns learned by the SVM classifier recovers biologically important motifs in protein families and superfamilies.     

Markovian domain fingerprinting: statistical segmentation of protein sequences.

MOTIVATION: Characterization of a protein family by its distinct sequence domains is crucial for functional annotation and correct classification of newly discovered proteins. Conventional Multiple Sequence Alignment (MSA) based methods find difficulties when faced with heterogeneous groups of proteins. However, even many families of proteins that do share a common domain contain instances of several other domains, without any common underlying linear ordering. Ignoring this modularity may lead to poor or even false classification results. An automated method that can analyze a group of proteins into the sequence domains it contains is therefore highly desirable. RESULTS: We apply a novel method to the problem of protein domain detection. The method takes as input an unaligned group of protein sequences. It segments them and clusters the segments into groups sharing the same underlying statistics. A Variable Memory Markov (VMM) model is built using a Prediction Suffix Tree (PST) data structure for each group of segments. Refinement is achieved by letting the PSTs compete over the segments, and a deterministic annealing framework infers the number of underlying PST models while avoiding many inferior solutions. We show that regions of similar statistics correlate well with protein sequence domains, by matching a unique signature to each domain. This is done in a fully automated manner, and does not require or attempt an MSA. Several representative cases are analyzed. We identify a protein fusion event, refine an HMM superfamily classification into the underlying families the HMM cannot separate, and detect all 12 instances of a short domain in a group of 396 sequences. CONTACT: jill@cs.huji.ac.il; tishby@cs.huji.ac.il.     

Graphical models of residue coupling in protein families

Many statistical measures and algorithmic techniques have been proposed for studying residue coupling in protein families. Generally speaking, two residue positions are considered coupled if, in the sequence record, some of their amino acid type combinations are significantly more common than others. While the proposed approaches have proven useful in finding and describing coupling, a significant missing component is a formal probabilistic model that explicates and compactly represents the coupling, integrates information about sequence,structure, and function, and supports inferential procedures for analysis, diagnosis, and prediction.We present an approach to learning and using probabilistic graphical models of residue coupling. These models capture significant conservation and coupling constraints observable ina multiply-aligned set of sequences. Our approach can place a structural prior on considered couplings, so that all identified relationships have direct mechanistic explanations. It can also incorporate information about functional classes, and thereby learn a differential graphical model that distinguishes constraints common to all classes from those unique to individual classes.Such differential models separately account for class-specific conservation and family-wide coupling, two different sources of sequence covariation. They are then able to perform interpretable functional classification of new sequences, explaining classification decisions in terms of the underlying conservation and coupling constraints. We apply our approach in studies of both G protein-coupled receptors and PDZ domains, identifying and analyzing family-wide and class-specific constraints, and performing functional classification. The results demonstrate that graphical models of residue coupling provide a powerful tool for uncovering, representing, and utilizing significant sequence structure-function relationships in protein families.