CluSTr: a database of clusters of SWISS-PROT+TrEMBL proteins

The CluSTr (Clusters of SWISS-PROT and TrEMBL proteins) database offers an automatic classification of SWISS-PROT and TrEMBL proteins into groups of related proteins. The clustering is based on analysis of all pairwise comparisons between protein sequences. Analysis has been carried out for different levels of protein similarity, yielding a hierarchical organisation of clusters. The database provides links to InterPro, which integrates information on protein families, domains and functional sites from PROSITE, PRINTS, Pfam and ProDom. Links to the InterPro graphical interface allow users to see at a glance whether proteins from the cluster share particular functional sites. CluSTr also provides cross-references to HSSP and PDB. The database is available for querying and browsing at http://www.ebi.ac.uk/clustr.     

A functional hierarchical organization of the protein sequence space

Background

It is a major challenge of computational biology to provide a comprehensive functional classification of all known proteins. Most existing methods seek recurrent patterns in known proteins based on manually-validated alignments of known protein families. Such methods can achieve high sensitivity, but are limited by the necessary manual labor. This makes our current view of the protein world incomplete and biased. This paper concerns ProtoNet, a automatic unsupervised global clustering system that generates a hierarchical tree of over 1,000,000 proteins, based solely on sequence similarity.

Results

In this paper we show that ProtoNet correctly captures functional and structural aspects of the protein world. Furthermore, a novel feature is an automatic procedure that reduces the tree to 12% its original size. This procedure utilizes only parameters intrinsic to the clustering process. Despite the substantial reduction in size, the system's predictive power concerning biological functions is hardly affected. We then carry out an automatic comparison with existing functional protein annotations. Consequently, 78% of the clusters in the compressed tree (5,300 clusters) get assigned a biological function with a high confidence. The clustering and compression processes are unsupervised, and robust.

Conclusions

We present an automatically generated unbiased method that provides a hierarchical classification of all currently known proteins.

     

Predicting fold novelty based on ProtoNet hierarchical classification

MOTIVATION: Structural genomics projects aim to solve a large number of protein structures with the ultimate objective of representing the entire protein space. The computational challenge is to identify and prioritize a small set of proteins with new, currently unknown, superfamilies or folds. RESULTS: We develop a method that assigns each protein a likelihood of it belonging to a new, yet undetermined, structural superfamily. The method relies on a variant of ProtoNet, an automatic hierarchical classification scheme of all protein sequences from SwissProt. Our results show that proteins that are remote from solved structures in the ProtoNet hierarchy are more likely to belong to new superfamilies. The results are validated against SCOP releases from recent years that account for about half of the solved structures known to date. We show that our new method and the representation of ProtoNet are superior in detecting new targets, compared to our previous method using ProtoMap classification. Furthermore, our method outperforms PSI-BLAST search in detecting potential new superfamilies.     

Graph-based clustering for finding distant relationships in a large set of protein sequences

MOTIVATION: Clustering of protein sequences is widely used for the functional characterization of proteins. However, it is still not easy to cluster distantly-related proteins, which have only regional similarity among their sequences. It is therefore necessary to develop an algorithm for clustering such distantly-related proteins. RESULTS: We have developed a time and space efficient clustering algorithm. It uses a graph representation where its vertices and edges denote proteins and their sequence similarities above a certain cutoff score, respectively. It repeatedly partitions the graph by removing edges that have small weights, which correspond to low sequence similarities. To find the appropriate partitions, we introduce a score combining the normalized cut and a locally minimal cut capacities. Our method is applied to the entire 40,703 human proteins in SWISS-PROT and TrEMBL. The resulting clusters shows a 76% recall (20,529 proteins) of the 26,917 classified by InterPro. It also finds relationships not found by other clustering methods. AVAILABILITY: The complete result of our algorithm for all the human proteins in SWISS-PROT and TrEMBL, and other supplementary information are available at http://motif.ics.es.osaka-u.ac.jp/Ncut-KL/     

Functional annotation prediction: all for one and one for all

In an era of rapid genome sequencing and high-throughput technology, automatic function prediction for a novel sequence is of utter importance in bioinformatics. While automatic annotation methods based on local alignment searches can be simple and straightforward, they suffer from several drawbacks, including relatively low sensitivity and assignment of incorrect annotations that are not associated with the region of similarity. ProtoNet is a hierarchical organization of the protein sequences in the UniProt database. Although the hierarchy is constructed in an unsupervised automatic manner, it has been shown to be coherent with several biological data sources. We extend the ProtoNet system in order to assign functional annotations automatically. By leveraging on the scaffold of the hierarchical classification, the method is able to overcome some frequent annotation pitfalls.     

The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003

The SWISS-PROT protein knowledgebase (http://www.expasy.org/sprot/ and http://www.ebi.ac.uk/swissprot/) connects amino acid sequences with the current knowledge in the Life Sciences. Each protein entry provides an interdisciplinary overview of relevant information by bringing together experimental results, computed features and sometimes even contradictory conclusions. Detailed expertise that goes beyond the scope of SWISS-PROT is made available via direct links to specialised databases. SWISS-PROT provides annotated entries for all species, but concentrates on the annotation of entries from human (the HPI project) and other model organisms to ensure the presence of high quality annotation for representative members of all protein families. Part of the annotation can be transferred to other family members, as is already done for microbes by the High-quality Automated and Manual Annotation of microbial Proteomes (HAMAP) project. Protein families and groups of proteins are regularly reviewed to keep up with current scientific findings. Complementarily, TrEMBL strives to comprise all protein sequences that are not yet represented in SWISS-PROT, by incorporating a perpetually increasing level of mostly automated annotation. Researchers are welcome to contribute their knowledge to the scientific community by submitting relevant findings to SWISS-PROT at swiss-prot@expasy.org.     

A dynamically growing self-organizing tree (DGSOT) for hierarchical clustering gene expression profiles

MOTIVATION: The increasing use of microarray technologies is generating large amounts of data that must be processed in order to extract useful and rational fundamental patterns of gene expression. Hierarchical clustering technology is one method used to analyze gene expression data, but traditional hierarchical clustering algorithms suffer from several drawbacks (e.g. fixed topology structure; mis-clustered data which cannot be reevaluated). In this paper, we introduce a new hierarchical clustering algorithm that overcomes some of these drawbacks. RESULT: We propose a new tree-structure self-organizing neural network, called dynamically growing self-organizing tree (DGSOT) algorithm for hierarchical clustering. The DGSOT constructs a hierarchy from top to bottom by division. At each hierarchical level, the DGSOT optimizes the number of clusters, from which the proper hierarchical structure of the underlying dataset can be found. In addition, we propose a new cluster validation criterion based on the geometric property of the Voronoi partition of the dataset in order to find the proper number of clusters at each hierarchical level. This criterion uses the Minimum Spanning Tree (MST) concept of graph theory and is computationally inexpensive for large datasets. A K-level up distribution (KLD) mechanism, which increases the scope of data distribution in the hierarchy construction, was used to improve the clustering accuracy. The KLD mechanism allows the data misclustered in the early stages to be reevaluated at a later stage and increases the accuracy of the final clustering result. The clustering result of the DGSOT is easily displayed as a dendrogram for visualization. Based on a yeast cell cycle microarray expression dataset, we found that our algorithm extracts gene expression patterns at different levels. Furthermore, the biological functionality enrichment in the clusters is considerably high and the hierarchical structure of the clusters is more reasonable. AVAILABILITY: DGSOT is available upon request from the authors.     

The metric space of proteins-comparative study of clustering algorithms

MOTIVATION: A large fraction of biological research concentrates on individual proteins and on small families of proteins. One of the current major challenges in bioinformatics is to extend our knowledge to very large sets of proteins. Several major projects have tackled this problem. Such undertakings usually start with a process that clusters all known proteins or large subsets of this space. Some work in this area is carried out automatically, while other attempts incorporate expert advice and annotation. RESULTS: We propose a novel technique that automatically clusters protein sequences. We consider all proteins in SWISSPROT, and carry out an all-against-all BLAST similarity test among them. With this similarity measure in hand we proceed to perform a continuous bottom-up clustering process by applying alternative rules for merging clusters. The outcome of this clustering process is a classification of the input proteins into a hierarchy of clusters of varying degrees of granularity. Here we compare the clusters that result from alternative merging rules, and validate the results against InterPro. Our preliminary results show that clusters that are consistent with several rather than a single merging rule tend to comply with InterPro annotation. This is an affirmation of the view that the protein space consists of families that differ markedly in their evolutionary conservation.     

Using repeated measurements to validate hierarchical gene clusters

MOTIVATION: Hierarchical clustering is a common approach to study protein and gene expression data. This unsupervised technique is used to find clusters of genes or proteins which are expressed in a coordinated manner across a set of conditions. Because of both the biological and technical variability, experimental repetitions are generally performed. In this work, we propose an approach to evaluate the stability of clusters derived from hierarchical clustering by taking repeated measurements into account. RESULTS: The method is based on the bootstrap technique that is used to obtain pseudo-hierarchies of genes from resampled datasets. Based on a fast dynamic programming algorithm, we compare the original hierarchy to the pseudo-hierarchies and assess the stability of the original gene clusters. Then a shuffling procedure can be used to assess the significance of the cluster stabilities. Our approach is illustrated on simulated data and on two microarray datasets. Compared to the standard hierarchical clustering methodology, it allows to point out the dubious and stable clusters, and thus avoids misleading interpretations. AVAILABILITY: The programs were developed in C and R languages.     

Comparison of topological clustering within protein networks using edge metrics that evaluate full sequence,full structure,and active site microenvironment similarity

The development of accurate protein function annotation methods has emerged as a major unsolved biological problem. Protein similarity networks, one approach to function annotation via annotation transfer, group proteins into similarity-based clusters. An underlying assumption is that the edge metric used to identify such clusters correlates with functional information. In this contribution, this assumption is evaluated by observing topologies in similarity networks using three different edge metrics: sequence (BLAST), structure (TM-Align), and active site similarity (active site profiling, implemented in DASP). Network topologies for four well-studied protein superfamilies (enolase, peroxiredoxin (Prx), glutathione transferase (GST), and crotonase) were compared with curated functional hierarchies and structure. As expected, network topology differs, depending on edge metric; comparison of topologies provides valuable information on structure/function relationships. Subnetworks based on active site similarity correlate with known functional hierarchies at a single edge threshold more often than sequence- or structure-based networks. Sequence- and structure-based networks are useful for identifying sequence and domain similarities and differences; therefore, it is important to consider the clustering goal before deciding appropriate edge metric. Further, conserved active site residues identified in enolase and GST active site subnetworks correspond with published functionally important residues. Extension of this analysis yields predictions of functionally determinant residues for GST subgroups. These results support the hypothesis that active site similarity-based networks reveal clusters that share functional details and lay the foundation for capturing functionally relevant hierarchies using an approach that is both automatable and can deliver greater precision in function annotation than current similarity-based methods.     

Proteome-wide functional classification and identification of prokaryotic transmembrane proteins by transmembrane topology similarity comparison

We propose a new method for classifying and identifying transmembrane (TM) protein functions in proteome-scale by applying a single-linkage clustering method based on TM topology similarity, which is calculated simply from comparing the lengths of loop regions. In this study, we focused on 87 prokaryotic TM proteomes consisting of 31 proteobacteria, 22 gram-positive bacteria, 19 other bacteria, and 15 archaea. Prior to performing the clustering, we first categorized individual TM protein sequences as "known," "putative" (similar to "known" sequences), or "unknown" by using the homology search and the sequence similarity comparison against SWISS-PROT to assess the current status of the functional annotation of the TM proteomes based on sequence similarity only. More than three-quarters, that is, 75.7% of the TM protein sequences are functionally "unknown," with only 3.8% and 20.5% of them being classified as "known" and "putative," respectively. Using our clustering approach based on TM topology similarity, we succeeded in increasing the rate of TM protein sequences functionally classified and identified from 24.3% to 60.9%. Obtained clusters correspond well to functional superfamilies or families, and the functional classification and identification are successfully achieved by this approach. For example, in an obtained cluster of TM proteins with six TM segments, 109 sequences out of 119 sequences annotated as "ATP-binding cassette transporter" are properly included and 122 "unknown" sequences are also contained.     

Breaking the hierarchy - a new cluster selection mechanism for hierarchical clustering methods

Background  

Hierarchical clustering methods like Ward's method have been used since decades to understand biological and chemical data sets. In order to get a partition of the data set, it is necessary to choose an optimal level of the hierarchy by a so-called level selection algorithm. In 2005, a new kind of hierarchical clustering method was introduced by Palla et al. that differs in two ways from Ward's method: it can be used on data on which no full similarity matrix is defined and it can produce overlapping clusters, i.e., allow for multiple membership of items in clusters. These features are optimal for biological and chemical data sets but until now no level selection algorithm has been published for this method.     

Improvements to CluSTr: the database of SWISS-PROT+TrEMBL protein clusters

The CluSTr database (http://www.ebi.ac.uk/clustr/) offers an automatic classification of SWISS-PROT+TrEMBL proteins into groups of related proteins. The clustering is based on analysis of all pair-wise sequence comparisons between proteins using the Smith-Waterman algorithm. The analysis, carried out on different levels of protein similarity, yields a hierarchical organization of clusters. Information about domain content of the clustered proteins is provided via the InterPro resource. The introduced InterPro 'condensed graphical view' simplifies the visual analysis of represented domain architectures. Integrated applications allow users to visualize and edit multiple alignments and build sequence divergence trees. Links to the relevant structural data in Protein Data Bank (PDB) and Homology derived Secondary Structure of Proteins (HSSP) are also provided.     

The SYSTERS protein sequence cluster set

The SYSTERS (short for SYSTEmatic Re-Searching) protein sequence cluster set consists of the classification of all sequences from SWISS-PROT and PIR into disjoint protein family clusters and hierarchically into superfamily and subfamily clusters. The cluster set can be searched with a sequence using the SSMAL search tool or a traditional database search tool like BLAST or FASTA. Additionally a multiple alignment is generated for each cluster and annotated with domain information from the Pfam database of protein domain families. A taxonomic overview of the organisms covered by a cluster is given based on the NCBI taxonomy. The cluster set is available for querying and browsing at http://www.dkfz-heidelberg. de/tbi/services/cluster/systersform     

Hydrophobic interaction network analysis for thermostabilization of a mesophilic xylanase

One widely known drawback of enzymes is their instability in diverse conditions. The thermostability of enzymes is particularly relevant for industrial applications because operation at high temperatures has the advantage of a faster reaction rate. Protein stability is mainly determined in this study by intra-molecular hydrophobic interactions that have a collective and 3-dimensional clustering effect. To interpret the thermostability of enzymes, network analysis was introduced into the protein structure, and a network parameter of structural hierarchy, k of k-clique, was used to discern more developed hydrophobic interaction clusters in the protein structure. The favorable clustering conformations of hydrophobic residues, which seemed to be important for protein thermostability, were discovered by the application of a network analysis to hydrophobic interactions of GH11 xylanases. Coordinating higher k-clique hydrophobic interaction clusters through the site-directed mutagenesis of the model enzyme, Bacillus circulans xylanase, stabilized the local structure and thus improved thermostability, such that the enzyme half-life and melting temperature increased by 78 fold and 8.8 °C, respectively. This study highlights the advantages of interpreting collective hydrophobic interaction patterns and their structural hierarchy and the possibility of applying network analysis to the thermostabilization of enzymes.     

ProtoMap: automatic classification of protein sequences and hierarchy of protein families

The ProtoMap site offers an exhaustive classification of all proteins in the SWISS-PROT database, into groups of related proteins. The classification is based on analysis of all pairwise similarities among protein sequences. The analysis makes essential use of transitivity to identify homologies among proteins. Within each group of the classification, every two members are either directly or transitively related. However, transitivity is applied restrictively in order to prevent unrelated proteins from clustering together. The classification is done at different levels of confidence, and yields a hierarchical organization of all proteins. The resulting classification splits the protein space into well-defined groups of proteins, which are closely correlated with natural biological families and superfamilies. Many clusters contain protein sequences that are not classified by other databases. The hierarchical organization suggested by our analysis may help in detecting finer subfamilies in families of known proteins. In addition it brings forth interesting relationships between protein families, upon which local maps for the neighborhood of protein families can be sketched. The ProtoMap web server can be accessed at http://www.protomap.cs.huji.ac.il     

Global considerations in hierarchical clustering reveal meaningful patterns in data

Background

A hierarchy, characterized by tree-like relationships, is a natural method of organizing data in various domains. When considering an unsupervised machine learning routine, such as clustering, a bottom-up hierarchical (BU, agglomerative) algorithm is used as a default and is often the only method applied.

Methodology/Principal Findings

We show that hierarchical clustering that involve global considerations, such as top-down (TD, divisive), or glocal (global-local) algorithms are better suited to reveal meaningful patterns in the data. This is demonstrated, by testing the correspondence between the results of several algorithms (TD, glocal and BU) and the correct annotations provided by experts. The correspondence was tested in multiple domains including gene expression experiments, stock trade records and functional protein families. The performance of each of the algorithms is evaluated by statistical criteria that are assigned to clusters (nodes of the hierarchy tree) based on expert-labeled data. Whereas TD algorithms perform better on global patterns, BU algorithms perform well and are advantageous when finer granularity of the data is sought. In addition, a novel TD algorithm that is based on genuine density of the data points is presented and is shown to outperform other divisive and agglomerative methods. Application of the algorithm to more than 500 protein sequences belonging to ion-channels illustrates the potential of the method for inferring overlooked functional annotations. ClustTree, a graphical Matlab toolbox for applying various hierarchical clustering algorithms and testing their quality is made available.

Conclusions

Although currently rarely used, global approaches, in particular, TD or glocal algorithms, should be considered in the exploratory process of clustering. In general, applying unsupervised clustering methods can leverage the quality of manually-created mapping of proteins families. As demonstrated, it can also provide insights in erroneous and missed annotations.     

Progressive Clustering Based Method for Protein Function Prediction

In recent years, significant effort has been given to predicting protein functions from protein interaction data generated from high throughput techniques. However, predicting protein functions correctly and reliably still remains a challenge. Recently, many computational methods have been proposed for predicting protein functions. Among these methods, clustering based methods are the most promising. The existing methods, however, mainly focus on protein relationship modeling and the prediction algorithms that statically predict functions from the clusters that are related to the unannotated proteins. In fact, the clustering itself is a dynamic process and the function prediction should take this dynamic feature of clustering into consideration. Unfortunately, this dynamic feature of clustering is ignored in the existing prediction methods. In this paper, we propose an innovative progressive clustering based prediction method to trace the functions of relevant annotated proteins across all clusters that are generated through the progressive clustering of proteins. A set of prediction criteria is proposed to predict functions of unannotated proteins from all relevant clusters and traced functions. The method was evaluated on real protein interaction datasets and the results demonstrated the effectiveness of the proposed method compared with representative existing methods.