Automated annotation of protein function is challenging. As the number of sequenced genomes rapidly grows, the overwhelming majority of protein products can only be annotated computationally. If computational predictions are to be relied upon, it is crucial that the accuracy of these methods be high. Here we report the results from the first large-scale community-based Critical Assessment of protein Function Annotation (CAFA) experiment. Fifty-four methods representing the state-of-the-art for protein function prediction were evaluated on a target set of 866 proteins from eleven organisms. Two findings stand out: (i) today’s best protein function prediction algorithms significantly outperformed widely-used first-generation methods, with large gains on all types of targets; and (ii) although the top methods perform well enough to guide experiments, there is significant need for improvement of currently available tools.
Motivation: The number of missense mutations being identified in cancer genomes has greatly increased as a consequence of technological advances and the reduced cost of whole-genome/whole-exome sequencing methods. However, a high proportion of the amino acid substitutions detected in cancer genomes have little or no effect on tumour progression (passenger mutations). Therefore, accurate automated methods capable of discriminating between driver (cancer-promoting) and passenger mutations are becoming increasingly important. In our previous work, we developed the Functional Analysis through Hidden Markov Models (FATHMM) software and, using a model weighted for inherited disease mutations, observed improved performances over alternative computational prediction algorithms. Here, we describe an adaptation of our original algorithm that incorporates a cancer-specific model to potentiate the functional analysis of driver mutations.
Results: The performance of our algorithm was evaluated using two separate benchmarks. In our analysis, we observed improved performances when distinguishing between driver mutations and other germ line variants (both disease-causing and putatively neutral mutations). In addition, when discriminating between somatic driver and passenger mutations, we observed performances comparable with the leading computational prediction algorithms: SPF-Cancer and TransFIC.
Availability and implementation: A web-based implementation of our cancer-specific model, including a downloadable stand-alone package, is available at http://fathmm.biocompute.org.uk.
Supplementary data are available at Bioinformatics online.
Computational/manual annotations of protein functions are one of the first routes to making sense of a newly sequenced genome. Protein domain predictions form an essential part of this annotation process. This is due to the natural modularity of proteins with domains as structural, evolutionary and functional units. Sometimes two, three, or more adjacent domains (called supra-domains) are the operational unit responsible for a function, e.g. via a binding site at the interface. These supra-domains have contributed to functional diversification in higher organisms. Traditionally functional ontologies have been applied to individual proteins, rather than families of related domains and supra-domains. We expect, however, to some extent functional signals can be carried by protein domains and supra-domains, and consequently used in function prediction and functional genomics.
Here we present a domain-centric Gene Ontology (dcGO) perspective. We generalize a framework for automatically inferring ontological terms associated with domains and supra-domains from full-length sequence annotations. This general framework has been applied specifically to primary protein-level annotations from UniProtKB-GOA, generating GO term associations with SCOP domains and supra-domains. The resulting 'dcGO Predictor', can be used to provide functional annotation to protein sequences. The functional annotation of sequences in the Critical Assessment of Function Annotation (CAFA) has been used as a valuable opportunity to validate our method and to be assessed by the community. The functional annotation of all completely sequenced genomes has demonstrated the potential for domain-centric GO enrichment analysis to yield functional insights into newly sequenced or yet-to-be-annotated genomes. This generalized framework we have presented has also been applied to other domain classifications such as InterPro and Pfam, and other ontologies such as mammalian phenotype and disease ontology. The dcGO and its predictor are available at http://supfam.org/SUPERFAMILY/dcGO including an enrichment analysis tool.
As functional units, domains offer a unique perspective on function prediction regardless of whether proteins are multi-domain or single-domain. The 'dcGO Predictor' holds great promise for contributing to a domain-centric functional understanding of genomes in the next generation sequencing era.
Genome3D, available at http://www.genome3d.eu, is a new collaborative project that integrates UK-based structural resources to provide a unique perspective on sequence–structure–function relationships. Leading structure prediction resources (DomSerf, FUGUE, Gene3D, pDomTHREADER, Phyre and SUPERFAMILY) provide annotations for UniProt sequences to indicate the locations of structural domains (structural annotations) and their 3D structures (structural models). Structural annotations and 3D model predictions are currently available for three model genomes (Homo sapiens, E. coli and baker’s yeast), and the project will extend to other genomes in the near future. As these resources exploit different strategies for predicting structures, the main aim of Genome3D is to enable comparisons between all the resources so that biologists can see where predictions agree and are therefore more trusted. Furthermore, as these methods differ in whether they build their predictions using CATH or SCOP, Genome3D also contains the first official mapping between these two databases. This has identified pairs of similar superfamilies from the two resources at various degrees of consensus (532 bronze pairs, 527 silver pairs and 370 gold pairs).
We present the Database of Disordered Protein Prediction (D2P2), available at http://d2p2.pro (including website source code). A battery of disorder predictors and their variants, VL-XT, VSL2b, PrDOS, PV2, Espritz and IUPred, were run on all protein sequences from 1765 complete proteomes (to be updated as more genomes are completed). Integrated with these results are all of the predicted (mostly structured) SCOP domains using the SUPERFAMILY predictor. These disorder/structure annotations together enable comparison of the disorder predictors with each other and examination of the overlap between disordered predictions and SCOP domains on a large scale. D2P2 will increase our understanding of the interplay between disorder and structure, the genomic distribution of disorder, and its evolutionary history. The parsed data are made available in a unified format for download as flat files or SQL tables either by genome, by predictor, or for the complete set. An interactive website provides a graphical view of each protein annotated with the SCOP domains and disordered regions from all predictors overlaid (or shown as a consensus). There are statistics and tools for browsing and comparing genomes and their disorder within the context of their position on the tree of life.
We present ‘dcGO’ (http://supfam.org/SUPERFAMILY/dcGO), a comprehensive ontology database for protein domains. Domains are often the functional units of proteins, thus instead of associating ontological terms only with full-length proteins, it sometimes makes more sense to associate terms with individual domains. Domain-centric GO, ‘dcGO’, provides associations between ontological terms and protein domains at the superfamily and family levels. Some functional units consist of more than one domain acting together or acting at an interface between domains; therefore, ontological terms associated with pairs of domains, triplets and longer supra-domains are also provided. At the time of writing the ontologies in dcGO include the Gene Ontology (GO); Enzyme Commission (EC) numbers; pathways from UniPathway; human phenotype ontology and phenotype ontologies from five model organisms, including plants; anatomy ontologies from three organisms; human disease ontology and drugs from DrugBank. All ontological terms have probabilistic scores for their associations. In addition to associations to domains and supra-domains, the ontological terms have been transferred to proteins, through homology, providing annotations of >80 million sequences covering 2414 complete genomes, hundreds of meta-genomes, thousands of viruses and so forth. The dcGO database is updated fortnightly, and its website provides downloads, search, browse, phylogenetic context and other data-mining facilities.
SCOP is a hierarchical domain classification system for proteins of known structure. The superfamily level has a clear definition: Protein domains belong to the same superfamily if there is structural, functional and sequence evidence for a common evolutionary ancestor. Superfamilies are sub-classified into families, however, there is not such a clear basis for the family level groupings. Do SCOP families group together domains with sequence similarity, do they group domains with similar structure or by common function? It is these questions we answer, but most importantly, whether each family represents a distinct phylogenetic group within a superfamily.
Several phylogenetic trees were generated for each superfamily: one derived from a multiple sequence alignment, one based on structural distances, and the final two from presence/absence of GO terms or EC numbers assigned to domains. The topologies of the resulting trees and confidence values were compared to the SCOP family classification.
We show that SCOP family groupings are evolutionarily consistent to a very high degree with respect to classical sequence phylogenetics. The trees built from (automatically generated) structural distances correlate well, but are not always consistent with SCOP (hand annotated) groupings. Trees derived from functional data are less consistent with the family level than those from structure or sequence, though the majority still agree. Much of GO and EC annotation applies directly to one family or subset of the family; relatively few terms apply at the superfamily level. Maximum sequence diversity within a family is on average 22% but close to zero for superfamilies.
InterPro (http://www.ebi.ac.uk/interpro/) is a database that integrates diverse information about protein families, domains and functional sites, and makes it freely available to the public via Web-based interfaces and services. Central to the database are diagnostic models, known as signatures, against which protein sequences can be searched to determine their potential function. InterPro has utility in the large-scale analysis of whole genomes and meta-genomes, as well as in characterizing individual protein sequences. Herein we give an overview of new developments in the database and its associated software since 2009, including updates to database content, curation processes and Web and programmatic interfaces.
The SUPERFAMILY resource provides protein domain assignments at the structural classification of protein (SCOP) superfamily level for over 1400 completely sequenced genomes, over 120 metagenomes and other gene collections such as UniProt. All models and assignments are available to browse and download at http://supfam.org. A new hidden Markov model library based on SCOP 1.75 has been created and a previously ignored class of SCOP, coiled coils, is now included. Our scoring component now uses HMMER3, which is in orders of magnitude faster and produces superior results. A cloud-based pipeline was implemented and is publicly available at Amazon web services elastic computer cloud. The SUPERFAMILY reference tree of life has been improved allowing the user to highlight a chosen superfamily, family or domain architecture on the tree of life. The most significant advance in SUPERFAMILY is that now it contains a domain-based gene ontology (GO) at the superfamily and family levels. A new methodology was developed to ensure a high quality GO annotation. The new methodology is general purpose and has been used to produce domain-based phenotypic ontologies in addition to GO.
Motivation: Some first order methods for protein sequence analysis inherently treat each position as independent. We develop a general framework for introducing longer range interactions. We then demonstrate the power of our approach by applying it to secondary structure prediction; under the independence assumption, sequences produced by existing methods can produce features that are not protein like, an extreme example being a helix of length 1. Our goal was to make the predictions from state of the art methods more realistic, without loss of performance by other measures.
Results: Our framework for longer range interactions is described as a k-mer order model. We succeeded in applying our model to the specific problem of secondary structure prediction, to be used as an additional layer on top of existing methods. We achieved our goal of making the predictions more realistic and protein like, and remarkably this also improved the overall performance. We improve the Segment OVerlap (SOV) score by 1.8%, but more importantly we radically improve the probability of the real sequence given a prediction from an average of 0.271 per residue to 0.385. Crucially, this improvement is obtained using no additional information.
Phylogenetic trees are complex data forms that need to be graphically displayed to be human-readable. Traditional techniques of plotting phylogenetic trees focus on rendering a single static image, but increases in the production of biological data and large-scale analyses demand scalable, browsable, and interactive trees.
We introduce TreeVector, a Scalable Vector Graphics–and Java-based method that allows trees to be integrated and viewed seamlessly in standard web browsers with no extra software required, and can be modified and linked using standard web technologies. There are now many bioinformatics servers and databases with a range of dynamic processes and updates to cope with the increasing volume of data. TreeVector is designed as a framework to integrate with these processes and produce user-customized phylogenies automatically. We also address the strengths of phylogenetic trees as part of a linked-in browsing process rather than an end graphic for print.
TreeVector is fast and easy to use and is available to download precompiled, but is also open source. It can also be run from the web server listed below or the user's own web server. It has already been deployed on two recognized and widely used database Web sites.
SUPERFAMILY provides structural, functional and evolutionary information for proteins from all completely sequenced genomes, and large sequence collections such as UniProt. Protein domain assignments for over 900 genomes are included in the database, which can be accessed at http://supfam.org/. Hidden Markov models based on Structural Classification of Proteins (SCOP) domain definitions at the superfamily level are used to provide structural annotation. We recently produced a new model library based on SCOP 1.73. Family level assignments are also available. From the web site users can submit sequences for SCOP domain classification; search for keywords such as superfamilies, families, organism names, models and sequence identifiers; find over- and underrepresented families or superfamilies within a genome relative to other genomes or groups of genomes; compare domain architectures across selections of genomes and finally build multiple sequence alignments between Protein Data Bank (PDB), genomic and custom sequences. Recent extensions to the database include InterPro abstracts and Gene Ontology terms for superfamiles, taxonomic visualization of the distribution of families across the tree of life, searches for functionally similar domain architectures and phylogenetic trees. The database, models and associated scripts are available for download from the ftp site.
The InterPro database (http://www.ebi.ac.uk/interpro/) integrates together predictive models or ‘signatures’ representing protein domains, families and functional sites from multiple, diverse source databases: Gene3D, PANTHER, Pfam, PIRSF, PRINTS, ProDom, PROSITE, SMART, SUPERFAMILY and TIGRFAMs. Integration is performed manually and approximately half of the total ∼58 000 signatures available in the source databases belong to an InterPro entry. Recently, we have started to also display the remaining un-integrated signatures via our web interface. Other developments include the provision of non-signature data, such as structural data, in new XML files on our FTP site, as well as the inclusion of matchless UniProtKB proteins in the existing match XML files. The web interface has been extended and now links out to the ADAN predicted protein–protein interaction database and the SPICE and Dasty viewers. The latest public release (v18.0) covers 79.8% of UniProtKB (v14.1) and consists of 16 549 entries. InterPro data may be accessed either via the web address above, via web services, by downloading files by anonymous FTP or by using the InterProScan search software (http://www.ebi.ac.uk/Tools/InterProScan/).
InterPro is an integrated resource for protein families, domains and functional sites, which integrates the following protein signature databases: PROSITE, PRINTS, ProDom, Pfam, SMART, TIGRFAMs, PIRSF, SUPERFAMILY, Gene3D and PANTHER. The latter two new member databases have been integrated since the last publication in this journal. There have been several new developments in InterPro, including an additional reading field, new database links, extensions to the web interface and additional match XML files. InterPro has always provided matches to UniProtKB proteins on the website and in the match XML file on the FTP site. Additional matches to proteins in UniParc (UniProt archive) are now available for download in the new match XML files only. The latest InterPro release (13.0) contains more than 13 000 entries, covering over 78% of all proteins in UniProtKB. The database is available for text- and sequence-based searches via a webserver (), and for download by anonymous FTP (). The InterProScan search tool is now also available via a web service at .
The SUPERFAMILY database provides protein domain assignments, at the SCOP ‘superfamily’ level, for the predicted protein sequences in over 400 completed genomes. A superfamily groups together domains of different families which have a common evolutionary ancestor based on structural, functional and sequence data. SUPERFAMILY domain assignments are generated using an expert curated set of profile hidden Markov models. All models and structural assignments are available for browsing and download from . The web interface includes services such as domain architectures and alignment details for all protein assignments, searchable domain combinations, domain occurrence network visualization, detection of over- or under-represented superfamilies for a given genome by comparison with other genomes, assignment of manually submitted sequences and keyword searches. In this update we describe the SUPERFAMILY database and outline two major developments: (i) incorporation of family level assignments and (ii) a superfamily-level functional annotation. The SUPERFAMILY database can be used for general protein evolution and superfamily-specific studies, genomic annotation, and structural genomics target suggestion and assessment.
Many classification schemes for proteins and domains are either hierarchical or semi-hierarchical yet most databases, especially those offering genome-wide analysis, only provide assignments to sequences at one level of their hierarchy. Given an established hierarchy, the problem of assigning new sequences to lower levels of that existing hierarchy is less hard (but no less important) than the initial top level assignment which requires the detection of the most distant relationships. A solution to this problem is described here in the form of a new procedure which can be thought of as a hybrid between pairwise and profile methods. The hybrid method is a general procedure that can be applied to any pre-defined hierarchy, at any level, including in principle multiple sub-levels. It has been tested on the SCOP classification via the SUPERFAMILY database and performs significantly better than either pairwise or profile methods alone. Perhaps the greatest advantage of the hybrid method over other possible approaches to the problem is that within the framework of an existing profile library, the assignments are fully automatic and come at almost no additional computational cost. Hence it has already been applied at the SCOP family level to all genomes in the SUPERFAMILY database, providing a wealth of new data to the biological and bioinformatics communities.
The international FANTOM consortium aims to produce a comprehensive picture of the mammalian transcriptome, based upon an extensive cDNA collection and functional annotation of full-length enriched cDNAs. The previous dataset, FANTOM2, comprised 60,770 full-length enriched cDNAs. Functional annotation revealed that this cDNA dataset contained only about half of the estimated number of mouse protein-coding genes, indicating that a number of cDNAs still remained to be collected and identified. To pursue the complete gene catalog that covers all predicted mouse genes, cloning and sequencing of full-length enriched cDNAs has been continued since FANTOM2. In FANTOM3, 42,031 newly isolated cDNAs were subjected to functional annotation, and the annotation of 4,347 FANTOM2 cDNAs was updated. To accomplish accurate functional annotation, we improved our automated annotation pipeline by introducing new coding sequence prediction programs and developed a Web-based annotation interface for simplifying the annotation procedures to reduce manual annotation errors. Automated coding sequence and function prediction was followed with manual curation and review by expert curators. A total of 102,801 full-length enriched mouse cDNAs were annotated. Out of 102,801 transcripts, 56,722 were functionally annotated as protein coding (including partial or truncated transcripts), providing to our knowledge the greatest current coverage of the mouse proteome by full-length cDNAs. The total number of distinct non-protein-coding transcripts increased to 34,030. The FANTOM3 annotation system, consisting of automated computational prediction, manual curation, and final expert curation, facilitated the comprehensive characterization of the mouse transcriptome, and could be applied to the transcriptomes of other species.
Globins occur in all three kingdoms of life: they can be classified into single-domain globins and chimeric globins. The latter comprise the flavohemoglobins with a C-terminal FAD-binding domain and the gene-regulating globin coupled sensors, with variable C-terminal domains. The single-domain globins encompass sequences related to chimeric globins and «truncated» hemoglobins with a 2-over-2 instead of the canonical 3-over-3 α-helical fold.
A census of globins in 26 archaeal, 245 bacterial and 49 eukaryote genomes was carried out. Only ~25% of archaea have globins, including globin coupled sensors, related single domain globins and 2-over-2 globins. From one to seven globins per genome were found in ~65% of the bacterial genomes: the presence and number of globins are positively correlated with genome size. Globins appear to be mostly absent in Bacteroidetes/Chlorobi, Chlamydia, Lactobacillales, Mollicutes, Rickettsiales, Pastorellales and Spirochaetes. Single domain globins occur in metazoans and flavohemoglobins are found in fungi, diplomonads and mycetozoans. Although red algae have single domain globins, including 2-over-2 globins, the green algae and ciliates have only 2-over-2 globins. Plants have symbiotic and nonsymbiotic single domain hemoglobins and 2-over-2 hemoglobins. Over 90% of eukaryotes have globins: the nematode Caenorhabditis has the most putative globins, ~33. No globins occur in the parasitic, unicellular eukaryotes such as Encephalitozoon, Entamoeba, Plasmodium and Trypanosoma.
Although Bacteria have all three types of globins, Archaeado not have flavohemoglobins and Eukaryotes lack globin coupled sensors. Since the hemoglobins in organisms other than animals are enzymes or sensors, it is likely that the evolution of an oxygen transport function accompanied the emergence of multicellular animals.
RIKEN's FANTOM project has revealed many previously unknown coding sequences, as well as an unexpected degree of variation in transcripts resulting from alternative promoter usage and splicing. Ever more transcripts that do not code for proteins have been identified by transcriptome studies, in general. Increasing evidence points to the important cellular roles of such non-coding RNAs (ncRNAs). The distinction of protein-coding RNA transcripts from ncRNA transcripts is therefore an important problem in understanding the transcriptome and carrying out its annotation. Very few in silico methods have specifically addressed this problem. Here, we introduce CONC (for “coding or non-coding”), a novel method based on support vector machines that classifies transcripts according to features they would have if they were coding for proteins. These features include peptide length, amino acid composition, predicted secondary structure content, predicted percentage of exposed residues, compositional entropy, number of homologs from database searches, and alignment entropy. Nucleotide frequencies are also incorporated into the method. Confirmed coding cDNAs for eukaryotic proteins from the Swiss-Prot database constituted the set of true positives, ncRNAs from RNAdb and NONCODE the true negatives. Ten-fold cross-validation suggested that CONC distinguished coding RNAs from ncRNAs at about 97% specificity and 98% sensitivity. Applied to 102,801 mouse cDNAs from the FANTOM3 dataset, our method reliably identified over 14,000 ncRNAs and estimated the total number of ncRNAs to be about 28,000.
There are two types of RNA: messenger RNAs (mRNAs), which are translated into proteins, and non-coding RNAs (ncRNAs), which function as RNA molecules. Besides textbook examples such as tRNAs and rRNAs, non-coding RNAs have been found to carry out very diverse functions, from mRNA splicing and RNA modification to translational regulation. It has been estimated that non-coding RNAs make up the vast majority of transcription output of higher eukaryotes. Discriminating mRNA from ncRNA has become an important biological and computational problem. The authors describe a computational method based on a machine learning algorithm known as a support vector machine (SVM) that classifies transcripts according to features they would have if they were coding for proteins. These features include peptide length, amino acid composition, secondary structure content, and protein alignment information. The method is applied to the dataset from the FANTOM3 large-scale mouse cDNA sequencing project; it identifies over 14,000 ncRNAs in mouse and estimates the total number of ncRNAs in the FANTOM3 data to be about 28,000.
Lipid modification of the N-terminal Cys residue (N-acyl-S-diacylglyceryl-Cys) has been found to be an essential, ubiquitous, and unique bacterial posttranslational modification. Such a modification allows anchoring of even highly hydrophilic proteins to the membrane which carry out a variety of functions important for bacteria, including pathogenesis. Hence, being able to identify such proteins is of great value. To this end, we have created a comprehensive database of bacterial lipoproteins, called DOLOP, which contains information and links to molecular details for about 278 distinct lipoproteins and predicted lipoproteins from 234 completely sequenced bacterial genomes. The website also features a tool that applies a predictive algorithm to identify the presence or absence of the lipoprotein signal sequence in a user-given sequence. The experimentally verified lipoproteins have been classified into different functional classes and more importantly functional domain assignments using hidden Markov models from the SUPERFAMILY database that have been provided for the predicted lipoproteins. Other features include the following: primary sequence analysis, signal sequence analysis, and search facility and information exchange facility to allow researchers to exchange results on newly characterized lipoproteins. The website, along with additional information on the biosynthetic pathway, statistics on predicted lipoproteins, and related figures, is available at http://www.mrc-lmb.cam.ac.uk/genomes/dolop/.
The SUPERFAMILY database provides structural assignments to protein sequences and a framework for analysis of the results. At the core of the database is a library of profile Hidden Markov Models that represent all proteins of known structure. The library is based on the SCOP classification of proteins: each model corresponds to a SCOP domain and aims to represent an entire superfamily. We have applied the library to predicted proteins from all completely sequenced genomes (currently 154), the Swiss-Prot and TrEMBL databases and other sequence collections. Close to 60% of all proteins have at least one match, and one half of all residues are covered by assignments. All models and full results are available for download and online browsing at http://supfam.org. Users can study the distribution of their superfamily of interest across all completely sequenced genomes, investigate with which other superfamilies it combines and retrieve proteins in which it occurs. Alternatively, concentrating on a particular genome as a whole, it is possible first, to find out its superfamily composition, and secondly, to compare it with that of other genomes to detect superfamilies that are over- or under-represented. In addition, the webserver provides the following standard services: sequence search; keyword search for genomes, superfamilies and sequence identifiers; and multiple alignment of genomic, PDB and custom sequences.
Profile hidden Markov models (HMMs) are amongst the most successful procedures for detecting remote homology between proteins. There are two popular profile HMM programs, HMMER and SAM. Little is known about their performance relative to each other and to the recently improved version of PSI-BLAST. Here we compare the two programs to each other and to non-HMM methods, to determine their relative performance and the features that are important for their success. The quality of the multiple sequence alignments used to build models was the most important factor affecting the overall performance of profile HMMs. The SAM T99 procedure is needed to produce high quality alignments automatically, and the lack of an equivalent component in HMMER makes it less complete as a package. Using the default options and parameters as would be expected of an inexpert user, it was found that from identical alignments SAM consistently produces better models than HMMER and that the relative performance of the model-scoring components varies. On average, HMMER was found to be between one and three times faster than SAM when searching databases larger than 2000 sequences, SAM being faster on smaller ones. Both methods were shown to have effective low complexity and repeat sequence masking using their null models, and the accuracy of their E-values was comparable. It was found that the SAM T99 iterative database search procedure performs better than the most recent version of PSI-BLAST, but that scoring of PSI-BLAST profiles is more than 30 times faster than scoring of SAM models.
The SUPERFAMILY database contains a library of hidden Markov models representing all proteins of known structure. The database is based on the SCOP ‘superfamily’ level of protein domain classification which groups together the most distantly related proteins which have a common evolutionary ancestor. There is a public server at http://supfam.org which provides three services: sequence searching, multiple alignments to sequences of known structure, and structural assignments to all complete genomes. Given an amino acid or nucleotide query sequence the server will return the domain architecture and SCOP classification. The server produces alignments of the query sequences with sequences of known structure, and includes multiple alignments of genome and PDB sequences. The structural assignments are carried out on all complete genomes (currently 59) covering approximately half of the soluble protein domains. The assignments, superfamily breakdown and statistics on them are available from the server. The database is currently used by this group and others for genome annotation, structural genomics, gene prediction and domain-based genomic studies.