The KEGG resource for deciphering the genome

Graph representation

To understand the overall architecture, it is useful to know that KEGG consists of three graph objects for representation and manipulation of genomic, chemical and network data. Mathematically, a graph is a set of nodes (building blocks) and edges (interactions or relations). As shown in Table 1 the three graph objects are called the gene universe (GENES, SSDB and KO databases), the chemical universe (COMPOUND, GLYCAN and REACTION databases), and the protein network (PATHWAY database). The gene universe is a conceptual graph object representing ortholog/paralog relations, operon information and other relationships between genes in all the completely sequenced genomes. The chemical universe is another conceptual graph object representing chemical reactions and structural/functional relations among metabolites and other biochemical compounds. In contrast, the protein network is based on biological phenomena, representing known molecular interaction networks in various cellular processes (2).

Network hierarchy

Another important aspect in the overall architecture of KEGG is network hierarchy. The protein network, which is the most unique data object in KEGG, is stored as a collection of pathway maps in the PATHWAY database, representing wiring diagrams of proteins and other gene products responsible for various cellular functions. Reflecting the map resolution and functional modules at different levels, these pathway maps are hierarchically classified. There are five categories in the top level (metabolism, genetic information processing, environmental information processing, cellular processes and human diseases) and 24 subcategories in the second level. The third level in the hierarchy corresponds to individual pathway maps. When the protein network is linked to the gene universe, the fourth level corresponds to KO (KEGG Orthology) entries. Thus the hierarchy of gene functions in KEGG is based on the hierarchy of the protein network as shown in Table 2.

GENES database

The information about individual genes is stored in the GENES database. As of September 12, 2003 the GENES database contains 572 881 genes in 155 organisms. The GENES entries are generated semi-automatically by selecting and combining various sources including authors’ submissions to GenBank (ftp://ftp.ncbi.nih.gov/genbank/genomes/), the NCBI RefSeq database (ftp://ftp.ncbi.nih.gov/genomes/), the EMBL database (ftp://ftp.ebi.ac.uk/pub/databases/embl/ genomes/) and publicly available organism-specific databases. They are then subjected to internal re-annotation, in which we just assign K numbers for the KO grouping of genes without updating the description of the genes. Our KO assignment appears in the ORTHOLOG line of the GENES entry.

SSDB database

SSDB was originally a sequence similarity database containing precomputed similarity scores by the SSEARCH program with additional information about best hits and best-best hits in pairwise genome comparisons (2). We have recently implemented an automatic procedure, based on a graph analytical method, to computationally generate ortholog clusters (OCs) and paralog clusters (PCs) from the huge SSDB graph, currently containing 200 million edges. The resulting ortholog clusters can be examined by clicking on the ORTHOLOG link in the GENES entry.

KO database

When the KEGG project was initiated in 1995, the integration of genomic information and network information was achieved via the EC numbers. The EC numbers were common identifiers for matching genes in the genome and gene products (enzymes) in the metabolic pathway. Then, a new scheme using ortholog identifiers was introduced (3) to extend the matching procedure to regulatory pathways and to overcome various problems inherent in the enzyme nomenclature. KO is a further extension of this scheme based on computational analysis, as well as manual curation, of SSDB ortholog clusters in order to classify all gene functions and explore unknown pathways. Each KO entry is identified by the K number (accession number) with the previous ortholog identifier as an alternative name. In future releases of KEGG, the KO hierarchy (Table 2) will become more complete, and the current ortholog group tables will be part of the KO database.

COMPOUND database

The COMPOUND database contains chemical structures of most known metabolic compounds and some pharmaceutical and environmental compounds. All chemical structures are manually entered, computationally verified and continuously updated. Currently the database contains 10 739 entries, each of which is identified by the C number (accession number). A new feature implemented in the COMPOUND database is the KCF (KEGG Chemical Function) representation of chemical structures shown in Figure 1 and the resulting graph- based chemical structure comparison method (4). The COMPOUND/REACTION databases are being moved from the ISIS system (5) to the in-house-developed relational database system, in order to integrate with the GLYCAN database. Once this is done the substructure search against the database will be performed more rigorously by our graph comparison algorithm rather than the bit string comparison in the ISIS system.

GLYCAN database

GLYCAN is a new addition to the KEGG suite of databases. We have initiated efforts to collect carbohydrate structures because of the lack of a publicly available database after the termination of the CarbBank project (6). The pathway diagrams for metabolism of complex carbohydrates and metabolism of complex lipids are now linked to individual entries of carbohydrate structures in the GLYCAN database. The reactions catalyzed by glycosyltransferases and other sugar-related enzymes are represented in the REACTION database in a simpler form of carbohydrate structures (Fig. 1) rather than the all-atom representation. Each GLYCAN entry is identified by the G number (accession number) and the current total is 10 445 entries, among which only a few hundred were manually entered and linked to KEGG pathways. The rest represents unique structures derived from CarbBank. The GLYCAN database is maintained in a relational database with the structure drawing tool in Java. A database search is also made available based on newly developed algorithms for tree structure comparisons.

REACTION database

The REACTION database contains reaction formulas for enzymic reactions, currently totaling 5799 entries. Each entry is identified by the R number (accession number) representing a unique reaction corresponding to sets of reactants and products represented by the C number in the COMPOUND database or the G number in the GLYCAN database. This should be compared with the EC number, which may correspond to multiple reaction formulas. The EC number hierarchy is supposed to represent aspects of enzymatic reactions, but in reality it often contains aspects of enzyme molecules. Within the KEGG resource, these two aspects of EC numbers are clearly distinguished: R numbers for reactions and K numbers for molecules. We are working to develop a new hierarchy, tentatively called RC (Reaction Classification), for understanding chemistry of enzymic reactions.

ENZYME database

The ENZYME database contains enzyme nomenclature with numerous links to KEGG databases. It is generated semi-automatically from the enzyme nomenclature website (http://www.chem.qmul.ac.uk/iubmb/enzyme/). The role of this database within KEGG has diminished, but the EC number is still the simplest way to link to KEGG from outside resources.

PATHWAY database

The protein network in KEGG is an abstract network of gene products, representing not only the pathway or the complex resulting from direct protein–protein interactions, but also the metabolic network viewed as a network of enzymes, and the gene regulatory network viewed as a network of transcription factors and target products (2,3). The PATHWAY database is a collection of manually drawn diagrams called the KEGG reference pathway diagrams (maps), each corresponding to a known network of functional significance. The PATHWAY database also contains organism-specific pathways, which are automatically generated by superimposing (coloring) genes in given organisms. The database currently contains 13 457 entries including 235 reference pathway diagrams.

In the past, the pathway diagrams were available only in GIF (or PNG) image files. Although the coordinates of nodes (boxes) could be obtained from the HTML file, it was not possible to reconstruct the pathway because the edge information was not readily available. We have released the KEGG Markup Language (KGML) as a specification of graph objects in KEGG. All metabolic pathways and some regulatory pathways are now available in KGML, enabling computational reconstruction and manipulation of KEGG pathways.