The DAVID Gene Functional Classification Tool: a novel biological module-centric algorithm to functionally analyze large gene lists

Abstract

The DAVID Gene Functional Classification Tool http://david.abcc.ncifcrf.gov uses a novel agglomeration algorithm to condense a list of genes or associated biological terms into organized classes of related genes or biology, called biological modules. This organization is accomplished by mining the complex biological co-occurrences found in multiple sources of functional annotation. It is a powerful method to group functionally related genes and terms into a manageable number of biological modules for efficient interpretation of gene lists in a network context.

Figure 1

Flow chart of the procedures for the DAVID Gene Functional Classification Tool and the DAVID Functional Annotation Clustering Tool.

Figure 2

A hypothetical example of detecting gene-gene functional relationships by kappa statistics. (a) The all-redundant and structured terms are broken into 'independent' terms in a flat linear collection. Each gene associates with some of the annotation term collection so that a gene-annotation matrix can be built in a binary format, where 1 represents a positive match for the particular gene-term and 0 represents the unknown. Thus, each gene has a unique profile of annotation terms represented by a combination of 1 s and 0 s. (b) For a particular example of genes a and b, a contingency table was constructed for kappa statistics calculation. The higher kappa score (0.66) indicates that genes a and b are in considerable agreement, more so than by random chance. By flipping the table 90 degrees, the kappa score of term-term can be achieved, based on the agreement of common genes (not shown). For more information see Additional data files 11 and 12.

Figure 3

The gene-gene functional relationship can be specifically detected by kappa statistics. (a) Kappa scores were calculated for all possible combinations of human gene-gene pairs (approximately 300 million). Only gene-gene pairs with a higher number of annotation terms in common possibly have good kappa values. The box plot consists of the smallest and largest observations at the two end points (95% confidence interval), as well as a box from the 1st to 3rd quartiles. The blue and red lines represent median and mean observations, respectively. (b) Kappa scores were calculated for all possible human gene-gene pairs, gene-gene pairs with randomized annotation terms, all collected protein-protein interacting pairs, and all 'chemokine' gene pairs, respectively. The distributions of those kappa scores from protein-protein interacting pairs (pink) and 'chemokine' gene pairs (light blue) significantly shift to the high value end compared to human total (blue); conversely, the kappa score distribution (yellow) of gene pairs with randomized annotation terms remains in the lower value end below 0.35. Interestingly, for the human genome (blue), over 50% of the kappa scores equal 0 (no detectable relationships) and >95% are lower than 0.35. Altogether, this indicates that kappa statistics can specifically detect the gene-gene functional relationships.

Figure 4

Graphical illustration of the heuristic fuzzy partition algorithm. (a) Hypothetically, each element (gene) can be positioned in a virtual two-dimensional space, based on its characteristics (annotation terms). The distance represents the degree of relationship (kappa score) among the genes. (b) Any gene has a chance as a medoid to form an initial seeding group. Only the initial groups with enough closely related members (for example, members >3 and kappa score ≥0.4) are qualified (solid-line circle). Conversely, unqualified ones are shown as dashed-line circles. (c) Every qualified initial seeding group is iteratively merged with each other to form a larger group based on the multi-linkage rule, that is, sharing 50% or more of memberships, until all secondary clusters (thicker oval) are stable. Importantly, the genes not covered by any qualified initial seeding group are considered as outliers (in gray). (d) Finally, three final groups (thicker ovals) are formed because they can no longer be merged with any other group. One gene (in red) belonging to two groups represents the fuzziness capability of the algorithm. And outliers (in gray in (c)) are removed for clearer presentation. A step-by-step example can be found in Additional data file 13.

Figure 5

A text format report from the Gene Functional Classification Tool. The example shows the output of 16 genes (Additional data file 1) analyzed by the tool with default settings. Without prior knowledge, the tool is able to classify genes into three functional gene groups. On each group header, a set of buttons is provided for in-depth exploration of the annotation for the group. 'T' reports the major enriched annotation terms associated with the group. The 'Heat Map' symbol provides a detailed graphical view of gene-term relationships. 'RG' searches other related genes in the genome but not in the list.

Figure 6

An example of genes-to-terms 2-D view. All the related 23 kinase genes and their associated annotation terms from gene group 3 (kinase group) for demo list 2 are displayed in a 2-D heat map-like interactive graphical view. Green represents the positive association between the gene-term; conversely, black represent an unknown relationship. The annotation terms are ordered based on their enrichment scores associated with the group. The kinase commonly related annotations (big green block) are shown on the left side, and the scattered pattern (green and black) on the right side shows the functional difference.