PANTHER in 2013: modeling the evolution of gene function, and other gene attributes, in the context of phylogenetic trees

Abstract

The data and tools in PANTHER-a comprehensive, curated database of protein families, trees, subfamilies and functions available at http://pantherdb.org-have undergone continual, extensive improvement for over a decade. Here, we describe the current PANTHER process as a whole, as well as the website tools for analysis of user-uploaded data. The main goals of PANTHER remain essentially unchanged: the accurate inference (and practical application) of gene and protein function over large sequence databases, using phylogenetic trees to extrapolate from the relatively sparse experimental information from a few model organisms. Yet the focus of PANTHER has continually shifted toward more accurate and detailed representations of evolutionary events in gene family histories. The trees are now designed to represent gene family evolution, including inference of evolutionary events, such as speciation and gene duplication. Subfamilies are still curated and used to define HMMs, but gene ontology functional annotations can now be made at any node in the tree, and are designed to represent gain and loss of function by ancestral genes during evolution. Finally, PANTHER now includes stable database identifiers for inferred ancestral genes, which are used to associate inferred gene attributes with particular genes in the common ancestral genomes of extant species.

Figure 1.

Cumulative citations of PANTHER for different research applications. All searches have an exclusion filter to remove false positives, which includes terms such as ‘panther publishing’, ‘panther informatics’, ‘black panther’ and 15 other terms. Data from Google Scholar as of 1 October 2012, so figures for 2012 will appear artificially low.

Figure 2.

PANTHER data generation process overview.

Figure 3.

Phylogenetic distribution of genomes in PANTHER reference trees. Triangles at the end of branches represent clades with more than one genome, whereas other branch tips represent single genomes. MONBE (Monosiga brevicollis, choanoflagellate), NEMVE (Nematostella vectensis, sea anemone), TRIAD (Trichoplax adhaerens, placozoan) and SCHMA (Schistosoma mansoni, trematode).

Figure 4.

Example subfamily annotations, for P73 and P53 subfamilies (PTHR11447). The P73 subfamily (blue) includes descendants of the annotated P73 node, except for more recent subfamilies such as the P53 subfamily (green) and P63 subfamily (pink, collapsed SF8).

Figure 5.

Example tree annotations of gene function, for the MutS homolog family (PTHR11361). The tree is annotated with functional ‘gains’ (indicated by plus) and ‘losses’ (indicated by minus). Inferred gene duplications are indicated by small gray squares, and annotated speciation events by small gray circles. Based on the distribution of experimental GO annotations from the literature for genes in model organisms (not shown here), the curator has inferred that the common ancestor of the family had the molecular function ‘double-stranded DNA binding’. Prior to the common ancestor of mutS (bacteria) and the mutS homologs (MSH’s in eukaryotes), one duplicate gained a function in ‘DNA repair’ (biological process). This function was preserved in most descendant homologs, but was lost prior to the radiation of MSH4 and MSH5. In the MSH1 lineage, a specific function in ‘mitochondrial DNA repair’ was gained (likely through the endosymbiotic origin of mitochondria). Extant sequences (leaves of the tree) are annotated by inheritance from the ancestral node annotations. Note that all ancestral annotations are inherited unless they are lost in a more recent ancestor, e.g. MSH4 and MSH5 do not inherit DNA repair even though they have an ancestor that likely participated in DNA repair. Full annotations for this family are available at http://www.pantree.org/tree/family.jsp?accession=PTHR11361.

Figure 6.

Percentage of protein-coding genes tracked forward from PANTHER 7 (2009) to PANTHER 8 (2012). Overall, the nodes are very stable, but the predicted gene sets for a few genomes have undergone extensive revision, notably Ciona intestinalis (sea squirt), Strongylocentrotus purpuratus (purple sea urchin), chicken and Tetrahymena.

Figure 7.

New PANTHER home page. The most common user workflows are organized by ‘folder tabs’ across the top. The Gene List Analysis tab is displayed by default, and users are guided on how to enter or upload a list of genes (optionally with numeric values included), and then launch one of four different functional analyses using the data in the PANTHER database (Table 1).