Splice-mediated Variants of Proteins (SpliVaP) - data and characterization of changes in signatures among protein isoforms due to alternative splicing

Abstract

Background: It is often the case that mammalian genes are alternatively spliced; the resulting alternate transcripts often encode protein isoforms that differ in amino acid sequences. Changes among the protein isoforms can alter the cellular properties of proteins. The effect can range from a subtle modulation to a complete loss of function.

Results: (i) We examined human splice-mediated protein isoforms (as extracted from a manually curated data set, and from a computationally predicted data set) for differences in the annotation for protein signatures (Pfam domains and PRINTS fingerprints) and we characterized the differences & their effects on protein functionalities. An important question addressed relates to the extent of protein isoforms that may lack any known function in the cell. (ii) We present a database that reports differences in protein signatures among human splice-mediated protein isoform sequences.

Conclusion: (i) Characterization: The work points to distinct sets of alternatively spliced genes with varying degrees of annotation for the splice-mediated protein isoforms. Protein molecular functions seen to be often affected are those that relate to: binding, catalytic, transcription regulation, structural molecule, transporter, motor, and antioxidant; and the processes that are often affected are nucleic acid binding, signal transduction, and protein-protein interactions. Signatures are often included/excluded and truncated in length among protein isoforms; truncation is seen as the predominant type of change. Analysis points to the following novel aspects: (a) Analysis using data from the manually curated Vega indicates that one in 8.9 genes can lead to a protein isoform of no "known" function; and one in 18 expressed protein isoforms can be such an "orphan" isoform; the corresponding numbers as seen with computationally predicted ASD data set are: one in 4.9 genes and one in 9.8 isoforms. (b) When swapping of signatures occurs, it is often between those of same functional classifications. (c) Pfam domains can occur in varying lengths, and PRINTS fingerprints can occur with varying number of constituent motifs among isoforms - since such a variation is seen in large number of genes, it could be a general mechanism to modulate protein function. (ii)

Data: The reported resource (at http://www.bioinformatica.crs4.org/tools/dbs/splivap/) provides the community ability to access data on splice-mediated protein isoforms (with value-added annotation such as association with diseases) through changes in protein signatures.

Figure 1

Definitions of splice-mediated changes in the annotation for PRINTS fingerprints and Pfam domains among protein isoforms.

Figure 2

Flow of data (on genes and protein isoforms) through methodological steps adopted to derive the Set D used for characterizations. The numbers given in red correspond to the ASD data set, and those given in print colour correspond to the Vega data set. The number of genes in Set D forms 44.7% (33.4% in the case of ASD) of the genes from the start-up data set, the number of (PRINTS and Pfam) annotated protein isoforms and unannotated protein isoforms form 41% and 7% (27.5% and 8.6% in the case of ASD), respectively of the isoforms from the start-up data set.

Figure 3

Illustration of a typical result page from the web access of SpliVaP database. Reported is the data on protein isoforms from PEPD gene. Reported changes in Pfam domains between two isoforms SP1 and SP4 (which are hyperlinked to splice patterns in ASD database) are an insertion/deletion and a truncation. Associations to a template structure entry in MSD, and to a related entry of genetic disorder in OMIM are shown and are hyperlinked.