Automatic Extraction of Protein Point Mutations Using a Graph Bigram Association

Abstract

Protein point mutations are an essential component of the evolutionary and experimental analysis of protein structure and function. While many manually curated databases attempt to index point mutations, most experimentally generated point mutations and the biological impacts of the changes are described in the peer-reviewed published literature. We describe an application, Mutation GraB (Graph Bigram), that identifies, extracts, and verifies point mutations from biomedical literature. The principal problem of point mutation extraction is to link the point mutation with its associated protein and organism of origin. Our algorithm uses a graph-based bigram traversal to identify these relevant associations and exploits the Swiss-Prot protein database to verify this information. The graph bigram method is different from other models for point mutation extraction in that it incorporates frequency and positional data of all terms in an article to drive the point mutation–protein association. Our method was tested on 589 articles describing point mutations from the G protein–coupled receptor (GPCR), tyrosine kinase, and ion channel protein families. We evaluated our graph bigram metric against a word-proximity metric for term association on datasets of full-text literature in these three different protein families. Our testing shows that the graph bigram metric achieves a higher F-measure for the GPCRs (0.79 versus 0.76), protein tyrosine kinases (0.72 versus 0.69), and ion channel transporters (0.76 versus 0.74). Importantly, in situations where more than one protein can be assigned to a point mutation and disambiguation is required, the graph bigram metric achieves a precision of 0.84 compared with the word distance metric precision of 0.73. We believe the graph bigram search metric to be a significant improvement over previous search metrics for point mutation extraction and to be applicable to text-mining application requiring the association of words.

CoagMDB: a database analysis of missense mutations within four conserved domains in five vitamin K-dependent coagulation serine proteases using a text-mining tool

“…A 2004 study developed regular expressions to extract mutations from MEDLINE abstracts [Rebholz-Schuhmann et al, 2004]. Two subsequent studies used pipelines to extract mutations automatically from full-length publications [Baker and Witte, 2006;Lee et al, 2007]. Both of these pipelines focused on extracting mutagenesis data from fulllength publications and were applied to specific protein families such as the protein tyrosine kinases.…”

“…This relies on the user manually changing the protein name if it is incorrectly assigned. This simplifies the problem, and does not really increase processing time since the majority of papers only discuss mutations within one protein [Lee et al, 2007].…”

Rapid Pattern Development for Concept Recognition Systems: Application to Point Mutations

“…6,[8][9][10][11][12] MuteXt, 8 MEMA, 9 and Mutation GraB 10 attempt to extract mentions of mutations paired with a specific gene or gene product from input texts. OSIRIS 11 is a web-based information retrieval system for compiling the mutation literature using a concept-driven, mutation-recognition approach.…”

“…Like the earlier mutation recognition systems, [8][9][10] MutationFinder applies a set of regular expressions to identify mutation mentions in input texts. Our currently top-performing collection of regular expressions results in a precision of 98.4% and a recall of 81.9% when extracting mutation mentions from completely blind test data.…”

“…Our Normalized Mutations metric is equivalent to their "Cited Mutation" metric. Since Lee et al 10 only present performance data on this corpus for the more ambitious task of extracting associated pairs of mutations and genes/proteins, a direct comparison with their system cannot be Table 8. Performance of MutationFinder on the Mutation GraB corpus.…”