Finding Functionally Related Genes by Local and Global Analysis of MEDLINE Abstracts

Abstract

Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. We present a textual analysis of documents associated with pairs of genes, and describe how this approach can be used to discover and annotate functional relationships among genes. A study on a subset of human genes show that our analysis tool can act as a ranking mechanism for sets of genes based on their functional relatedness.

A GO-driven semantic similarity measure for quantifying the biological relatedness of gene products

“…Traditional, data-driven approaches for clustering large scale data sets resulting from DNA microarray gene expression experiments lack the fundamental ability to automatically assess and illustrate the characteristics of the resulting clusters from a biological standpoint [43]. Information retrieval [32], text mining [21] and statistical natural processing methods [17,20] have been recently deployed in order to quantify and assess the pair-wise biological similarity between gene products. Additionally, similar approaches have been used in order to discover and analyse the functional enrichment of groups of gene products, such as clusters resulting from data clustering analysis [37].…”

“…Glenisson et al [20] implemented and presented a framework, TXTGate, based on textual information for profiling groups of individual genes. In their work, Nakken [32] described a method of text analysis based on global and local analysis of documents associated with pairs of genes and illustrate how their approach can be utilized for discovering, identifying and annotating functional relationships between them. In their study, Bolshakova [8] developed a knowledge-driven cluster validity assessment system for results obtained by DNA microarray hybridization measurement clustering experiments.…”