Finding disease similarity based on implicit semantic similarity

Abstract

Genomics has contributed to a growing collection of gene-function and gene-disease annotations that can be exploited by informatics to study similarity between diseases. This can yield insight into disease etiology, reveal common pathophysiology and/or suggest treatment that can be appropriated from one disease to another. Estimating disease similarity solely on the basis of shared genes can be misleading as variable combinations of genes may be associated with similar diseases, especially for complex diseases. This deficiency can be potentially overcome by looking for common biological processes rather than only explicit gene matches between diseases. The use of semantic similarity between biological processes to estimate disease similarity could enhance the identification and characterization of disease similarity. We present functions to measure similarity between terms in an ontology, and between entities annotated with terms drawn from the ontology, based on both co-occurrence and information content. The similarity measure is shown to outperform other measures used to detect similarity. A manually curated dataset with known disease similarities was used as a benchmark to compare the estimation of disease similarity based on gene-based and Gene Ontology (GO) process-based comparisons. The detection of disease similarity based on semantic similarity between GO Processes (Recall=55%, Precision=60%) performed better than using exact matches between GO Processes (Recall=29%, Precision=58%) or gene overlap (Recall=88% and Precision=16%). The GO-Process based disease similarity scores on an external test set show statistically significant Pearson correlation (0.73) with numeric scores provided by medical residents. GO-Processes associated with similar diseases were found to be significantly regulated in gene expression microarray datasets of related diseases.

Research on the Acquisition Algorithm of Ontology Meta-model in Medical Domain Knowledge

“…The corresponding relation can be expressed by multiple groups as <SME, TME, Relationship>. With Gruber given five tuple ontology definition structure [4]: O=(C，I，R，F，A) that includes four major types in the process of ontology mapping: mapping between concepts, mapping between attributes and concept, mapping between attribute and attribute, mapping between context and constraint [5].…”

Gene2DisCo: Gene to disease using disease commonalities

“…Finally, a promising category of GP methods has focused on the analysis of common characteristics among different diseases [33,34], discovering sets of interacting proteins and molecular pathways often shared by multiple diseases [35]. The main benefit of such an approach is that 'transferring' information from comparable diseases provides researcher with additional predictive information to prioritize genes, and in particular for less studied abnormalities [36], thus leading to new therapeutic treatments not previously considered.…”

Research of Semantic Similarity Algorithm Based on the Knowledge of Medical Domain

“…Similarity computing can improve the performance of information retrieval for medical resources, and can effectively promote the integration of heterogeneous clinical data. Semantic similarity method to analyze the patient's medical records in a semantic way to identify patients with similar cases [2]. Analysis of related references [3][4][5], some research suggests a general knowledge ontology and semantic similarity between concepts of corpus research, while others are used to study the semantic similarity method of ontology and domain specific corpus.…”