inferring novel gene-disease associations using medical subject heading over-representation profiles

background: medline^®/pubmed^® currently indexes over 18 million biomedical articles, providing unprecedented opportunities and challenges for text analysis. using medical subject heading over-representation profiles(meshops), an entity of interest can be robustly summarized, quantitatively identifying associated biomedical termsand predicting novel indirect associations.methods: a procedure is introduced for quantitative comparison of meshops derived from a group of medline®articles for a biomedical topic (for example, articles for a specific gene or disease). similarity scores are computedto compare meshops of genes and diseases.results: similarity scores successfully infer novel associations between diseases and genes. the number of papersaddressing a gene or disease has a strong influence on predicted associations, revealing an important bias forgene-disease relationship prediction. predictions derived from comparisons of meshops achieves a mean 8% aucimprovement in the identification of gene-disease relationships compared to gene-independent baselineproperties. conclusions: meshop comparisons are demonstrated to provide predictive capacity for novel relationshipsbetween genes and human diseases. we demonstrate the impact of literature bias on the performance of genediseaseprediction methods. meshops provide a rich source of annotation to facilitate relationship discovery inbiomedical informatics.