Gene fingerprint model for literature based detection of the associations among complex diseases: a case study of COPD

Abstract

BackgroundDisease comorbidity is very common and has significant impact on disease treatment. Revealing the associations among diseases may help to understand the mechanisms of diseases, improve the prevention and treatment of diseases, and support the discovery of new drugs or new uses of existing drugs.MethodsIn this paper, we introduced a mathematical model to represent gene related diseases with a series of associated genes based on the overrepresentation of genes and diseases in PubMed literature. We also illustrated an efficient way to reveal the implicit connections between COPD and other diseases based on this model.ResultsWe applied this approach to analyze the relationships between Chronic Obstructive Pulmonary Disease (COPD) and other diseases under the Lung diseases branch in the Medical subject heading index system and detected 4 novel diseases relevant to COPD. As judged by domain experts, the F score of our approach is up to 77.6%.ConclusionsThe results demonstrate the effectiveness of the gene fingerprint model for diseases on the basis of medical literature.

Literature-based discovery approaches for evidence-based healthcare: a systematic review

“…Disease comorbidity is very common and is a popular area of research in the medical community, because of its impact on the treatment of diseases. Knowledge of the association between diseases can significantly improve the understanding of the mechanisms of diseases, thus aiding in better prevention and treatment [ 37 ]. Thus, Chen et al [ 37 ] have used an open LBD approach for the detection of associations among complex diseases.…”

“…Knowledge of the association between diseases can significantly improve the understanding of the mechanisms of diseases, thus aiding in better prevention and treatment [ 37 ]. Thus, Chen et al [ 37 ] have used an open LBD approach for the detection of associations among complex diseases. Closed LBD approach was also used for the explanation of the correlation between epilepsy and inflammatory bowel disease [ 38 ], and between myocardial infarction and depression [ 39 ].…”

“…Relatedness between a pair of concepts is then derived based on the similarity between the vectors. Various distributional semantic techniques which have been proposed include Semantic Predications [ 18 , 25 , 30 ], Latent Semantic Analysis (LSA) [ 37 ], Predication-based Semantic Indexing (PSI) [ 28 ] and composite feature vectors [ 29 ]. Mower et al [ 29 ] have shown that distributional models perform better than co-occurrence-based models.…”

“…Due to the very large datasets and the multitude of possible pathways, the LBD models proposed are computationally intensive, therefore leading to certain limitations. Techniques proposed to improve accuracy include: Integration of machine learning and deep learning algorithms in LBD models [ 27 , 29 , 37 ] , Development of high-quality NLP tools for better accuracy, due to the reported shortcomings of existing tools Use of relevant tools for the normalization of gene and disease targets [ 19 ] Consideration of full texts of research articles instead of only titles and abstracts [ 32 ] Use of graph embedding to obtain long paths [ 23 ] Consideration of indirect relationships from knowledge graphs [ 24 ] …”

The International Conference on Intelligent Biology and Medicine 2018: Medical Informatics Thematic Track (MedicalInfo2018)

“…Revealing the associations between diseases and genes as well as between diseases may help to understand the mechanisms of diseases, improve the prevention and treatment of diseases, and support the discovery of drug repurposing. Chen et al [6] introduced a mathematic model to quantitatively measure the associations between genes and diseases, which was then used to indicate the relations between diseases. By applying this approach to analyze the relationships between Chronic Obstructive Pulmonary Disease (COPD) and other diseases under the Lung diseases branch in MeSH (the Medical subject heading index system), 4 novel diseases relevant to COPD were detected.…”