Abstract
Background: Accumulating experimental studies have indicated that disease comorbidity causes additional pain to patients and leads to the failure of standard treatments compared to patients who have a single disease. Therefore, accurate prediction of potential comorbidity is essential to design more efficient treatment strategies. However, only a few disease comorbidities have been discovered in the clinic.
Objective: In this work, we propose PCHS, an effective computational method for predicting disease comorbidity.
Materials and Methods: We utilized the HeteSim measure to calculate the relatedness score for different disease pairs in the global heterogeneous network, which integrates six networks based on biological information, including disease-disease associations, drug-drug interactions, protein-protein interactions and associations among them. We built the prediction model using the Support Vector Machine (SVM) based on the HeteSim scores.
Results and Conclusion: The results showed that PCHS performed significantly better than previous state-of-the-art approaches and achieved an AUC score of 0.90 in 10-fold cross-validation. Furthermore, some of our predictions have been verified in literatures, indicating the effectiveness of our method.
Keywords: Disease comorbidity, HeteSim measure, heterogeneous network, disease gene, disease drug, protein-protein interaction.
Graphical Abstract
[http://dx.doi.org/10.1016/j.molmed.2013.07.004]
[http://dx.doi.org/10.1370/afm.1]
[http://dx.doi.org/10.1186/1472-6963-6-84]
[http://dx.doi.org/10.1053/ajkd.2001.29275]
[http://dx.doi.org/10.1016/j.neucom.2018.01.085]
[http://dx.doi.org/10.1073/pnas.0701361104]
[http://dx.doi.org/10.1073/pnas.0701722105]
[http://dx.doi.org/10.1038/msb.2009.16]
[http://dx.doi.org/10.1073/pnas.0802208105]
[http://dx.doi.org/10.1109/TCBB.2013.10]
[http://dx.doi.org/10.1038/nature04209]
[http://dx.doi.org/10.1016/j.cell.2005.08.029]
[http://dx.doi.org/10.2174/1566523218666181010101114]
[http://dx.doi.org/10.1038/msb.2011.29]
[http://dx.doi.org/10.1038/srep00757]
[http://dx.doi.org/10.1186/2043-9113-4-8]
[http://dx.doi.org/10.1126/science.1257601]
[http://dx.doi.org/10.1186/s12864-017-4272-7]
[http://dx.doi.org/10.1109/TCBB.2016.2550443]
[http://dx.doi.org/10.1038/s41598-017-03986-1]
[http://dx.doi.org/10.1109/TCBB.2016.2520947]
[http://dx.doi.org/10.1093/nar/gkq1126]
[http://dx.doi.org/10.1016/j.ins.2019.05.017]
[http://dx.doi.org/10.1016/j.jbi.2018.11.005]
[http://dx.doi.org/10.1093/nar/gku1003]
[http://dx.doi.org/10.1093/nar/gki033]
[http://dx.doi.org/10.1109/BIBM.2017.8217698]
[http://dx.doi.org/10.1186/s12859-018-2220-4]
[http://dx.doi.org/10.1016/j.ymeth.2018.06.001]
[http://dx.doi.org/10.1186/s12920-018-0414-2]
[http://dx.doi.org/10.1109/TCBB.2017.2701379]
[http://dx.doi.org/10.1109/TCBB.2017.2704587]
[http://dx.doi.org/10.1093/bioinformatics/btx833]
[http://dx.doi.org/10.1016/j.compbiolchem.2018.03.017]
[http://dx.doi.org/10.3389/fgene.2019.00003]
[http://dx.doi.org/10.1109/TCBB.2019.2904965]
[http://dx.doi.org/10.1038/s41598-019-45954-x]
[http://dx.doi.org/10.1093/nar/gky1051]
[http://dx.doi.org/10.1093/bioinformatics/bty002]
[http://dx.doi.org/10.1093/bib/bbx103]
[http://dx.doi.org/10.1093/bioinformatics/bty440]
[http://dx.doi.org/10.1109/TCBB.2016.2530062] [PMID: 26890921]
[http://dx.doi.org/10.1038/s41598-019-45814-8] [PMID: 31249365]
[http://dx.doi.org/10.1093/bib/bbx041] [PMID: 28453640]
[http://dx.doi.org/10.1109/TKDE.2013.2297920]
[http://dx.doi.org/10.1186/s12859-018-2390-0]
[http://dx.doi.org/10.1023/A:1009715923555]
[http://dx.doi.org/10.1214/aos/1013203451]
[http://dx.doi.org/10.1155/2015/671950]
[http://dx.doi.org/10.1038/s41598-018-19357-3]
[http://dx.doi.org/10.1126/science.1257601]
[http://dx.doi.org/10.1097/MD.0000000000006396]
[http://dx.doi.org/10.5306/wjco.v5.i3.197]
[http://dx.doi.org/10.2174/1566523218666181004145424]