Back

Integrated Identification of Disease Specific Pathways Using Multi-omics data

Lu, Y.; Chang, Y.-T.; Hoffman, E. P.; Yu, G.; Herrington, D. M.; Clarke, R.; Wu, C.-T.; Chen, L.; Wang, Y.

2019-06-11 bioinformatics
10.1101/666065 bioRxiv
Show abstract

MotivationIdentification of biological pathways plays a central role in understanding both human health and diseases. Although much work has previously been done to explore the biological pathways by using single omics data, little effort has been reported using multi-omics data integration, mainly due to methodological and technological limitations. Compared to single omics data, multi-omics data will help identifying disease specific functional pathways with both higher sensitivity and specificity, thus gaining more comprehensive insights into the molecular architecture of disease processes.\n\nResultsIn this paper, we propose two computational approaches that integrate multi-omics data and identify disease-specific biological pathways with high sensitivity and specificity. Applying our methods to an experimental multi-omics data dataset on muscular dystrophy subtypes, we identified disease-specific pathways of high biological plausibility. The developed methodology will likely have a broad impact on improving the molecular characterization of many common diseases.\n\nContactyuewang@vt.edu\n\nSupplementary informationSupplementary information attached.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.