Back

vWCluster: A Network Based Clustering of Multi-omics Breast Cancer Data Based on Vector-Valued Optimal Transport

Zhu, J.; Oh, J. H.; Deasy, J.; Tannenbaum, A. R.

2021-06-18 bioinformatics
10.1101/2021.06.17.448878 bioRxiv
Show abstract

In this paper, we present a network-based clustering method based on the vector-valued Wasserstein distance derived from optimal mass transport (OMT) theory. This distance allows for the natural integration of multi-layer representations of data in a given network from which one derives clusters via a hierarchical clustering approach. In this study, we applied the methodology, called vector Wasserstein clustering (vW-cluster), to multi-omics data from the two largest breast cancer studies. The resultant clusters showed significantly different survival rates in Kaplan-Meier analysis in both datasets. CIBERSORT scores were compared among the identified clusters. Out of the 22 CIBERSORT immune cell types, 9 were commonly significantly different in both datasets, suggesting the difference of tumor immune microenvironment in the cluster. vWCluster can aggregate multi-omics data represented as a vectorial form in a network with multiple layers, taking into account the concordant effect of heterogeneous data, and further identify subtypes of tumors with different survival rates.

Matching journals

The top 7 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.