Conference paper Open Access

Clinical trajectories estimated from bulk tumoral molecular proles using elastic principal trees

Alexander Chervov; Andrei Zinovyev

Clinical trajectory is a clinically relevant sequence of ordered patient phenotypes representing consecutive states of a developing disease and leading to some final state. Extracting trajectories from large scale medical data is of great interest for dynamical phenotyping of various diseases but remains a challenge for machine learning methods, especially in the case of synchronic (with short follow up) observations. Here we describe an approach for trajectory-based analysis of cancer data using elastic principal trees and test it on a large collection of molecular tumoral profiles for breast cancer. We show that the disease progress quantified with pseudotime (the geodesic distance from the root) along a particular trajectory can serve as a significant prognostic factor, not redundant with gene expression-based predictors. We conclude that application of the elastic principal trees to transcriptomic data can be of interest for clinical applications.

Files (1.4 MB)
Name Size
1.4 MB Download
All versions This version
Views 7070
Downloads 3131
Data volume 44.9 MB44.9 MB
Unique views 6262
Unique downloads 3131


Cite as