Tensor clustering with algebraic constraints gives interpretable groups of crosstalk mechanisms in breast cancer
Preprint
Abstract
We introduce a tensor-based clustering method to extract sparse, low-dimensional structure from high-dimensional, multi-indexed datasets. This framework is designed to enable detection of clusters of data in the presence of structural requirements which we encode as algebraic constraints in a linear program. Our clustering method is general and can be tailored to a variety of applications in science and industry. We illustrate our method on a collection of experiments measuring the response of genetically diverse breast cancer cell lines to an array of ligands. Each experiment consists of a cell line-ligand combination, and contains time-course measurements of the early-signalling kinases MAPK and AKT at two different ligand dose levels. By imposing appropriate structural constraints and respecting the multi-indexed structure of the data, the analysis of clusters can be optimized for biological interpretation and therapeutic understanding. We then perform a systematic, large-scale exploration of mechanistic models of MAPK-AKT crosstalk for each cluster. This analysis allows us to quantify the heterogeneity of breast cancer cell subtypes, and leads to hypotheses about the signalling mechanisms that mediate the response of the cell lines to ligands.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- k-CEVCLUS: Constrained evidential clustering of large dissimilarity dataKnowledge-Based Systems, 2018
- Constrained clustering by constraint programmingArtificial Intelligence, 2017
- Model‐Based Design of a Decision Tree for Treating HER2+ Cancers Based on Genetic and Protein BiomarkersCPT: Pharmacometrics & Systems Pharmacology, 2015
- Encoding and Decoding Cellular Information through Signaling DynamicsCell, 2013
- On constrained spectral clustering and its applicationsData Mining and Knowledge Discovery, 2012
- Therapeutic resistance resulting from mutations in Raf/MEK/ERK and PI3K/PTEN/Akt/mTOR signaling pathwaysJournal of Cellular Physiology, 2011
- Triple‐negative breast cancer: Present challenges and new perspectivesMolecular Oncology, 2010
- Integer Linear Programming Models for Constrained Clustering2010
- DAISY: A new software tool to test global identifiability of biological and physiological systemsComputer Methods and Programs in Biomedicine, 2007
- Specificity of receptor tyrosine kinase signaling: Transient versus sustained extracellular signal-regulated kinase activationCell, 1995