Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published September 17, 2018 | Version v1
Conference paper Open

Network Reconstruction From Time-Course Perturbation Data Using Multivariate Gaussian Processes

  • 1. Department of Electrical Engineering Technische Universität Darmstadt, Germany
  • 2. Department of Electrical Engineering and Department of Biology, Technische Universität Darmstadt, Germany

Description

In this work, we appropriate the popular tool of Gaussian processes to solve the problem of reconstructing networks from time-series
perturbation data. To this end, we propose a construction for multivariate Gaussian processes to describe the continuous-time trajectories of the states of the network entities. We then show that this  construction admits a state-space representation for the network dynamics. By exploiting Kalman filtering techniques, we are able to infer the underlying network in a computationally efficient manner.

Files

final64.pdf

Files (629.3 kB)

Name Size Download all
md5:9a13c3f5d1f378f8b4151297408a445a
629.3 kB Preview Download

Additional details

Funding

PrECISE – PERSONALIZED ENGINE FOR CANCER INTEGRATIVE STUDY AND EVALUATION 668858
European Commission