Quantifying the multi-scale performance of network inference algorithms

DOI10.1515/SAGMB-2014-0012MaRDI QIDQ470320zbMATH OpenOpenAlexWikidataFDO

Authors Chris J. Oates, Richard Amos, Simon E. F. Spencer

Publication date 12 November 2014

Published in Statistical Applications in Genetics and Molecular Biology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1402.7322

zbMATH Keywords

performance assessmentnetwork inferencemulti-scale scores

Mathematics Subject Classification ID

Applications of graph theory (05C90) Systems biology, networks (92C42)

Abstract: Graphical models are widely used to study complex multivariate biological systems. Network inference algorithms aim to reverse-engineer such models from noisy experimental data. It is common to assess such algorithms using techniques from classifier analysis. These metrics, based on ability to correctly infer individual edges, possess a number of appealing features including invariance to rank-preserving transformation. However, regulation in biological systems occurs on multiple scales and existing metrics do not take into account the correctness of higher-order network structure. In this paper novel performance scores are presented that share the appealing properties of existing scores, whilst capturing ability to uncover regulation on multiple scales. Theoretical results confirm that performance of a network inference algorithm depends crucially on the scale at which inferences are to be made; in particular strong local performance does not guarantee accurate reconstruction of higher-order topology. Applying these scores to a large corpus of data from the DREAM5 challenge, we undertake a data-driven assessment of estimator performance. We find that the ``wisdom of crowds network, that demonstrated superior local performance in the DREAM5 challenge, is also among the best performing methodologies for inference of regulation on multiple length scales. MATLAB R2013b code "net_assess" is provided as Supplement.

Recommendations

• Network inference and biological dynamics
• scientific article; zbMATH DE number 5262713
• Inferring multiple graphical structures
• Joint estimation of multiple related biological networks
• Using Complexity for the Estimation of Bayesian Networks

Cites work

• scientific article; zbMATH DE number 1493045 (Why is no real title available?)
• scientific article; zbMATH DE number 1844472 (Why is no real title available?)
• A Survey on PageRank Computing
• A Theorem on Boolean Matrices
• Causality and model abstraction
• Graph spectra as a systematic tool in computational biology
• Inductive Logic Programming
• Joint estimation of multiple related biological networks
• Network inference and biological dynamics

Cited in

(6)

• Combining gene expression data and prior knowledge for inferring gene regulatory networks via Bayesian networks using structural restrictions
• QRF
• scientific article; zbMATH DE number 5262713 (Why is no real title available?)
• Bayesian state space models for dynamic genetic network construction across multiple tissues
• Influence of statistical estimators on the large-scale causal inference of regulatory networks
• A T-S fuzzy state observer-based model predictive reset control for a class of fuzzy nonlinear systems with event-triggered mechanism

Describes a project that uses

Uses Software

• GeneRank

This page was built for publication: Quantifying the multi-scale performance of network inference algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q470320)