Automating parameter selection to avoid implausible biological pathway models

Abstract

A common way to integrate and analyze large amounts of biological omic data is through pathway finding: creating a subnetwork of a generic background network that represents some process or cellular state using condition-specific omic data. A challenge in pathway finding is that adjusting pathway creation algorithms' parameters produces pathways with drastically different topological properties and biological interpretations. Due to the exploratory nature of pathway finding, there is no ground truth for direct evaluation, so parameter tuning methods typically used in statistics and machine learning are inapplicable. We developed the pathway parameter advising method to tune pathway finding algorithms to minimize biologically implausible predictions. We leverage background knowledge in pathway databases to select pathways whose high-level structure resembles that of manually curated biological pathways. At the core of this method is a graphlet decomposition metric, which measures topological similarity to curated biological pathways. In order to evaluate pathway parameter advising, we compare its performance in avoiding implausible networks and reconstructing pathways from the NetPath database with other parameter selection methods across four pathway finding algorithms. We also demonstrate how pathway parameter advising can guide construction of an influenza host factor network. Pathway parameter advising is method-agnostic; it is applicable to any pathway finding algorithm with tunable parameters. Our pathway parameter advising software is available on GitHub at https://github.com/gitter-lab/pathway-parameter-advising.