Modeling in systems biology: Causal understanding before prediction?

Abstract

Babur et al. (2021) developed the CausalPath tool to infer causal signaling interactions in high-throughput proteomics data that may foster mechanical understanding from large-scale biological datasets.

Figure 1

Schematic representation of systems biology modeling directions Knowledge-driven methods (top) use literature-curated gene sets of functionally related genes and perform some kind of overrepresentation/enrichment analysis using them. The enriched gene sets can help to interpret associations with different biological mechanisms; however, causal interactions are hard to be identified. Data-driven methods (bottom) use statistical/machine-learning methods to predict biological phenotypes. While these methods reach good predictive performance, their generalization and ability to gain mechanistic insight is limited in several cases. Causal reasoning methods (middle) use prior-knowledge network information together with data to identify contextualized causal signaling networks. The identified causal interactions can be used for hypothesis generation; however, future benchmarking of these methods is needed. Figure was created with BioRender.com.