Reconciling multiple connectivity-based systems biology methods for drug repurposing

Abstract

In the last two decades, numerous in silico methods have been developed for drug repurposing, to accelerate and reduce the risks about early drug development. Particularly, following Connectivity Map, dozens of distinct data-driven methods have been implemented to find candidates from the comparison of differential transcriptomic signatures. Interestingly, there have been multiple proposals to integrate available knowledge using systems biology databases and adapted algorithms from the network biology research field. Despite their similarities, these methods have been formulated inconsistently over the years, even if some of them are fundamentally similar. The aim of this review is to reconcile these integrative methods, focusing on elucidating their common structures while underlining the specificities of their strategies. To achieve this, we classified those methods into two main categories, provided schematic workflow representations, and presented a homogenized formulation for each.

Keywords: connectivity score; data integration; differential expression signature; drug repurposing; system biology.

Figure 1

Taxonomy and chronology of system biology-based connectivity scores. The twelve scores were primarily classified depending on the mathematical object used to integrate systems biology knowledge into connectivity computations: Gene sets or networks. Among gene set driven methods, we distinguish predefined gene sets such as KEGG [19] or GO [20] with inferred gene sets using either data (gene co-expression) or prior knowledge. CMAP1 and CMAP2 connectivity scores were included in the chronology as references, along with the reconciling review by Samart et al. [16].

Figure 2

Schematic representation of key concepts in network analysis. (A) Network-based module inference. Different clustering strategies exist, such as agglomerative hierarchical clustering, to identify communities or modules of related nodes. (B) Bipartite network. These networks are characterized for having two classes of nodes with edges only existing between nodes of different classes. They can be transformed by suppressing one class and connecting nodes with common neighbors. (C) Weighted directed network. In this type of network, each edge has an associated direction and a weight. The shortest path between two nodes can be identified by finding the path that minimizes the sum of weights. (D) Network propagation process. This process can be applied to different types of networks as a way to spread information across them. Created in BioRender. Gonzalez Gomez, C. (2025) https://BioRender.com/h78r633.

Figure 3

Unified representation of the stages in system biology-based connectivity scores. This schema is a unified representation that illustrates the common workflow stages in the studied methods as well as the methodological variations. Each line represents the specific path followed by each method, highlighting the similarities and differences between the approaches.