Pioneering topological methods for network-based drug-target prediction by exploiting a brain-network self-organization theory

Abstract

The bipartite network representation of the drug-target interactions (DTIs) in a biosystem enhances understanding of the drugs' multifaceted action modes, suggests therapeutic switching for approved drugs and unveils possible side effects. As experimental testing of DTIs is costly and time-consuming, computational predictors are of great aid. Here, for the first time, state-of-the-art DTI supervised predictors custom-made in network biology were compared-using standard and innovative validation frameworks-with unsupervised pure topological-based models designed for general-purpose link prediction in bipartite networks. Surprisingly, our results show that the bipartite topology alone, if adequately exploited by means of the recently proposed local-community-paradigm (LCP) theory-initially detected in brain-network topological self-organization and afterwards generalized to any complex network-is able to suggest highly reliable predictions, with comparable performance with the state-of-the-art-supervised methods that exploit additional (non-topological, for instance biochemical) DTI knowledge. Furthermore, a detailed analysis of the novel predictions revealed that each class of methods prioritizes distinct true interactions; hence, combining methodologies based on diverse principles represents a promising strategy to improve drug-target discovery. To conclude, this study promotes the power of bio-inspired computing, demonstrating that simple unsupervised rules inspired by principles of topological self-organization and adaptiveness arising during learning in living intelligent systems (like the brain) can efficiently equal perform complicated algorithms based on advanced, supervised and knowledge-based engineering.

Figure 1

CNs and quadrangular closure in bipartite networks. (A) A bipartite network of targets (t, dark green squares) and drugs (d, red circles) and its equivalent matrix representation. (B) Four CNs (white nodes) together with three LCLs (white links) as defined by Daminelli et al. [30] are used to calculate the interaction likelihood of the two seed nodes d_z and t_y (black nodes) of the existing link d_z-t_y (left). Similarly, five CNs and five LCLs are used to predict the likelihood of the missing d_x-t_y interaction (right) .

Figure 2

Existing and removal re-prediction evaluation frameworks. (A) Existing link evaluation framework. Every possible link (black and white squares) is left out one time and re-predicted (B) Removal and re-prediction evaluation framework. Ten percent of the network (gray squares) are randomly removed and re-predicted.

Figure 3

Performance comparison in the existing links evaluation framework. Normalized AUPR values considering all existing links as TP as described in Figure 2A. On the left (A, C, E, G and I), comparison of three types of unsupervised methods: LCP-based, projection-based and MF-based. On the right (B, D, F, and H), comparison of three types of supervised: BLM, GRMF and wGRMF with unsupervised LCP-based methods.

Figure 4

Performance comparison in the removal and re-prediction evaluation framework. Median of normalized AUPR values (over 100 repetitions) from the removal and re-prediction evaluation framework described in Figure 1D. On the left (A, C, E, G and I), comparison of three types of unsupervised methods: LCP-based, projection-based and MF-based. On the right (B, D, F and H), comparison of three types of supervised methods: BLM, GRMF and wGRMF with unsupervised LCP-based methods.

Figure 5

Performance comparison in the independent validation evaluation framework. Normalized AUPR values considering the independent validation evaluation framework as described in the ‘Methods’ section. On the left (A, C, E, G and I), comparison of three types of unsupervised methods: LCP-based, projection-based and MF-based. On the right (B, D, F and H), comparison of three types of supervised methods: BLM, GRMF and wGRMF with unsupervised LCP-based methods.

Figure 6

Precision–recall curves of the independent validation evaluation framework. For each class of prediction methods, the best method in enzymes and NR network was compared with the best LCP-based method: LCP-based (red), BLM (yellow) and wGRMF (green). (A) Precision–recall curves in enzyme network, LCP-based (CJC) versus BLM (BLMdt). (B) Precision–recall curves in NR network, LCP-based (CJC) versus wGRMF (wGRMFd).

Figure 7

Mean position ranking on drug–target prediction across all networks within the three evaluation frameworks. Mean position for each method in each evaluation framework over all networks. Each bar in the plot is ordered from the best (left) to the worst (right) method. On the left (A, C and E), comparison of three types of unsupervised methods: LCP-based, projection-based and MF-based. On the right (B, D and F), comparison of three types of supervised methods: BLM, GRMF and wGRMF with unsupervised LCP-based methods. The arrows point the methods selected for the comparison of drug–target prioritization in the first percentile.

Figure 8

Statistical comparison for the classes of supervised and unsupervised methods. P-values computed by the non-parametric Mann–Whitney test and adjusted by Bonferroni’s correction for the classes of supervised and unsupervised methods in the three evaluation frameworks. Significant differences between classes of methods are highlighted in blue. On the left, comparison between three types of unsupervised methods: LCP-based, projection-based and MF-based. On the right, comparison of three types of supervised methods: BLM, GRMF and wGRMF with unsupervised LCP-based methods.

Figure 9

Comparison of novel predicted interactions. (A) Overlap of the first percentile predictions in five networks for unsupervised methods, considering the representative method of each class: MFb (MF-based), Jac (projection-based) and CJC (LCP-based). (B) Overlap of the nodes (drugs and targets) involved in the first percentile predictions for the unsupervised methods. (C) Overlap of the first percentile predictions in four networks for supervised and LCP-based methods, considering the representative method of each class: BLMd (supervised), GRMFdt (supervised) and CJC (LCP-based). (D) Overlap of the nodes (drugs and targets) involved in the first percentile predictions for the previous methods.

Figure 10

Comparison of computational time between supervised and LCP-based methods. Comparison of computational time on supervised and LCP-based methods for one simulation attempt. (A) Enzyme network, (B) ion channel network, (C) GPCR network, (D) NR network.