Network-based prediction of drug combinations

Abstract

Drug combinations, offering increased therapeutic efficacy and reduced toxicity, play an important role in treating multiple complex diseases. Yet, our ability to identify and validate effective combinations is limited by a combinatorial explosion, driven by both the large number of drug pairs as well as dosage combinations. Here we propose a network-based methodology to identify clinically efficacious drug combinations for specific diseases. By quantifying the network-based relationship between drug targets and disease proteins in the human protein-protein interactome, we show the existence of six distinct classes of drug-drug-disease combinations. Relying on approved drug combinations for hypertension and cancer, we find that only one of the six classes correlates with therapeutic effects: if the targets of the drugs both hit disease module, but target separate neighborhoods. This finding allows us to identify and validate antihypertensive combinations, offering a generic, powerful network methodology to identify efficacious combination therapies in drug development.

Fig. 1

Network-based model of drug–drug relationship. a A subnetwork of the human interactome illustrating the network-based relationship between drug targets associated with three drugs (imatinib [I], tandutinib [T], and natalizumab [N]). b, c The definition of drug pairs that are topologically overlapping (s_AB < 0, b) or topologically separated (s_AB ≥ 0, c). d–j The interplay between topological separation of drug pairs and five types of drug profiles: drug–drug chemical similarity (d); drug target-encoding gene co-expression pattern across human tissues (e); drug target protein sequence similarity (f). Using the Gene Ontology (GO) annotations, we determine for each drug how similar its associated target-encoding genes are in terms of their biological processes (g), cellular component (h), and molecular function (i); and clinical similarity (j) of drug pairs derived from Anatomical Therapeutic Chemical Classification Systems codes (see Methods). Overlapping drug pairs are highlighted in orange (s_AB < 0); topologically separated drug pairs are highlighted in blue (s_AB ≥ 0)

Fig. 2

The efficacy of hypertensive drug–drug interactions. a–f Schematic diagrams of the six distinct classes capturing the network-based relationship between two drug–target modules and one disease module on a drug–drug–disease combination. For s_AB < 0, the two sets of drug targets overlap topologically (Fig. 1b); while for s_AB ≥ 0, the two sets of drug targets are separated topologically (Fig. 1c). The z-scores (z), measuring the drug–disease separation, are calculated for quantifying the significance of the shortest paths between drug targets and disease proteins in the human protein–protein interactome. For z < 0, the drug–target module and the disease module overlap; while for z ≥ 0, the drug–target module and the disease module are separated. Color histograms (Real) show the antihypertensive combinations (purple) and clinically reported adverse drug interactions on high blood pressure (blue), respectively. We assembled the antihypertensive combinations from three types of experimental evidences: (i) FDA-approved evidence, (ii) clinical data from Clinicaltrials.gov database, and (iii) preclinical studies from literature (Supplementary Data 3). We randomly selected the same number of adverse drug–drug interactions related to high blood pressure from 1512 clinically reported adverse drug–drug interactions (Supplementary Data 4) corresponding to the number of antihypertensive combinations using a bootstrapping algorithm in R software and this process was repeated 100 times (Supplementary Note 5). Gray boxes (Random) show random expectation. Error bars indicate the standard deviation. The P-value (P) is calculated by testing 10,000 permutations (Supplementary Note 5). The network-based relationships between two drug–target modules and one disease module for FDA-approved hypertensive drug combinations only are illustrated in Supplementary Fig. 11

Fig. 3

Network-based stratification of hypertensive drug combinations. a Heatmap showing the predicted network-based separation (s_AB) among 65 FDA-approved anti-hypertensive drugs. Drugs are clustered based on their target families. FDA-approved or experimentally validated drug combinations for the treatment of hypertension are highlighted by circles (o). Clinically reported adverse drug interactions are highlighted by X. Color keys are shown by s_AB. The right heatmap highlighting the four distinct classes capturing the network-based relationship (P1–P4, Fig. 2a–d) for 65 FDA-approved anti-hypertensive drugs on the hypertension disease module. b A network map showing the relationship between the drug–target modules and the hypertension disease module (the largest connected subgraph by red) in the human interactome. Complementary Exposure for two FDA-approved drug combinations (hydrochlorothiazide–amiloride and hydrochlorothiazide–spironolactone) are highlighted by blue and orange via blue arrow, respectively. Overlapping Exposure for two clinically reported adverse drug–drug interactions (diazoxide–hydrochlorothiazide and diazoxide–bendroflumethiazide) are also illustrated by red arrow. The target families of 65 FDA-approved anti-hypertensive drugs are highlighted by different colors in both (a) and (b). The edges in (b) denote the protein–protein interactions (PPIs) colored by different types of hypertensive drug target families or known hypertension disease proteins (genes)