Chemogenomic model identifies synergistic drug combinations robust to the pathogen microenvironment

Abstract

Antibiotics need to be effective in diverse environments in vivo. However, the pathogen microenvironment can have a significant impact on antibiotic potency. Further, antibiotics are increasingly used in combinations to combat resistance, yet, the effect of microenvironments on drug-combination efficacy is unknown. To exhaustively explore the impact of diverse microenvironments on drug-combinations, here we develop a computational framework-Metabolism And GENomics-based Tailoring of Antibiotic regimens (MAGENTA). MAGENTA uses chemogenomic profiles of individual drugs and metabolic perturbations to predict synergistic or antagonistic drug-interactions in different microenvironments. We uncovered antibiotic combinations with robust synergy across nine distinct environments against both E. coli and A. baumannii by searching through 2556 drug-combinations of 72 drugs. MAGENTA also accurately predicted the change in efficacy of bacteriostatic and bactericidal drug-combinations during growth in glycerol media, which we confirmed experimentally in both microbes. Our approach identified genes in glycolysis and glyoxylate pathway as top predictors of synergy and antagonism respectively. Our systems approach enables tailoring of antibiotic therapies based on the pathogen microenvironment.

Fig 1. Antibiotic interactions change significantly in different growth environments.

(a) Heat maps represent all pairwise interactions among 8 antibiotics in rich media (LB) and minimal media supplemented with glucose. Blue, white or red boxes correspond to synergistic, additive or antagonistic pairs. All drug combinations on average showed a significant shift towards synergy in glucose media. This was strongly pronounced for combinations involving both bactericidal and bacteriostatic drugs. The average interaction score for each class of drug combinations is shown in the table. (b) Scatter plot comparison of interaction scores in rich media versus glucose minimal media. The log transformed FIC interaction score is shown. While there is a significant correlation between interaction scores in the different media conditions, there are salient differences. Outlier combinations that have divergent outcomes in each condition are highlighted. For example, ampicillin is synergistic with azithromycin only in minimal media.

Fig 2. Predicting multi-drug combinations using MAGENTA.

(a) Schematic workflow of MAGENTA approach. MAGENTA takes drug chemogenomic profiles and interactions among drugs as input. This is used to train a Random Forest Model which can predict synergy and antagonism among pair-wise or higher-order combinations of new drugs given their chemogenomic profiles. (b) All three-way interactions among 8 antibiotics are represented as 3D heat-map. Blue, white or red boxes correspond to synergistic, additive or antagonistic three-way combinations. Among 56 combinations, only Azi+Min+Rif and Min+Cip+Rif exhibit strong synergy. The three-way interactions among 8 antibiotics are also represented as layers for maximum visibility. The dotted lines depict the interaction between nitrofurantoin, minocycline and chloramphenicol. (c) Scatter plot comparison of MAGENTA 3-way interaction predictions and experimental measurements demonstrate that MAGENTA can robustly identify 3-way antibiotic synergy and antagonism (rank correlation R = 0.57, p = 5 x10^-6).

Fig 3. Predicting impact of novel metabolic environments on drug interactions using MAGENTA.

(a) Schematic workflow of MAGENTA approach. MAGENTA takes drug chemogenomic profiles and interactions among drugs or between drugs and metabolic conditions as input. This is used to train a Random Forest model which can predict synergy and antagonism among pair-wise or higher-order combinations of new drugs in novel metabolic conditions given their chemogenomic profiles. (b) All pairwise interactions among 11 antibiotics in minimal media supplemented with glycerol are represented as a heat map. Blue, white or red boxes correspond to synergistic, additive or antagonistic combinations. Clustering of interaction scores was done using Euclidean distance and average linkage (Unweighted average distance (UPGMA)). (c) Scatter plot comparison of MAGENTA predictions and experimental measurements in glycerol minimal media demonstrate that MAGENTA can robustly predict antibiotic synergy and antagonism in new environments (rank correlation R = 0.69, p = 1x10^-8).

Fig 4. Predicting the impact of metabolic environments on drug interactions in A. baumannii using MAGENTA.

(a) Schematic workflow of the approach for predicting interactions in a new bacterial strain using E. coli drug interaction and chemogenomics data. Genes that are common between E. coli and A. baumannii are overlaid onto the E. coli MAGENTA model. The non-orthologous genes were deleted (i.e. they were set to be zero) and interaction outcomes were predicted using the conserved orthologous genes alone. (b) All pairwise interactions among 6 antibiotics in three media conditions for A. baumannii are shown as heat maps. Blue, white or red boxes correspond to synergistic, additive or antagonistic combinations. (c) Comparison of the interaction scores for each drug combination in three media conditions identified combinations that are sensitive to the environment. For example, ampicillin-tetracycline combination is synergistic, additive and antagonistic in glucose, LB and glycerol environment, respectively. (d) Scatter plot comparison of media specific interaction scores predicted by MAGENTA and experimental measurements demonstrate that MAGENTA can robustly predict antibiotic synergy and antagonism in various environments for a new species using E. coli data (Rank correlation R = 0.57, p = 5x10^-5).

Fig 5. The drug-drug interaction landscape.

(a) The heat maps show the predicted impact of 9 distinct metabolic environments on the interaction outcomes of 2556 pairwise drug combinations (synergy (blue), antagonism (red)). The drug combinations and metabolic conditions are clustered based on similarity (Euclidean distance) and the dendrogram was plotted based on average linkage. Panel b shows the corresponding interaction scores for A. baumannii.