Drug target prediction and repositioning using an integrated network-based approach

Abstract

The discovery of novel drug targets is a significant challenge in drug development. Although the human genome comprises approximately 30,000 genes, proteins encoded by fewer than 400 are used as drug targets in the treatment of diseases. Therefore, novel drug targets are extremely valuable as the source for first in class drugs. On the other hand, many of the currently known drug targets are functionally pleiotropic and involved in multiple pathologies. Several of them are exploited for treating multiple diseases, which highlights the need for methods to reliably reposition drug targets to new indications. Network-based methods have been successfully applied to prioritize novel disease-associated genes. In recent years, several such algorithms have been developed, some focusing on local network properties only, and others taking the complete network topology into account. Common to all approaches is the understanding that novel disease-associated candidates are in close overall proximity to known disease genes. However, the relevance of these methods to the prediction of novel drug targets has not yet been assessed. Here, we present a network-based approach for the prediction of drug targets for a given disease. The method allows both repositioning drug targets known for other diseases to the given disease and the prediction of unexploited drug targets which are not used for treatment of any disease. Our approach takes as input a disease gene expression signature and a high-quality interaction network and outputs a prioritized list of drug targets. We demonstrate the high performance of our method and highlight the usefulness of the predictions in three case studies. We present novel drug targets for scleroderma and different types of cancer with their underlying biological processes. Furthermore, we demonstrate the ability of our method to identify non-suspected repositioning candidates using diabetes type 1 as an example.

Figure 1. Overview of the workflow.

The analysis starts with a set of microarray samples from diseased and healthy donors, which is statistically processed to identify differentially expressed genes (DEGs). Furthermore, a high-quality interaction network serves as input to the analysis. The DEGs are overlaid onto the network and serve as input to the four network analysis methods, namely Neighborhood Scoring, Interconnectivity, Network Propagation, and Random Walk. The output of the methods is aggregated using a logistic regression model, which is trained on a set of drug targets from Integrity, resulting in the final ranked list of prioritized gene products.

Figure 2. Consensus method performance.

(A) The plot shows the median AUC for each disease model. The highest AUC of 93.19% is achieved for hyperplastic polyposis syndrome and the lowest for ischemic stroke with 63.27%. (B) and (C) show the ROC curves for hyperplastic polyposis syndrome and periodontitis, which achieved the highest performance. The blue areas around the AUC curves represent the 95% confidence intervals.

Figure 3. Analysis of top 100 drug target predictions.

Blue represents the number of known drug targets for the disease. Drug targets that are currently not used to treat any disease are shown in red. The remainder represents drug targets that are used to treat other indications (highlighted by a black box). These drug targets are grouped into approved drugs, late stage clinical phases, early clinical phases, and biological testing.

Figure 4. Clustering of 14 diseases.

The clustering based on the gene expression signatures is shown on the left and the clustering based on the top 100 drug target predictions to the right. Cancer-related clusters are highlighted in blue and the placement of AIDS in the two clusterings is highlighted in red.

Figure 5. Network reconstruction for STAT1 signaling in scleroderma.

TLR signaling is activated by STAT1, which in turn activates IFN signaling, resulting in increased STAT1 activity. Predicted drug targets (within the top 100) for scleroderma are highlighted with colored stars, where the numbers correspond to the rank in the drug target predictions. Cyan stars represent known drug targets for scleroderma. Purple stars correspond to drug targets that have been associated with other diseases and can be readily repositioned to the treatment of scleroderma, while yellow stars indicate unexploited drug targets that can be used for the development of novel treatment strategies. Red thermometers show significantly up-regulated genes in scleroderma, blue thermometers show down-regulated genes. Green arrows correspond to activation edges, red arrows represent inhibition edges.

Figure 6. Core network of predicted drug targets in cancers.

(A) shows the commonly predicted drug targets (within the top 100 predictions) for colorectal cancer, thyroid cancer, ovarian cancer, melanoma, acute myeloid leukemia, and hepatocellular carcinoma. Yellow stars represent known disease biomarkers for neoplasms obtained from the Metabase resource. Cyan stars highlight genes that are known drug targets for at least one of the six types of cancer. (B) shows diseases that are significantly associated with the predicted drug targets. The diseases are ordered by the percentage of genes they cover. Neoplasms are found to cover all of the predicted drug targets. (C) shows the most enriched KEGG pathways for the predicted drug targets . Cancer-related pathways are most enriched followed by pathways for specific cancers as well as cancer-related signaling pathways.

Figure 7. Network reconstruction for c-Myc as a common drug target in different cancers.

The blue, green and magenta boxes show uniquely up-regulated genes that were predicted as drug targets (within the top 100 predictions) for the indicated cancer type and that contribute to the regulation of cell proliferation. c-Myc (in the middle) is the top drug target prediction for all three cancer types and is involved in the regulation of cell proliferation as well. Downstream targets of c-Myc are shown in the gray box below c-Myc and are uniformly up-regulated in all three cancer types. Cyan stars represent known drug targets for the respective cancer type. Purple stars correspond to drug targets that have been associated with other diseases and can be readily repositioned to the treatment of this type of cancer, while yellow stars indicate unexploited drug targets that can be used for the development of novel treatment strategies. Red thermometers show significantly up-regulated genes in (1) Thyroid Cancer, (2) Colon Cancer, and (3) Melanoma.

Figure 8. Network reconstruction for COX-2 as repositioning candidate for diabetes type 1 therapy.

Over-expression of COX-2 in monocytes leads to an increased production of prostaglandin E2. Prostaglandin E2 activates T-cell signaling through the PGE2 receptor resulting in increased cAMP levels and activation of the transcription factors CREB1 and CREM. cAMP inactivates the IL-2 receptor of T-cells, while CREM acts as repressor for IL-2. The inhibition of IL-2 and the IL-2 receptor result in immune regulation dysfunction leading to autoimmunity and ultimately the death of beta-cells, which is the cause of diabetes type 1. Predicted drug targets (within the top 100) for diabetes are highlighted with colored stars, where the numbers correspond to the rank in the drug target predictions. Purple stars correspond to drug targets that have been associated with other diseases and can be readily repositioned to the treatment of diabetes type 1. Red thermometers show significantly up-regulated genes in diabetes type 1. Green arrows correspond to activation edges, red arrows represent inhibition edges.