Human Nephrotoxicity Prediction Models for Three Types of Kidney Injury Based on Data Sets of Pharmacological Compounds and Their Metabolites

Abstract

The kidney is the most important organ for the excretion of pharmaceuticals and their metabolites. Among the complex structures of the kidney, the proximal tubule and renal interstitium are major targets of nephrotoxins. Despite its importance, there are only a few in silico models for predicting human nephrotoxicity for drug candidates. Here, we present quantitative structure-activity relationship (QSAR) models for three common patterns of drug-induced kidney injury, i.e., tubular necrosis, interstitial nephritis, and tubulo-interstitial nephritis. A support vector machine (SVM) was used to build the binary classification models of nephrotoxin versus non-nephrotoxin with eight fingerprint descriptors. To build the models, we constructed two types of data sets, i.e., parent compounds of pharmaceuticals (251 nephrotoxins and 387 non-nephrotoxins) and their major urinary metabolites (307 nephrotoxins and 233 non-nephrotoxins). Information on the nephrotoxicity of the pharmaceuticals was taken from clinical trial and postmarketing safety data. Though the mechanisms of nephrotoxicity are very complex, by using the metabolite information, the predictive accuracies of the best models for each type of kidney injury were better than 83% for external validation sets. Software to predict nephrotoxicity is freely available from our Web site at http://bmdrc.org/DemoDownload .

A critical review of adverse effects to the kidney: mechanisms, data sources, andin silicotools to assist prediction

“…As noted above, as part of the hazard identification process it is important to be able to predict accurately human nephrotoxicity. The traditional approach for determining safety and toxicity of drug candidates is through histopathological observation from in vivo animal studies [42,[250][251][252] or, more recently, from targeted in vitro testing. However, in recent decades, alternative methods for hazard assessment without the need for testing, such as in silico approaches, have been increasingly applied, particularly for the prioritisation of data requirements and identification of chemicals that may require more detailed risk assessment.…”

“…(Q)SAR models developed so far for nephrotoxicity, specifically, are summarised in Table 3 with details on the exact endpoint, number and type of molecules the model is based on, the method used, results, as well as strengths and weaknesses of the approach below. More detailed information on these QSAR models are provided in Appendix C [87,99,252,[262][263][264][265][266][267][268][269][270][271][272][273][274][275][276] of the supplementary information. It is also noted that QSAR models have been developed to predict renal clearance, which were examined in more detail elsewhere [56].…”

“…A mechanistic understanding of intrarenal oxygen transport and consumption may be a valuable component to add to a toxicokinetics related kidney model as renal tissue hypoxia has been argued to drive kidney disease [289,290]. Overall, there are limited computational toxicity methods available for more complex endpoints such as nephrotoxicity -likely to be due to the highly complex mechanisms of toxicity [250,252,262] or limitations of the availability of structured, high quality data. inter-individual variability.…”

In silico assessment of adverse drug reactions and associated mechanisms

“…A c c e p t e d M a n u s c r i p t the initial drugs themselves significantly improves the accuracy of predictive models for renal ADRs [95]. Third, datasets for many ADRs are unbalanced (i.e.…”

Nephrotoxicity assessment of the hydroethanolic leaf extract of Ziziphus mauritiana LAM (Rhamnaceae) in mammalians.

“…Metabolites derived drugs excreted by kidney can cause cellular damage by disrupting its functioning (Sands and Verlande., 2010). The proximal tubule and renal interstitium are the major targets of nephrotic substances (Lee and al.,2013). In advanced renal degradation, disturbances appear in mineral metabolism and bone structure (Muschio and Oldri., 2000).…”