![Dataverify](static/images/logo.png?v1.0.190828)
- Home
- Industry Solutions
- Services
- Support
- About Us
The liver plays a crucial role in metabolism and is highly susceptible to xenobiotics. Drug-induced hepatotoxicity may involve a variety of different liver injuries, some of which can lead to organ failure and ultimately death. Drug-induced liver injury (DILI) is one of the main causes of drug failure in clinical trials, which seriously hinders the development of new drugs. Early assessment of the DILI risk of drug candidates is considered an effective strategy to reduce the rate of drug discovery depletion. However, successful prediction of DILI is still a great challenge due to the severe lack of methods to predict liver toxicity from chemical structure. Therefore, it is urgent to develop effective methods for predicting hepatotoxicity. In recent years, a large number of in silico methods to predict hepatotoxicity have been reported and achieved satisfactory performance. Based on the advanced AI-assisted platform, Creative Biolabs can accurately predict the ADMET properties and help customers accelerate the drug screening process and reduce R&D costs.
Fig.1 Concept map of drug-induced liver injury (DILI) modeling process. (Wang, et al., 2019)
As the first organ to come into contact with the majority of digestive products, the liver is particularly susceptible to the effects of xenobiotics, such as drugs and environmental chemicals. The key function of the liver in the metabolism and disposal of nutrients and other substances is directly connected to this tendency for damage. The liver is frequently where xenobiotics and their metabolites are concentrated, and on occasion, these concentrations can be toxic, leading to a variety of acute and long-term hepatocellular injuries, cholestatic injuries, neoplasia, and high hepatobiliary enzyme levels. Hepatotoxicity remains one of the most expensive and dangerous forms of toxicity encountered during the drug development cycle. Evidence of liver injury has led to the discontinuation of numerous clinical studies. The most common causes of acute liver failure nowadays are drug-induced hepatotoxicity, which frequently results in patient death or the urgent need for a liver transplant. There is no doubting that liver toxicity is a significant issue in both pharmaceutical and environmental research, and there is no question as to the value of a model that could provide accurate in silico predictions of hepatotoxicity.
The traditional detection of drug hepatotoxicity is carried out by experiment. However, there is no denying that many experimental methods are laborious and time-consuming. In addition, most drug-induced hepatotoxicity is specific in nature and usually cannot be determined by the animal/cytotoxicity tests required by regulation. Compared with the experimental detection of hepatotoxicity, the prediction of hepatotoxicity risk by in silico model is less time and cost, which is considered to be an effective method to evaluate the potential hepatotoxicity risk of drug candidates. The statistics-based and expert-based methods are the two main methods of in silico approaches. Statistical-based approaches often make an effort to link the results of DILI with molecular descriptors or molecular fingerprints using machine learning techniques. The initial step in developing expert-based models is almost usually the extraction of structural alerts. The researcher's knowledge of the toxicological mechanisms was then used to define relationships between the structural alerts and the biological activity. The prediction of hepatotoxicity has greatly benefited from the application of several machine learning techniques, particularly the QSAR model, which has been employed extensively in the study of liver toxicity.
Fig.2 Machine learning for Predicting Drug-Induced Hepatotoxicity. (He, et al., 2019)
As a reliable partner to the world's leading pharmaceutical companies and research institutions, Creative Biolabs brings together the market-leading in silico expertise to build our AI-assisted platform that can provide custom professional drug-induced hepatotoxicity prediction.
References