In Silico Approaches: Advancing Safety Prediction of Chemicals and Drugs

An unprecedented increase in the number of synthesized chemicals has created a significant hurdle to rapidly screen and accurately assess their potential adverse biological effects, mainly due to the enormous costs and lengthy time-consuming nature of in vivo and in vitro toxicity testing. Conversely, in silico predictive toxicology techniques offer a swift and cost-efficient alternative or supplement to in vivo/in vitro testing for predicting the toxicity of chemical compounds. As a result, in silico toxicology plays a vital role in estimating the safety/toxicity of chemicals, as well as in the drug discovery and development process. Consequently, the capability and applicability of in silico approaches in predicting safety/toxicity continue to increase.

The aim of this Research Topic is to focus on the most recent scientific contributions regarding various aspects of computational approaches used to predict safety/toxicity and prioritize chemicals and drugs in order to minimize adverse effects. Authors are welcome to submit the following article types: General Commentary, Hypothesis and Theory, Methods, Mini Review, Opinion, Original Research, Perspective, and Review, which cover, but are not limited to, the following themes:

• Various in silico techniques, including traditional and machine learning/artificial intelligence-based approaches
• Various safety/toxicity endpoints of chemicals/drugs
• Applications of novel machine learning/artificial intelligence techniques, such as ChatGPT, for computationally assessing toxicity or elucidating toxic mechanisms
• Implementation of novel programming languages, such as "mojo," for computational toxicity
• Novel packages/strategies that can be utilized to predict toxicity
• Other related issues