Toxicity prediction based on artificial intelligence: A multidisciplinary overview

Abstract

The use and production of chemical compounds are subjected to strong legislative pressure. Chemical toxicity and adverse effects derived from exposure to chemicals are key regulatory aspects for a multitude of industries, such as chemical, pharmaceutical, or food, due to direct harm to humans, animals, plants, or the environment. Simultaneously, there are growing demands on the authorities to replace traditional in vivo toxicity tests carried out on laboratory animals (e.g., European Union REACH/3R principles, Tox21 and ToxCast by the U.S. government, etc.) with in silica computational models. This is not only for ethical aspects, but also because of its greater economic and time efficiency, as well as more recently because of their superior reliability and robustness than in vivo tests, mainly since the entry into the scene of artificial intelligence (AI)‐based models, promoting and setting the necessary requirements that these new in silico methodologies must meet. This review offers a multidisciplinary overview of the state of the art in the application of AI‐based methodologies for the fulfillment of regulatory‐related toxicological issues. This article is categorized under: Data Science > Chemoinformatics Data Science > Artificial Intelligence/Machine Learning

Alternative Plasticizers As Emerging Global Environmental and Health Threat: Another Regrettable Substitution?

“…68 Preventing regrettable substitutions is a considerable challenge for scientists globally. Green chemistry, 69,70 and intelligent toxicology 71,72 can provide a safe way forward as elaborated in a proposed general framework to avoid regrettable substitutions in Figure 2. Green chemistry can enable the design and production of least toxic/safe alternative chemicals based on 12 green principles, 70 thus eliminating hazardous waste.…”

“…Green chemistry can enable the design and production of least toxic/safe alternative chemicals based on 12 green principles, 70 thus eliminating hazardous waste. Emerging intelligent toxicological tools can provide critical information (e.g., AI-based computational tools), 71 from chemical toxicity to environmental hazards at early stages of development. It is not only efficient in reducing incidence of regrettable substitution but will also result in greater economic advantage and time efficiency.…”

Multi-Strategy Assessment of Different Uses of QSAR under REACH Analysis of Alternatives to Advance Information Transparency

“…Thus, if ECHA wanted to confirm QSAR predictions or research any QSAR evidence based on the predictions, not only would they be unable to find this information in the AoA, other applicants who share information may replicate the same error, further lowering the quality of AoA. At the same time, approaches to addressing uncertainty need to be inclusive of forward-thinking regulatory use of QSARs not necessarily addressed in the OECD principles in addition to initiatives around state-of-the-art A.I.-based QSAR models [ 72 , 73 ].…”

The review of food safety inspection system based on artificial intelligence, image processing, and robotic

“…Today, a wide range of inspections have been proposed in which microbiological and chemical analyses have been introduced to assess the safety or quality of food products and raw materials. FS relies on regulatory sampling regimes and inspections (Pérez Santín et al, 2021). In fact, the FS management system, although mainly based on the good design of processes, products, and procedures, is the final product test, is considered a measure of production process control (see Figure 2).…”