ToxAIcology - The evolving role of artificial intelligence in advancing toxicology and modernizing regulatory science

Abstract

Diamandis (1961-) "I summarize it like this: There will be two kinds of companies at the end of this decade... Those that are fully utilizing AI, and those that are out of".The convergence of increased computational power, availability of large datasets, and improvements in machine learning algorithms have driven tremendous advances in AI over the past decade (Esteva et al., 2019). In the life sciences, AI holds great potential to transform areas like medical diagnosis, drug discovery, genetics, clinical decision support, and toxicology research (Hamet and Tremblay, 2017). AI methods are well suited to analyze large and complex biological datasets, enhance the precision and speed of medical diagnosis and treatment, expedite drug IntroductionArtificial intelligence (AI) refers to simulation of human intelligence in machines, enabling systems to perform tasks commonly thought to require human cognition and decision-making abilities. My own definition is simpler: AI makes Big Sense from Big Data. AI is a rapidly progressing field that is significantly impacting various domains including healthcare, transportation, finance, agriculture, education, and more. Elon Musk (1971-) summarized nicely "Companies have to race to build AI or they will be made uncompetitive. Essentially, if your competitor is racing to build AI, they will crush you.

Artificial intelligence (AI)—it’s the end of the tox as we know it (and I feel fine)*

“…AI has seen rapid advancements in recent years, driven by exponential growth in computing power, availability of large datasets, and improvements in machine learning algorithms. The field of toxicology is poised to benefit immensely from the integration of AI techniques (e.g., Luechtefeld and Hartung 2017 ; Idakwo et al 2018 ; Tang et al 2018 ; Baskin 2018 ; Luechtefeld et al 2018a , Bhhatarai et al 2019 ; Pu et al 2019 ; Mansouri et al 2021 ; Lin and Chou 2022 ; Jeong et al 2022 ; Sedykh et al 2022 ; Tuyet et al 2023 , Hartung 2023b , 2023c ).…”

“…Life scientists can leverage the power of AI to analyze vast and complex biological data sets, enhance the precision and speed of diagnosis, expedite drug discovery, personalize medicine, elucidate disease mechanisms, and much more in a truly transformative way for healthcare, 1 2 (Hartung 2023c ). AI is the ability of a digital computer or machine to perform tasks commonly associated with intelligent beings.…”

The Cost Outcome Pathway Framework: Integrating socio-economic impacts to Adverse Outcome Pathways

“…As the AOP construction could be very time-intensive to compile existing heterogeneous knowledge from structured- and non-structured data, innovative computational methods based on artificial intelligence (AI), and data mining technologies are well suited. AI allows to identify, extract, and compile relevant sparse information from the wealth of available open-source data, and can be used for predictive toxicology (e.g., Abstract Sifter 12 , the ComptoxAI tools 13,14 ) or others computational approaches 15 . Recently, AI and text-mining were used to develop AOP-helpFinder 16,17 , a tool to automatically identify, extract, and prioritize knowledge from the literature (PubMed) (https://aop-helpfinder.u-paris-sciences.fr/) 18 .…”

The pivotal role of artificial intelligence in enhancing experimental animal model research: A machine learning perspective

“…The application of AI in toxicity prediction aligns with advancements in data availability and algorithm capabilities. [ 18 ] Integrated AI approaches hold promise in transforming toxicology by predicting hazards for new chemical entities and reducing reliance on animal testing. Early rule-based expert systems evolved into statistical and machine-learning models such as Quantitative Structure Activity Relationship (QSAR).…”