In silico approaches in carcinogenicity hazard assessment: Current status and future needs

Tice, Raymond R.; Bassan, Arianna; Amberg, Alexander; Anger, Lennart T.; Beal, Marc A.; Bellion, Phillip; Benigni, Romualdo; Birmingham, J.; Brigo, Alessandro; Bringezu, Frank; Ceriani, Lidia; Crooks, Ian; Cross, Kevin P.; Elespuru, Rosalie K.; Faulkner, David; Fortin, Marie; Fowler, Paul; Frericks, Markus; Gerets, Helga; Jahnke, Gloria D.; Jones, David R.; Kruhlak, Naomi L.; Piparo, Elena Lo; López-Belmonte, Juan Luis; Luniwal, Amarjit; Luu, Alice; Madia, Federica; Manganelli, Serena; Manickam, Balasubramanian; Mestres, Jordi; Mihalchik-Burhans, Amy L.; Neilson, Louise; Pandiri, Arun R.; Pavan, Manuela; Rider, Cynthia; Rooney, John P.; Trejo‐Martin, Alejandra; Watanabe, Karen H.; White, Angela; Woolley, David; Myatt, Glenn J.

doi:10.1016/j.comtox.2021.100191

Cited by 27 publications

(19 citation statements)

References 251 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DeepCarc model performed better than other models, such as RF, k-NN, SVM, and XGB, using the test set, with an ACC of 75.4% and an average improvement rate of 37%. Details of other models are listed in Table and other helpful reviews. , …”

Section: Recent Advances In Ai-based Drug Toxicity Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Tran

Wibowo

Tayara

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

show abstract

Section: Recent Advances In Ai-based Drug Toxicity Predictionmentioning

confidence: 99%

“…Details of other models are listed in Table 5 and other helpful reviews. 129,136 2.6. Skin Sensitization Prediction.…”

Section: Carcinogenesis Predictionmentioning

confidence: 99%

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Tran

Wibowo

Tayara

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Smith et al ( 2016 ) analysed the biological effects of chemicals classified as known human carcinogens and deduced that they show one or more of 10 key characteristics (KCCs). Tice et al ( 2021 ) reviewed the KCCs with the intent of developing an integrated approach to testing and assessment (IATA) of carcinogenic potential using NAMs. Their conclusion was that the KCCs lack specificity for carcinogenicity as they are also involved in disease processes that are not related to cancer.…”

Section: Bringing Nams Into Carcinogenicity Assessmentmentioning

confidence: 99%

A new approach to the classification of carcinogenicity

et al. 2022

View full text Add to dashboard Cite

Concern over substances that may cause cancer has led to various classification schemes to recognize carcinogenic threats and provide a basis to manage those threats. The least useful schemes have a binary choice that declares a substance carcinogenic or not. This overly simplistic approach ignores the complexity of cancer causation by considering neither how the substance causes cancer, nor the potency of that mode of action. Consequently, substances are classified simply as “carcinogenic”, compromising the opportunity to properly manage these kinds of substances. It will likely be very difficult, if not impossible, to incorporate New Approach Methodologies (NAMs) into binary schemes. In this paper we propose a new approach cancer classification scheme that segregates substances by both mode of action and potency into three categories and, as a consequence, provides useful guidance in the regulation and management of substances with carcinogenic potential. Examples are given, including aflatoxin (category A), trichlorethylene (category B), and titanium dioxide (category C), which demonstrate the clear differentiation among these substances that generate appropriate levels of concern and management options.

show abstract

“…12−16 Typical examples are physicochemical properties like solubility and lipophilicity, 17,18 the activity of compounds on both on-and off-target proteins (e.g., hERG), 19,20 as well as more complex end points such as overall toxicity and carcinogenicity. 21,22 While physicochemical properties can generally be predicted using either mechanistic models or by machine learning, complex end point predictions typically rely on machine learning.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Small-Molecule Developability Using Large-Scale In Silico ADMET Models

Beckers,

Sturm,

Sirockin

et al. 2023

J. Med. Chem.

View full text Add to dashboard Cite

Early in silico assessment of the potential of a series of compounds to deliver a drug is one of the major challenges in computer-assisted drug design. The goal is to identify the right chemical series of compounds out of a large chemical space to then subsequently prioritize the molecules with the highest potential to become a drug. Although multiple approaches to assess compounds have been developed over decades, the quality of these predictors is often not good enough and compounds that agree with the respective estimates are not necessarily druglike. Here, we report a novel deep learning approach that leverages large-scale predictions of ∼100 ADMET assays to assess the potential of a compound to become a relevant drug candidate. The resulting score, which we termed bPK score, substantially outperforms previous approaches and showed strong discriminative performance on data sets where previous approaches did not.

show abstract

In silico approaches in carcinogenicity hazard assessment: Current status and future needs

Cited by 27 publications

References 251 publications

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

A new approach to the classification of carcinogenicity

Prediction of Small-Molecule Developability Using Large-Scale In Silico ADMET Models

Contact Info

Product

Resources

About