Artificial intelligence and real-world data for drug and food safety - A regulatory science perspective.

In 2013, the Global Coalition for Regulatory Science Research (GCRSR) was established with members from over ten countries (www.gcrsr.net). One of the main objectives of GCRSR is to facilitate communication among global regulators on the rise of new technologies with regulatory applications through the annual conference Global Summit on Regulatory Science (GSRS). The 11th annual GSRS conference (GSRS21) focused on "Regulatory Sciences for Food/Drug Safety with Real-World Data (RWD) and Artificial Intelligence (AI)." The conference discussed current advancements in both AI and RWD approaches with a specific emphasis on how they impact regulatory sciences and how regulatory agencies across the globe are pursuing the adaptation and oversight of these technologies. There were presentations from Brazil, Canada, India, Italy, Japan, Germany, Switzerland, Singapore, the United Kingdom, and the United States. These presentations highlighted how various agencies are moving forward with these technologies by either improving the agencies' operation and/or preparing regulatory mechanisms to approve the products containing these innovations. To increase the content and discussion, the GSRS21 hosted two debate sessions on the question of "Is Regulatory Science Ready for AI?" and a workshop to showcase the analytical data tools that global regulatory agencies have been using and/or plan to apply to regulatory science. Several key topics were highlighted and discussed during the conference, such as the capabilities of AI and RWD to assist regulatory science policies for drug and food safety, the readiness of AI and data science to provide solutions for regulatory science. Discussions highlighted the need for a constant effort to evaluate emerging technologies for fit-for-purpose regulatory applications. The annual GSRS conferences offer a unique platform to facilitate discussion and collaboration across regulatory agencies, modernizing regulatory approaches, and harmonizing efforts.

Quantitative analyses of misclassification rates in the hazard classification of environmental chemicals: Evaluation of procedures for deriving predicted no-effect concentrations in the Chemical Substance Control Law in Japan.

The quality of chemical management depends more or less on practical procedures used to assess chemicals. This study quantitatively assessed the efficacy of a derivation procedure for calculating no-effect concentrations for screening assessment of environmental hazards under the Chemical Substance Control Law in Japan. We first evaluated the derivation procedure by applying a series of test ecotoxicity datasets to the procedure and calculating the resulting misclassification rates of the hazardous class of chemicals. In this study, a chemical was deemed to have been misclassified if its classification differed from its classification based on the full dataset (chronic toxicity data for three trophic levels), which was defined as the correct assignment. We also calculated the effects of additional uncertainty factors to decrease the variance (i.e., to improve the consistency) of the misclassification rates among cases with different data availability in the derivation procedure. The results showed that the derivation procedure resulted in very high rates of misclassification when only particular sets of ecotoxicity data were available (e.g., only chronic toxicity data of algae were available). Our analyses also showed that the use of additional uncertainty factors improved the consistency of the misclassification rates within the derivation procedure. Our study presents a broadly applicable calculation framework for quantifying error rates in assessment procedures and serves as a case study for future development and reforms of chemical assessment processes and policies, while additional analyses using more extensive ecotoxicity data with various modes of actions are needed in the future.

Aquatic toxicity (Pre)screening strategy for structurally diverse chemicals: global or local classification tree models?

With an ever-increasing number of synthetic chemicals being manufactured, it is unrealistic to expect that they will all be subjected to comprehensive and effective risk assessment. A shift from conventional animal testing to computer-aided methods is therefore an important step towards advancing the environmental risk assessments of chemicals. The aims of this study are two-fold: firstly, it examines the relationships between structural and physicochemical features of a diverse set of organic chemicals, and their acute aquatic toxicity towards Daphnia magna and Oryzias latipes using a classification tree approach. Secondly, it compares the efficiency and accuracy of the predictions of two modeling schemes: local models that are inherently restricted to a smaller subset of structurally-related substances, and a global model that covers a wider chemical space and a number of modes of toxic action. The classification tree-based models differentiate the organic chemicals into either 'highly toxic' or 'low to non-toxic' classes, based on internal and external validation criteria. These mechanistically-driven models, which demonstrate good performance, reveal that the key factors driving acute aquatic toxicity are lipophilicity, electrophilic reactivity, molecular polarizability and size. A comparative analysis of the performance of the two modeling schemes indicates that the local models, trained on homogeneous data sets, are less error prone, and therefore superior to the global model. Although the global models showed worse performance metrics compared to the local ones, their applicability domain is much wider, thereby significantly increasing their usefulness in practical applications for regulatory purposes. This demonstrates their advantage over local models and shows they are an invaluable tool for modeling heterogeneous chemical data sets.

Generating accurate in silico predictions of acute aquatic toxicity for a range of organic chemicals: Towards similarity-based machine learning methods.

There has been an increase in the use of non-animal approaches, such as in silico and/or in vitro methods, for assessing the risks of hazardous chemicals. A number of machine learning algorithms link molecular descriptors that interpret chemical structural properties with their biological activity. These computer-aided methods encounter several challenges, the most significant being the heterogeneity of datasets; more efficient and inclusive computational methods that are able to process large and heterogeneous chemical datasets are needed. In this context, this study verifies the utility of similarity-based machine learning methods in predicting the acute aquatic toxicity of diverse organic chemicals on Daphnia magna and Oryzias latipes. Two similarity-based methods were tested that employ a limited training dataset, most similar to a given fitting point, instead of using the entire dataset that encompasses a wide range of chemicals. The kernel-weighted local polynomial approach had a number of advantages over the distance-weighted k-nearest neighbor (k-NN) algorithm. The results highlight the importance of lipophilicity, electrophilic reactivity, molecular polarizability, and size in determining acute toxicity. The rigorous model validation ensures that this approach is an important tool for estimating toxicity in new or untested chemicals.

Application of a kinetic energy partitioning scheme for ab initio molecular dynamics to reactions associated with ionization in water tetramers.

We analyze the short-time dynamics of 'cyclic' and 'branched' water tetramers after an ionization event, with the aid of a scheme that partitions the kinetic energy of a solute plus solvent system into separate solute and solvent (or bath) contributions, using instantaneous internal coordinates and atomic velocities. The analysis supports the partitioning of the tetrameric systems into two subsystems, a 'reactive trimer' and a 'solvent' molecule. The partitioned kinetic energy exhibits two features, a broad peak assigned to the interaction between the two sub-systems and a sharper peak arising from the proton transfer that occurs upon ionization. It is found that the stability of the hydroxyl radical formed upon ionization is sensitive to the configuration of the water molecules around the ionized water at the moment of the ionization event.