A broad range of computational models is available for animal-free chemical safety assessment. The models are used to predict a variety of endpoints, including adverse effects or apical endpoints, toxicokinetic properties, and exposure, often from chemical structure or in vitro inputs alone. To support their wider use, such models need to be findable, accessible, interoperable, and reusable (FAIR). This study has reevaluated the existing FAIR principles applied to quantitative structure-activity relationships (QSARs) in order to adapt these principles to a wider range of computational models. Despite the breadth and variety of approaches, many computational models comprise common components including the training series, information about the modelling engine, and the model itself. As a result, a refined set of four FAIR Lite principles is proposed based on the methodological foundations of computational toxicology which are unambiguously understood by practitioners such as developers and end-users. To this end, it is proposed that to comply with the original FAIR principles, a computational toxicology model should be associated with (i) a globally unique identifier for model citation; (ii) the capture and curation of the model; (iii) the metadata for the dependent and independent variables and, where possible, data; and (iv) storage in a searchable and interoperable platform. The FAIR Lite principles are mapped onto the original FAIR principles applied to QSARs, thereby demonstrating that a simpler checklist approach covers all aspects. Plain language summary Many types of computational models are used in animal-free chemical safety assessment. These are used to make predictions for numerous endpoints, primarily focusing on the hazardous properties of, or exposure to, a chemical substance. The models use information from chemical structures and/or properties, or other non-animal data as inputs. It is essential that the risk assessor or toxicologist can find and utilize the models with confidence. The previously developed findable, accessible, interoperable and reusable (FAIR) principles for computational models are a framework intended to ensure that models are accessible and stored appropriately. This investigation has refined the original FAIR principles applied to computational models to capture information for all types of modelling approaches that may be used in chemical safety assessment. The new principles, termed FAIR Lite, encapsulate the original principles in four criteria relating to identifiers, description of a model, its (meta)data, and storage

Amide bond synthesis is ranked as the second most important challenge in key green chemistry research areas identified by the ACS Green Chemistry Institute. While developing more sustainable amide bond forming reactions has been in focus, significantly less attention has been given to human toxicity and environmental aspects of the underlying amine and acid substrates and their corresponding coupled products, a potentially important contribution to the overall sustainability of the amide-bond-forming reactions. Here, we explore biocatalytic amide bond formation from a safer-and-more-sustainable-by-design perspective in which commercially available amines and acids as well as their corresponding amide products were evaluated in silico based on potential human toxicity and environmental fate and exposure. This in silico filtering resulted in a panel of 188 amine and 54 acid building blocks that could be classified as safe, referred to herein as “safechems”. To enable couplings of safechems, we generated a panel of robust and promiscuous ancestral ATP-dependent amide bond synthetases (ABS) using McbA from Marinactinospora thermotolerans SCSIO 00652 as a template. Ancestral ABS enzymes exhibited complementary specificities in the coupling of a representative safechem subset of 17 amines and 16 acids while showing an increased thermostability of up to 20 °C compared to the extant biocatalyst. Finally, the pool of safechems and their corresponding amides were evaluated by USEtox (the UNEP-SETAC toxicity model), analysing not only the intrinsic properties of the compounds but evaluating their complete impact pathway including fate, exposure and effects. The amides were in general predicted as more toxic compared to the starting acids and amines through non-additive effects, emphasising that focusing on the toxicity of the building blocks alone is not sufficient to strive towards low human and ecotoxicity impact. Pursuing a safer and more sustainable by design perspective in the implementation of safechems did not prevent us from generating an array of novel products with potentially potent applications as exemplified here by enzymatic synthesis of substructures that are part of drug candidates for e.g. cancer treatment. 

The rise of artificial intelligence (AI) based algorithms has gained a lot of interest in the pharmaceutical development field. Our study demonstrates utilization of traditional machine learning techniques such as random forest (RF), support-vector machine (SVM), extreme gradient boosting (XGBoost), deep neural network (DNN) as well as advanced deep learning techniques like gated recurrent unit-based DNN (GRU-DNN) and graph neural network (GNN), towards predicting human ether-á-go-go related gene (hERG) derived toxicity. Using the largest hERG dataset derived to date, we have utilized 203,853 and 87,366 compounds for training and testing the models, respectively. The results show that GNN, SVM, XGBoost, DNN, RF, and GRU-DNN all performed well, with validation set AUC ROC scores equals 0.96, 0.95, 0.95, 0.94, 0.94 and 0.94, respectively. The GNN was found to be the top performing model based on predictive power and generalizability. The GNN technique is free of any feature engineering steps while having a minimal human intervention. The GNN approach may serve as a basis for comprehensive automation in predictive toxicology. We believe that the models presented here may serve as a promising tool, both for academic institutes as well as pharmaceutical industries, in predicting hERG-liability in new molecular structures. 

An in silico method has been developed that permits the binary differentiation between pure liquids causing serious eye damage or eye irritation, and pure liquids with no need for such classification, according to the UN GHS system. The method is based on the finding that the Hansen Solubility Parameters (HSP) of a liquid are collectively important predictors for eye irritation. Thus, by applying a two-tier approach in which in silico predicted pKa values (firstly) and a trained model based solely on in silico-predicted HSP data (secondly) were used, we have developed, and validated, a fully in silico approach for predicting the outcome of a Draize test (in terms of UN GHS Cat. 1/Cat. 2A/Cat. 2B or UN GHS No Cat.) with high validation set performance (sensitivity = 0.846, specificity = 0.818, balanced accuracy = 0.832) using SMILES only. The method is applicable to pure non-ionic liquids with molecular weight below 500 g/mol, fewer than six hydrogen bond donors (e.g. nitrogen–hydrogen or oxygen–hydrogen bonds) and fewer than eleven hydrogen bond acceptors (e.g. nitrogen or oxygen atoms). Due to its fully in silico characteristics, this method can be applied to pure liquids that are still at the desktop design stage and not yet in production.