Reactivity prediction in aza-Michael additions without transition state calculations: the Ames test for mutagenicity

Low-cost quantum mechanical descriptors for data efficient skin sensitization QSAR models

Quantitative Structure Activity Relationship modelling methodologies need to incorporate relevant mechanistic information to have high predictive performance and validity. Electrophilic reactivity is a common mechanistic feature of skin sensitization endpoints which could be concisely characterized with electronic descriptors which is key to enabling the modelling of small datasets in this domain. However, quantum mechanical methodologies have previously featured high computational costs which would exclude the use of large datasets. Consequently, we investigate the use of electronic descriptors calculated using the Hartree Fock with 3 corrections (Hf-3c) method, a low-cost ab initio methodology that has higher chemical accuracy than previous semiempirical methodologies for modelling in vitro skin sensitization assay outcomes. We also model the Ames assay as a surrogate for determining skin sensitization outcomes. The quantum chemical descriptors calculated using the Hf-3c method with conductor-like polarizable continuum model (CPCM) implicit solvation found improved QSAR model performance for the in vitro Ames (n = 6049, 0.770 AUC), KeratinoSens (n = 164, 0.763 AUC), and Direct Peptide Reactivity Assay (n = 122, 0.750 AUC) datasets, with their combination producing high predictive performance for unseen in vivo Local Lymph Node Assay (n = 86, 0.789 AUC) and Human Repeated Insult Patch Test (n = 86, 0.791 AUC) assay toxicant outcomes.

Reformulating Reactivity Design for Data-Efficient Machine Learning

Machine learning (ML) can deliver rapid and accurate reaction barrier predictions for use in rational reactivity design. However, model training requires large data sets of typically thousands or tens of thousands of barriers that are very expensive to obtain computationally or experimentally. Furthermore, bespoke data sets are required for each region of interest in reaction space as models typically struggle to generalize. We have therefore reformulated the ML barrier prediction problem toward a much more data-efficient process: finding a reaction from a prespecified set with a desired target value. Our reformulation enables the rapid selection of reactions with purpose-specific activation barriers, for example, in the design of reactivity and selectivity in synthesis, catalyst design, toxicology, and covalent drug discovery, requiring just tens of accurately measured barriers. Importantly, our reformulation does not require generalization beyond the domain of the data set at hand, and we show excellent results for the highly toxicologically and synthetically relevant data sets of aza-Michael addition and transition-metal-catalyzed dihydrogen activation, typically requiring less than 20 accurately measured density functional theory (DFT) barriers. Even for incomplete data sets of E2 and SN2 reactions, with high numbers of missing barriers (74% and 56% respectively), our chosen ML search method still requires significantly fewer data points than the hundreds or thousands needed for more conventional uses of ML to predict activation barriers. Finally, we include a case study in which we use our process to guide the optimization of the dihydrogen activation catalyst. Our approach was able to identify a reaction within 1 kcal mol-1 of the target barrier by only having to run 12 DFT reaction barrier calculations, which illustrates the usage and real-world applicability of this reformulation for systems of high synthetic importance.

Eliminating Transition State Calculations for Faster and More Accurate Reactivity Prediction in Sulfa-Michael Additions Relevant to Human Health and the Environment

Fast and accurate computational approaches to predicting reactivity in sulfa-Michael additions are required for high-throughput screening in toxicology (e.g., predicting excess aquatic toxicity and skin sensitization), chemical synthesis, covalent drug design (e.g., targeting cysteine), and data set generation for machine learning. The kinetic glutathione chemoassay is a time-consuming in chemico method used to extract kinetic data in the form of log(k GSH) for organic electrophiles. In this work, we use density functional theory to compare the use of transition states (TSs) and enolate intermediate structures following C-S bond formation in the prediction of log(k GSH) for a diverse group of 1,4 Michael acceptors. Despite the widespread use of transition state calculations in the literature to predict sulfa-Michael reactivity, we observe that intermediate structures show much better performance for the prediction of log(k GSH), are faster to calculate, and easier to obtain than TSs. Furthermore, we show how linear combinations of atomic charges from the isolated Michael acceptors can further improve predictions, even when using inexpensive semiempirical quantum chemistry methods. Our models can be used widely in the chemical sciences (e.g., in the prediction of toxicity relevant to the environment and human health, synthesis planning, and the design of cysteine-targeting covalent inhibitors), and represent a low-cost, sustainable approach to reactivity assessment.