Transferable Machine Learning Interatomic Potential for Bond Dissociation Energy Prediction of Drug-like Molecules.

We present a transferable MACE interatomic potential that is applicable to open- and closed-shell drug-like molecules containing hydrogen, carbon, and oxygen atoms. Including an accurate description of radical species extends the scope of possible applications to bond dissociation energy (BDE) prediction, for example, in the context of cytochrome P450 (CYP) metabolism. The transferability of the MACE potential was validated on the COMP6 data set, containing only closed-shell molecules, where it reaches better accuracy than the readily available general ANI-2x potential. MACE achieves similar accuracy on two CYP metabolism-specific data sets, which include open- and closed-shell structures. This model enables us to calculate the aliphatic C-H BDE, which allows us to compare reaction energies of hydrogen abstraction, which is the rate-limiting step of the aliphatic hydroxylation reaction catalyzed by CYPs. On the "CYP 3A4" data set, MACE achieves a BDE RMSE of 1.37 kcal/mol and better prediction of BDE ranks than alternatives: the semiempirical AM1 and GFN2-xTB methods and the ALFABET model that directly predicts bond dissociation enthalpies. Finally, we highlight the smoothness of the MACE potential over paths of sp3C-H bond elongation and show that a minimal extension is enough for the MACE model to start finding reasonable minimum energy paths of methoxy radical-mediated hydrogen abstraction. Altogether, this work lays the ground for further extensions of scope in terms of chemical elements, (CYP-mediated) reaction classes and modeling the full reaction paths, not only BDEs.

Predicting routes of phase I and II metabolism based on quantum mechanics and machine learning.

1. Unexpected metabolism could lead to the failure of many late-stage drug candidates or even the withdrawal of approved drugs. Thus, it is critical to predict and study the dominant routes of metabolism in the early stages of research. In this study, we describe the development and validation of a 'WhichEnzyme' model that accurately predicts the enzyme families most likely to be responsible for a drug-like molecule's metabolism. Furthermore, we combine this model with our previously published regioselectivity models for Cytochromes P450, Aldehyde Oxidases, Flavin-containing Monooxygenases, UDP-glucuronosyltransferases and Sulfotransferases - the most important Phase I and Phase II drug metabolising enzymes - and a 'WhichP450' model that predicts the Cytochrome P450 isoform(s) responsible for a compound's metabolism. The regioselectivity models are based on a mechanistic understanding of these enzymes' actions, and use quantum mechanical simulations with machine learning methods to accurately predict sites of metabolism and the resulting metabolites. We train heuristic based on the outputs of the 'WhichEnzyme', 'WhichP450', and regioselectivity models to determine the most likely routes of metabolism and metabolites to be observed experimentally. Finally, we demonstrate that this combination delivers high sensitivity in identifying experimentally reported metabolites and higher precision than other methods for predicting in vivo metabolite profiles.

Predicting Regioselectivity of Cytosolic Sulfotransferase Metabolism for Drugs.

Cytosolic sulfotransferases (SULTs) are a family of enzymes responsible for the sulfation of small endogenous and exogenous compounds. SULTs contribute to the conjugation phase of metabolism and share substrates with the uridine 5'-diphospho-glucuronosyltransferase (UGT) family of enzymes. UGTs are considered to be the most important enzymes in the conjugation phase, and SULTs are an auxiliary enzyme system to them. Understanding how the regioselectivity of SULTs differs from that of UGTs is essential from the perspective of developing novel drug candidates. We present a general ligand-based SULT model trained and tested using high-quality experimental regioselectivity data. The current study suggests that, unlike other metabolic enzymes in the modification and conjugation phases, the SULT regioselectivity is not strongly influenced by the activation energy of the rate-limiting step of the catalysis. Instead, the prominent role is played by the substrate binding site of SULT. Thus, the model is trained only on steric and orientation descriptors, which mimic the binding pocket of SULT. The resulting classification model, which predicts whether a site is metabolized, achieved a Cohen's kappa of 0.71.

Predicting Regioselectivity of AO, CYP, FMO, and UGT Metabolism Using Quantum Mechanical Simulations and Machine Learning.

Unexpected metabolism in modification and conjugation phases can lead to the failure of many late-stage drug candidates or even withdrawal of approved drugs. Thus, it is critical to predict the sites of metabolism (SoM) for enzymes, which interact with drug-like molecules, in the early stages of the research. This study presents methods for predicting the isoform-specific metabolism for human AOs, FMOs, and UGTs and general CYP metabolism for preclinical species. The models use semi-empirical quantum mechanical simulations, validated using experimentally obtained data and DFT calculations, to estimate the reactivity of each SoM in the context of the whole molecule. Ligand-based models, trained and tested using high-quality regioselectivity data, combine the reactivity of the potential SoM with the orientation and steric effects of the binding pockets of the different enzyme isoforms. The resulting models achieve κ values of up to 0.94 and AUC of up to 0.92.

An Open Drug Discovery Competition: Experimental Validation of Predictive Models in a Series of Novel Antimalarials.

The Open Source Malaria (OSM) consortium is developing compounds that kill the human malaria parasite, Plasmodium falciparum, by targeting PfATP4, an essential ion pump on the parasite surface. The structure of PfATP4 has not been determined. Here, we describe a public competition created to develop a predictive model for the identification of PfATP4 inhibitors, thereby reducing project costs associated with the synthesis of inactive compounds. Competition participants could see all entries as they were submitted. In the final round, featuring private sector entrants specializing in machine learning methods, the best-performing models were used to predict novel inhibitors, of which several were synthesized and evaluated against the parasite. Half possessed biological activity, with one featuring a motif that the human chemists familiar with this series would have dismissed as "ill-advised". Since all data and participant interactions remain in the public domain, this research project "lives" and may be improved by others.

Binding Between Cyclohexanohemicucurbit[n]urils and Polar Organic Guests.

Inherently chiral, barrel-shaped, macrocyclic hosts such as cyclohexanohemicucurbit[n]urils (cycHC[n]) bind zinc porphyrins and trifluoroacetic acid externally in halogenated solvents. In the current study, we tested a set of eighteen organic guests with various functional groups and polarity, namely, thiophenols, phenols, and carboxylic and sulfonic acids, to identify a preference toward hydrogen bond-donating molecules for homologous cycHC[6] and cycHC[8]. Guests were characterized by Hirshfeld partial charges on acidic hydrogens and their binding by 1H and 19F NMR titrations. Evaluation of association constants revealed the complexity of the system and indirectly proved an external binding with stoichiometry over 2:1 for both homologs. It was found that overall binding strength is influenced by the stoichiometry of the formed complexes, the partial atomic charge on the hydrogen atom of the hydrogen bond donor, and the bulkiness of the guest. Additionally, a study on the formation of complexes with halogen anions (Cl- and Br-) in methanol and chloroform, analyzed by 1H NMR, did not confirm complexation. The current study widens the scope of potential applications for host molecules by demonstrating the formation of hydrogen-bonded complexes with multisite hydrogen bond acceptors such as cycHC[6] and cycHC[8].

Predicting reactivity to drug metabolism: beyond P450s-modelling FMOs and UGTs.

We present a study based on density functional theory calculations to explore the rate limiting steps of product formation for oxidation by Flavin-containing Monooxygenase (FMO) and glucuronidation by the UDP-glucuronosyltransferase (UGT) family of enzymes. FMOs are responsible for the modification phase of metabolism of a wide diversity of drugs, working in conjunction with Cytochrome P450 (CYP) family of enzymes, and UGTs are the most important class of drug conjugation enzymes. Reactivity calculations are important for prediction of metabolism by CYPs and reactivity alone explains around 70-85% of the experimentally observed sites of metabolism within CYP substrates. In the current work we extend this approach to propose model systems which can be used to calculate the activation energies, i.e. reactivity, for the rate-limiting steps for both FMO oxidation and glucuronidation of potential sites of metabolism. These results are validated by comparison with the experimentally observed reaction rates and sites of metabolism, indicating that the presented models are suitable to provide the basis of a reactivity component within generalizable models to predict either FMO or UGT metabolism.

Dynamic chiral cyclohexanohemicucurbit[12]uril.

NMR spectroscopy and DFT modeling studies of chiral cyclohexanohemicucurbit[12]uril indicate that the macrocycle adopts a concave octagonal shape with two distinct conformational flexibilities in solution. Methylene bridge flipping occurs at temperatures above 265 K, while urea monomers rotate at temperatures above 308 K, resulting in the loss of confined space within the macrocycle.

Chiral hemicucurbit[8]uril as an anion receptor: selectivity to size, shape and charge distribution.

A novel eight-membered macrocycle of the hemicucurbit[n]uril family, chiral (all-R)-cyclohexanohemicucurbit[8]uril (cycHC[8]) ‡The name cyclohexylhemicucurbituril, previously used for these macrocycles, is changed in accordance with the IUPAC nomenclature for fused cycles, as the cyclohexane substituents are fused with the parent hemicucurbituril. binds anions in a purely protic solvent with remarkable selectivity. The cycHC[8] portals open and close to fully encapsulate anions in a 1 : 1 ratio, resembling a molecular Pac-Man™. Comprehensive gas, solution and solid phase studies prove that the binding is governed by the size, shape and charge distribution of the bound anion. Gas phase studies show an order of SbF6- ≈ PF6- > ReO4- > ClO4- > SCN- > BF4- > HSO4- > CF3SO3- for anion complexation strength. An extensive crystallographic study reveals the preferred orientations of the anions within the octahedral cavity of cycHC[8] and highlights the importance of the size- and shape-matching between the anion and the receptor cavity. The solution studies show the strongest binding of the ideally fitting SbF6- anion, with an association constant of 2.5 × 105 M-1 in pure methanol. The symmetric, receptor cavity-matching charge distribution of the anions results in drastically stronger binding than in the case of anions with asymmetric charge distribution. Isothermal titration calorimetry (ITC) reveals the complexation to be exothermic and enthalpy-driven. The DFT calculations and VT-NMR studies confirmed that the complexation proceeds through a pre-complex formation while the exchange of methanol solvent with the anion is the rate-limiting step. The octameric cycHC[8] offers a unique example of template-controlled design of an electroneutral host for binding large anions in a competitive polar solvent.

Computational and ion mobility MS study of (all-S)-cyclohexylhemicucurbit[6]uril structure and complexes.

A computational study of (all-S)-cyclohexylhemicucurbit[6]uril and its complexes with anions (Cl(-), Br(-), I(-) and HCOO(-)), the proton (H(+)) and non-dissociated acid (HCl, HBr, HI and HCOOH) guests was performed. The geometries of guest-host complexes were optimized via density functional theory using the BP86 functional, SV(P) basis set and Stuttgart pseudopotentials for iodide. Binding affinities and their trends were evaluated at the BP86/TZVPD level of theory. In addition, the quantum theory of atoms in molecules was used to gain insight into guest-host interactions. A computational study in the gas phase and ion-mobility mass-spectrometry analysis revealed that the studied macrocycle formed inclusion complexes with anions. Protonation of the macrocycle is preferred at the nitrogen atom pointing inside of the cavity. In the studied conditions, non-dissociated acids formed complexes at the oxygen atom pointing outside of the macrocycle.

Organocatalytic asymmetric addition of malonates to unsaturated 1,4-diketones.

The organocatalytic Michael addition of malonates to symmetric unsaturated 1,4-diketones catalyzed by thiourea and squaramide derivatives with Cinchona alkaloids afforded the formation of a new C-C bond in high yields (up to 98%) and enantiomeric purities (up to 93%). The absolute configuration of the product was suggested from comparison of the experimental and calculated VCD spectra of the reaction product 3a.