Benefit of Retraining pKa Models Studied Using Internally Measured Data

Best of both worlds: An expansion of the state of the art pKa model with data from three industrial partners

In a unique collaboration between Simulations Plus and several industrial partners, we were able to develop a new version 11.0 of the previously published in silico pKa model, S+pKa, with considerably improved prediction accuracy. The model's training set was vastly expanded by large amounts of experimental data obtained from F. Hoffmann-La Roche AG, Genentech Inc., and the Crop Science division of Bayer AG. The previous v7.0 of S+pKa was trained on data from public sources and the Pharmaceutical division of Bayer AG. The model has shown dramatic improvements in predictive accuracy when externally validated on three new contributor compound sets. Less expected was v11.0's improvement in prediction on new compounds developed at Bayer Pharma after v7.0 was released (2013-2023), even without contributing additional data to v11.0. We illustrate chemical space coverage by chemistries encountered in the five domains, public and industrial, outline model construction, and discuss factors contributing to model's success.

Avoid missing pKas: High-throughput workflow using solution pH-metric in tandem with UV-metric measurements

We describe a new high-throughput automated pKa workflow using potentiometry starting with 10 mM DMSO stock (solution pH-metric). Two approaches using either neat DMSO stock solution or removal of DMSO were evaluated with different sample amounts and cosolvent schemes. These were validated against traditional potentiometric measurements for optimal conditions. Further, we detail how high throughput solution pH-metric experiments are performed in tandem with established UV-metric measurements to capitalize on the advantages of both approaches. This new workflow maintains the sample and time savings required for measuring a large number of samples in a drug discovery setting, while avoiding "missing pKas" due to lack of sufficient UV chromophores. The combination of the two assays is key to tackle the challenges of low solubility, overlapping pKas, and preliminary assignment of pKas for Structure-Activity Relationship (SAR) understanding.

Machine Learning for Fast, Quantum Mechanics-Based Approximation of Drug Lipophilicity

Lipophilicity, as measured by the partition coefficient between octanol and water (log P), is a key parameter in early drug discovery research. However, measuring log P experimentally is difficult for specific compounds and log P ranges. The resulting lack of reliable experimental data impedes development of accurate in silico models for such compounds. In certain discovery projects at Novartis focused on such compounds, a quantum mechanics (QM)-based tool for log P estimation has emerged as a valuable supplement to experimental measurements and as a preferred alternative to existing empirical models. However, this QM-based approach incurs a substantial computational cost, limiting its applicability to small series and prohibiting quick, interactive ideation. This work explores a set of machine learning models (Random Forest, Lasso, XGBoost, Chemprop, and Chemprop3D) to learn calculated log P values on both a public data set and an in-house data set to obtain a computationally affordable, QM-based estimation of drug lipophilicity. The message-passing neural network model Chemprop emerged as the best performing model with mean absolute errors of 0.44 and 0.34 log units for scaffold split test sets of the public and in-house data sets, respectively. Analysis of learning curves suggests that a further decrease in the test set error can be achieved by increasing the training set size. While models directly trained on experimental data perform better at approximating experimentally determined log P values than models trained on calculated values, we discuss the potential advantages of using calculated log P values going beyond the limits of experimental quantitation. We analyze the impact of the data set splitting strategy and gain insights into model failure modes. Potential use cases for the presented models include pre-screening of large compound collections and prioritization of compounds for full QM calculations.

Predicting In Vivo Compound Brain Penetration Using Multi-task Graph Neural Networks

Assessing whether compounds penetrate the brain can become critical in drug discovery, either to prevent adverse events or to reach the biological target. Generally, pre-clinical in vivo studies measuring the ratio of brain and blood concentrations (K_p) are required to estimate the brain penetration potential of a new drug entity. In this work, we developed machine learning models to predict in vivo compound brain penetration (as LogK_p) from chemical structure. Our results show the benefit of including in vitro experimental data as auxiliary tasks in multi-task graph neural network (MT-GNN) models. MT-GNNs outperformed single-task (ST) models solely trained on in vivo brain penetration data. The best-performing MT-GNN regression model achieved a coefficient of determination of 0.42 and a mean absolute error of 0.39 (2.5-fold) on a prospective validation set and outperformed all tested ST models. To facilitate decision-making, compounds were classified into brain-penetrant or non-penetrant, achieving a Matthew's correlation coefficient of 0.66. Taken together, our findings indicate that the inclusion of in vitro assay data as MT-GNN auxiliary tasks improves in vivo brain penetration predictions and prospective compound prioritization.

Towards the sustainable discovery and development of new antibiotics

An ever-increasing demand for novel antimicrobials to treat life-threatening infections caused by the global spread of multidrug-resistant bacterial pathogens stands in stark contrast to the current level of investment in their development, particularly in the fields of natural-product-derived and synthetic small molecules. New agents displaying innovative chemistry and modes of action are desperately needed worldwide to tackle the public health menace posed by antimicrobial resistance. Here, our consortium presents a strategic blueprint to substantially improve our ability to discover and develop new antibiotics. We propose both short-term and long-term solutions to overcome the most urgent limitations in the various sectors of research and funding, aiming to bridge the gap between academic, industrial and political stakeholders, and to unite interdisciplinary expertise in order to efficiently fuel the translational pipeline for the benefit of future generations.

Discovery and Optimization of DNA Gyrase and Topoisomerase IV Inhibitors with Potent Activity against Fluoroquinolone-Resistant Gram-Positive Bacteria

Herein, we describe the discovery and optimization of a novel series that inhibits bacterial DNA gyrase and topoisomerase IV via binding to, and stabilization of, DNA cleavage complexes. Optimization of this series led to the identification of compound 25, which has potent activity against Gram-positive bacteria, a favorable in vitro safety profile, and excellent in vivo pharmacokinetic properties. Compound 25 was found to be efficacious against fluoroquinolone-sensitive Staphylococcus aureus infection in a mouse thigh model at lower doses than moxifloxacin. An X-ray crystal structure of the ternary complex formed by topoisomerase IV from Klebsiella pneumoniae, compound 25, and cleaved DNA indicates that this compound does not engage in a water-metal ion bridge interaction and forms no direct contacts with residues in the quinolone resistance determining region (QRDR). This suggests a structural basis for the reduced impact of QRDR mutations on antibacterial activity of 25 compared to fluoroquinolones.

Recent advances in constraint and machine learning-based metabolic modeling by leveraging stoichiometric balances, thermodynamic feasibility and kinetic law formalisms

Understanding the governing principles behind organisms' metabolism and growth underpins their effective deployment as bioproduction chassis. A central objective of metabolic modeling is predicting how metabolism and growth are affected by both external environmental factors and internal genotypic perturbations. The fundamental concepts of reaction stoichiometry, thermodynamics, and mass action kinetics have emerged as the foundational principles of many modeling frameworks designed to describe how and why organisms allocate resources towards both growth and bioproduction. This review focuses on the latest algorithmic advancements that have integrated these foundational principles into increasingly sophisticated quantitative frameworks.

Topoisomerase Inhibitors Addressing Fluoroquinolone Resistance in Gram-Negative Bacteria

Since their discovery over 5 decades ago, quinolone antibiotics have found enormous success as broad spectrum agents that exert their activity through dual inhibition of bacterial DNA gyrase and topoisomerase IV. Increasing rates of resistance, driven largely by target-based mutations in the GyrA/ParC quinolone resistance determining region, have eroded the utility and threaten the future use of this vital class of antibiotics. Herein we describe the discovery and optimization of a series of 4-(aminomethyl)quinolin-2(1H)-ones, exemplified by 34, that inhibit bacterial DNA gyrase and topoisomerase IV and display potent activity against ciprofloxacin-resistant Gram-negative pathogens. X-ray crystallography reveals that 34 occupies the classical quinolone binding site in the topoisomerase IV-DNA cleavage complex but does not form significant contacts with residues in the quinolone resistance determining region.

Size Matters and How You Measure It: A Gram-Negative Antibacterial Example Exceeding Typical Molecular Weight Limits

Monobactam antibiotic 1 is active against Gram-negative bacteria even though it has a higher molecular weight (MW) than the limit of 600 Da typically applied in designing such compounds. On the basis of 2D NMR data, the compound is able to adopt a compact conformation. The dimensions, projection area, and dipole moment derived from this conformation are compatible with porin permeation, as are locations of polar groups upon superimposition to the crystal structure of ampicillin bound to E. coli OmpF porin. Minimum inhibitory concentration (MIC) shifts in a porin knock-out strain are also consistent with 1 predominately permeating through porins. In conclusion, we describe a carefully characterized case of a molecule outside default design parameters where MW does not adequately represent the 3D shape more directly related to permeability. Leveraging 3D design criteria would open up additional chemical space currently underutilized due to limitations perceived in 2D.

High accuracy quantum-chemistry-based calculation and blind prediction of macroscopic pKa values in the context of the SAMPL6 challenge

Recent advances in the development of low-cost quantum chemical methods have made the prediction of conformational preferences and physicochemical properties of medium-sized drug-like molecules routinely feasible, with significant potential to advance drug discovery. In the context of the SAMPL6 challenge, macroscopic pKa values were blindly predicted for a set of 24 of such molecules. In this paper we present two similar quantum chemical based approaches based on the high accuracy calculation of standard reaction free energies and the subsequent determination of those pKa values via a linear free energy relationship. Both approaches use extensive conformational sampling and apply hybrid and double-hybrid density functional theory with continuum solvation to calculate free energies. The blindly calculated macroscopic pKa values were in excellent agreement with the experiment.

Interactions between β2-Adrenoceptor Ligands and Membrane: Atomic-Level Insights from Magic-Angle Spinning NMR

To understand the relationship between structural properties of the β2-adrenoceptor ligands and their interactions with membranes, we have investigated the location and distribution of five β2 agonists with distinct clinical durations and onsets of action (indacaterol, two indacaterol analogues, salmeterol and formoterol) in monounsaturated model membranes using magic angle spinning NMR to measure these interactions through both ¹H nuclear Overhauser enhancement (NOE) and paramagnetic relaxation enhancement (PRE) techniques. The hydrophilic aromatic groups of all five β2 agonists show maximum distribution in the lipid/water interface, but distinct location and dynamic behavior were observed for the lipophilic aromatic rings. Our study elucidates at atomic level that the hydrophobicity and substitution geometry of lipophilic groups play important roles in compound-lipid interactions.

Evaluation of the GastroPlus™ Advanced Compartmental and Transit (ACAT) Model in Early Discovery

PURPOSE

The aim of this study was to evaluate the oral exposure predictions obtained early in drug discovery with a generic GastroPlus Advanced Compartmental And Transit (ACAT) model based on the in vivo intravenous blood concentration-time profile, in silico properties (lipophilicity, pKa) and in vitro high-throughput absorption-distribution-metabolism-excretion (ADME) data (as determined by PAMPA, solubility, liver microsomal stability assays).

METHODS

The model was applied to a total of 623 discovery molecules and their oral exposure was predicted in rats and/or dogs. The predictions of Cmax, AUClast and Tmax were compared against the observations.

RESULTS

The generic model proved to make predictions of oral Cmax, AUClast and Tmax within 3-fold of the observations for rats in respectively 65%, 68% and 57% of the 537 cases. For dogs, it was respectively 77%, 79% and 85% of the 124 cases. Statistically, the model was most successful at predicting oral exposure of Biopharmaceutical Classification System (BCS) class 1 compounds compared to classes 2 and 3, and was worst at predicting class 4 compounds oral exposure.

CONCLUSION

The generic GastroPlus ACAT model provided reasonable predictions especially for BCS class 1 compounds. For compounds of other classes, the model may be refined by obtaining more information on solubility and permeability in secondary assays. This increases confidence that such a model can be used in discovery projects to understand the parameters limiting absorption and extrapolate predictions across species. Also, when predictions disagree with the observations, the model can be updated to test hypotheses and understand oral absorption.