Machine learning methods for pKa prediction of small molecules: Advances and challenges

The molecular features of non-peptidic nucleophilic substrates and acceptor proteins determine the efficiency of sortagging

Sortase A-mediated ligation (SML) or "sortagging" has become a popular technology to selectively introduce structurally diverse protein modifications. Despite the great progress in the optimization of the reaction conditions and design of miscellaneous C- or N-terminal protein modification strategies, the reported yields of conjugates are highly variable. In this study, we have systematically investigated C-terminal protein sortagging efficiency using a combination of several rationally selected and modified acceptor proteins and a panel of incoming surrogate non-peptidic amine nucleophile substrates varying in the structural features of their amino linker parts and cargo molecules. Our data suggest that the sortagging efficiency is modulated by the combination of molecular features of the incoming nucleophilic substrate, including the ionization properties of the reactive amino group, structural recognition of the nucleophilic amino linker by the enzyme, as well as the molecular nature of the attached payload moiety. Previous reports have confirmed that the steric accessibility of the C-terminal SrtA recognition site in the acceptor protein is also the critical determinant of sortase reaction efficiency. We suggest a computational procedure for simplifying a priori predictions of sortagging outcomes through the structural assessment of the acceptor protein and introduction of a peptide linker, if deemed necessary.

Interpretable Deep-Learning pKa Prediction for Small Molecule Drugs via Atomic Sensitivity Analysis

Machine learning (ML) models now play a crucial role in predicting properties essential to drug development, such as a drug's logscale acid-dissociation constant (pKa). Despite recent architectural advances, these models often generalize poorly to novel compounds due to a scarcity of ground-truth data. Further, these models lack interpretability. To this end, with deliberate molecular embeddings, atomic-resolution information is accessible in chemical structures by observing the model response to atomic perturbations of an input molecule. Here, we present BCL-XpKa, a deep neural network (DNN)-based multitask classifier for pKa prediction that encodes local atomic environments through Mol2D descriptors. BCL-XpKa outputs a discrete distribution for each molecule, which stores the pKa prediction and the model's uncertainty for that molecule. BCL-XpKa generalizes well to novel small molecules. BCL-XpKa performs competitively with modern ML pKa predictors, outperforms several models in generalization tasks, and accurately models the effects of common molecular modifications on a molecule's ionizability. We then leverage BCL-XpKa's granular descriptor set and distribution-centered output through atomic sensitivity analysis (ASA), which decomposes a molecule's predicted pKa value into its respective atomic contributions without model retraining. ASA reveals that BCL-XpKa has implicitly learned high-resolution information about molecular substructures. We further demonstrate ASA's utility in structure preparation for protein-ligand docking by identifying ionization sites in 93.2% and 87.8% of complex small molecule acids and bases. We then applied ASA with BCL-XpKa to identify and optimize the physicochemical liabilities of a recently published KRAS-degrading PROTAC.

Investigating experimental vs. Predicted pKa values for PET radiotracer

The prediction of central nervous system (CNS) active pharmaceuticals and radiopharmaceuticals has experienced a boost by the introduction of computational approaches, like blood-brain barrier (BBB) score or CNS multiparameter optimization values. These rely heavily on calculated pKa values and other physicochemical parameters. Despite the inclusion of various physicochemical parameters in online data banks, pKa values are often missing and published experimental pKa values are limited especially for radiopharmaceuticals. This comparative study investigated the discrepancies between predicted and experimental pKa values and their impact on CNS activity prediction scores. The pKa values of 46 substances, including therapeutic drugs and PET imaging radiopharmaceuticals, were measured by means of potentiometry and spectrophotometry. Experimentally obtained pKa values were compared with in silico predictions (Chemicalize/Marvin). The results demonstrate a considerable discrepancy between experimental and in silico values, with linear regression analysis showing intermediate correlation (R2(Marvin) = 0.88, R2(Chemicalize) = 0.82). This indicates that if one requires an accurate pKa value, it is essential to experimentally assess it. This underscores the importance of experimentally determining pKa values for accurate drug design and optimization. The study's data provide a valuable library of reliable experimental pKa values for therapeutic drugs and radiopharmaceuticals, aiding researchers in the field.

Bridging Machine Learning and Thermodynamics for Accurate pK a Prediction

Integrating scientific principles into machine learning models to enhance their predictive performance and generalizability is a central challenge in the development of AI for Science. Herein, we introduce Uni-pK a, a novel framework that successfully incorporates thermodynamic principles into machine learning modeling, achieving high-precision predictions of acid dissociation constants (pK a), a crucial task in the rational design of drugs and catalysts, as well as a modeling challenge in computational physical chemistry for small organic molecules. Uni-pK a utilizes a comprehensive free energy model to represent molecular protonation equilibria accurately. It features a structure enumerator that reconstructs molecular configurations from pK a data, coupled with a neural network that functions as a free energy predictor, ensuring high-throughput, data-driven prediction while preserving thermodynamic consistency. Employing a pretraining-finetuning strategy with both predicted and experimental pK a data, Uni-pK a not only achieves state-of-the-art accuracy in chemoinformatics but also shows comparable precision to quantum mechanics-based methods.

Caught between a ROCK and a hard place: current challenges in structure-based drug design

The discipline of structure-based drug design (SBDD) is several decades old and it is tempting to think that the proliferation of experimental structures for many drug targets might make computer-aided drug design (CADD) straightforward. However, this is far from true. In this review, we illustrate some of the challenges that CADD scientists face every day in their work, even now. We use Rho-associated protein kinase (ROCK), and public domain structures and data, as an example to illustrate some of the challenges we have experienced during our project targeting this protein. We hope that this will help to prevent unrealistic expectations of what CADD can accomplish and to educate non-CADD scientists regarding the challenges still facing their CADD colleagues.

QupKake: Integrating Machine Learning and Quantum Chemistry for Micro-pKa Predictions

Accurate prediction of micro-pKa values is crucial for understanding and modulating the acidity and basicity of organic molecules, with applications in drug discovery, materials science, and environmental chemistry. This work introduces QupKake, a novel method that combines graph neural network models with semiempirical quantum mechanical (QM) features to achieve exceptional accuracy and generalization in micro-pKa prediction. QupKake outperforms state-of-the-art models on a variety of benchmark data sets, with root-mean-square errors between 0.5 and 0.8 pKa units on five external test sets. Feature importance analysis reveals the crucial role of QM features in both the reaction site enumeration and micro-pKa prediction models. QupKake represents a significant advancement in micro-pKa prediction, offering a powerful tool for various applications in chemistry and beyond.

GR-pKa: a message-passing neural network with retention mechanism for pKa prediction

During the drug discovery and design process, the acid-base dissociation constant (pKa) of a molecule is critically emphasized due to its crucial role in influencing the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties and biological activity. However, the experimental determination of pKa values is often laborious and complex. Moreover, existing prediction methods exhibit limitations in both the quantity and quality of the training data, as well as in their capacity to handle the complex structural and physicochemical properties of compounds, consequently impeding accuracy and generalization. Therefore, developing a method that can quickly and accurately predict molecular pKa values will to some extent help the structural modification of molecules, and thus assist the development process of new drugs. In this study, we developed a cutting-edge pKa prediction model named GR-pKa (Graph Retention pKa), leveraging a message-passing neural network and employing a multi-fidelity learning strategy to accurately predict molecular pKa values. The GR-pKa model incorporates five quantum mechanical properties related to molecular thermodynamics and dynamics as key features to characterize molecules. Notably, we originally introduced the novel retention mechanism into the message-passing phase, which significantly improves the model's ability to capture and update molecular information. Our GR-pKa model outperforms several state-of-the-art models in predicting macro-pKa values, achieving impressive results with a low mean absolute error of 0.490 and root mean square error of 0.588, and a high R2 of 0.937 on the SAMPL7 dataset.

AttenGpKa: A Universal Predictor of Solvation Acidity Using Graph Neural Network and Molecular Topology

Rapid and accurate calculation of acid dissociation constant (pKa) is crucial for designing chemical synthesis routes, optimizing catalysts, and predicting chemical behavior. Despite recent progress in machine learning, predicting solvation acidity, especially in nonaqueous solvents, remains challenging due to limited experimental data. This challenge arises from treating experimental values in different solvents as distinct data domains and modeling them separately. In this work, we treat both the solutes and solvents equally from a perspective of molecular topology and propose a highly universal framework called AttenGpKa for predicting solvation acidity. AttenGpKa is trained using 26,522 experimental pKa values from 60 pure and mixed solvents in the iBonD database. As a result, our model can simultaneously predict the pKa values of a compound in various solvents, including pure water, pure nonaqueous, and mixed solvents. AttenGpKa achieves universality by using graph neural networks and attention mechanisms to learn complex effects within solute and solvent molecules. Furthermore, encodings of both solute and solvent molecules are adaptively fused to simulate the influence of the solvent on acid dissociation. AttenGpKa demonstrates robust generalization in extensive validations. The interpretability studies further indicate that our model has effectively learnt electronic and solvent effects. A free-to-use software is provided to facilitate the use of AttenGpKa for pKa prediction.

Explainable Graph Neural Networks with Data Augmentation for Predicting pKa of C-H Acids

The pKa of C-H acids is an important parameter in the fields of organic synthesis, drug discovery, and materials science. However, the prediction of pKa is still a great challenge due to the limit of experimental data and the lack of chemical insight. Here, a new model for predicting the pKa values of C-H acids is proposed on the basis of graph neural networks (GNNs) and data augmentation. A message passing unit (MPU) was used to extract the topological and target-related information from the molecular graph data, and a readout layer was utilized to retrieve the information on the ionization site C atom. The retrieved information then was adopted to predict pKa by a fully connected network. Furthermore, to increase the diversity of the training data, a knowledge-infused data augmentation technique was established by replacing the H atoms in a molecule with substituents exhibiting different electronic effects. The MPU was pretrained with the augmented data. The efficacy of data augmentation was confirmed by visualizing the distribution of compounds with different substituents and by classifying compounds. The explainability of the model was studied by examining the change of pKa values when a specific atom was masked. This explainability was used to identify the key substituents for pKa. The model was evaluated on two data sets from the iBonD database. Dataset1 includes the experimental pKa values of C-H acids measured in DMSO, while dataset2 comprises the pKa values measured in water. The results show that the knowledge-infused data augmentation technique greatly improves the predictive accuracy of the model, especially when the number of samples is small.

Dissociation constants of relevant secondary organic aerosol components in the atmosphere

The presented studies focus on measuring the determination of the acidity constant (pKa) of relevant secondary organic aerosol components. For our research, we selected important oxidation products (mainly carboxylic acids) of the most abundant terpene compounds, such as α-pinene, β-pinene, β-caryophyllene, and δ-3-carene. The research covered the synthesis and determination of the acidity constant of selected compounds. We used three methods to measure the acidity constant, i.e., 1H NMR titration, pH-metric titration, Bates-Schwarzenbach spectrophotometric method. Moreover, the pKa values were calculated with Marvin 21.17.0 software to compare the experimentally derived values with those calculated from the chemical structure. pKa values measured with 1H NMR titration ranged from 3.51 ± 0.01 for terebic acid to 5.18 ± 0.06 for β-norcaryophyllonic acid. Moreover, the data determined by the 1H NMR method revealed a good correlation with the data obtained with the commonly used potentiometric and UV-spectroscopic methods (R2 = 0.92). In contrast, the comparison with in silico results exhibits a relatively low correlation (R2Marvin = 0.66). We found that most of the values calculated with the Marvin Program are lower than experimental values obtained with pH-metric titration with an average difference of 0.44 pKa units. For di- and tricarboxylic acids, we obtained two and three pKa values, respectively. A good correlation with the literature values was observed, for example, Howell and Fisher (1958) used pH-metric titration and measured pKa1 and pKa2 to be 4.48 and 5.48, while our results are 4.24 ± 0.10 and 5.40 ± 0.02, respectively.

Leveraging DFT and Molecular Fragmentation for Chemically Accurate pKa Prediction Using Machine Learning

We present a quantum mechanical/machine learning (ML) framework based on random forest to accurately predict the pKas of complex organic molecules using inexpensive density functional theory (DFT) calculations. By including physics-based features from low-level DFT calculations and structural features from our connectivity-based hierarchy (CBH) fragmentation protocol, we can correct the systematic error associated with DFT. The generalizability and performance of our model are evaluated on two benchmark sets (SAMPL6 and Novartis). We believe the carefully curated input of physics-based features lessens the model's data dependence and need for complex deep learning architectures, without compromising the accuracy of the test sets. As a point of novelty, our work extends the applicability of CBH, employing it for the generation of viable molecular descriptors for ML.

An Accurate Approach for Computational pKa Determination of Phenolic Compounds

Computational chemistry is a valuable tool, as it allows for in silico prediction of key parameters of novel compounds, such as pKa. In the framework of computational pKa determination, the literature offers several approaches based on different level of theories, functionals and continuum solvation models. However, correction factors are often used to provide reliable models that adequately predict pKa. In this work, an accurate protocol based on a direct approach is proposed for computing phenols pKa. Importantly, this methodology does not require the use of correction factors or mathematical fitting, making it highly practical, easy to use and fast. Above all, DFT calculations performed in the presence two explicit water molecules using CAM-B3LYP functional with 6-311G+dp basis set and a solvation model based on density (SMD) led to accurate pKa values. In particular, calculations performed on a series of 13 differently substituted phenols provided reliable results, with a mean absolute error of 0.3. Furthermore, the model achieves accurate results with -CN and -NO₂ substituents, which are usually excluded from computational pKa studies, enabling easy and reliable pKa determination in a wide range of phenols.