Holistic Prediction of the p K a in Diverse Solvents Based on a Machine‐Learning Approach

Accurate Protein pKa Prediction with Physical Organic Chemistry Guided 3D Protein Representation

Protein pKa is a fundamental physicochemical parameter that dictates protein structure and function. However, accurately determining protein site-pKa values remains a substantial challenge, both experimentally and theoretically. In this study, we introduce a physical organic approach, leveraging a protein structural and physical-organic-parameter-based representation (P-SPOC), to develop a rapid and intuitive model for protein pKa prediction. Our P-SPOC model achieves state-of-the-art predictive accuracy, with a mean absolute error (MAE) of 0.33 pKa units. Furthermore, we have incorporated advanced protein structure prediction models, like AlphaFold2, to approximate structures for proteins lacking three-dimensional representations, which enhances the applicability of our model in the context of structure-undetermined protein research. To promote broader accessibility within the research community, an online prediction interface was also established at isyn.luoszgroup.com.

Recent Progress in the Endosomal Escape Mechanism and Chemical Structures of Polycations for Nucleic Acid Delivery

Nucleic acid-based therapies are seeing a spiralling surge. Stimuli-responsive polymers, especially pH-responsive ones, are gaining widespread attention because of their ability to efficiently deliver nucleic acids. These polymers can be synthesized and modified according to target requirements, such as delivery sites and the nature of nucleic acids. In this regard, the endosomal escape mechanism of polymer-nucleic acid complexes (polyplexes) remains a topic of considerable interest owing to various plausible escape mechanisms. This review describes current progress in the endosomal escape mechanism of polyplexes and state-of-the-art chemical designs for pH-responsive polymers. The importance is also discussed of the acid dissociation constant (i.e., pKa) in designing the new generation of pH-responsive polymers, along with assays to monitor and quantify the endosomal escape behavior. Further, the use of machine learning is addressed in pKa prediction and polymer design to find novel chemical structures for pH responsiveness. This review will facilitate the design of new pH-responsive polymers for advanced and efficient nucleic acid delivery.

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.

Expanded ensemble predictions of absolute binding free energies in the SAMPL9 host-guest challenge

As part of the SAMPL9 community-wide blind host-guest challenge, we implemented an expanded ensemble workflow to predict absolute binding free energies for 13 small molecules against pillar[6]arene. Notable features of our protocol include consideration of a variety of protonation and enantiomeric states for both host and guests, optimization of alchemical intermediates, and analysis of free energy estimates and their uncertainty using large numbers of simulation replicates performed using distributed computing. Our predictions of absolute binding free energies resulted in a mean absolute error of 2.29 kcal mol-1 and an R2 of 0.54. Overall, results show that expanded ensemble calculations using all-atom molecular dynamics simulations are a valuable and efficient computational tool in predicting absolute binding free energies.

Reliable and accurate prediction of basic pK[Formula: see text] values in nitrogen compounds: the pK[Formula: see text] shift in supramolecular systems as a case study

This article presents a quantitative structure-activity relationship (QSAR) approach for predicting the acid dissociation constant (pK[Formula: see text]) of nitrogenous compounds, including those within supramolecular complexes based on cucurbiturils. The model combines low-cost quantum mechanical calculations with QSAR methodology and linear regressions to achieve accurate predictions for a broad range of nitrogen-containing compounds. The model was developed using a diverse dataset of 130 nitrogenous compounds and exhibits excellent predictive performance, with a high coefficient of determination (R[Formula: see text]) of 0.9905, low standard error (s) of 0.3066, and high Fisher statistic (F) of 2142. The model outperforms existing methods, such as Chemaxon software and previous studies, in terms of accuracy and its ability to handle heterogeneous datasets. External validation on pharmaceutical ingredients, dyes, and supramolecular complexes based on cucurbiturils confirms the reliability of the model. To enhance usability, a script-like tool has been developed, providing a streamlined process for users to access the model. This study represents a significant advancement in pK[Formula: see text] prediction, offering valuable insights for drug design and supramolecular system optimization.

Machine-Learning-Enabled Ligand Screening for Cs/Sr Crystallizing Separation

The reprocessing of spent nuclear fuel is critical for the sustainability of the nuclear energy industry. However, several key separation processes present challenges in this regard, calling for continuous research into next-generation separation materials. Herein, we propose a high-throughput screening framework to improve efficiency in identifying potential ligands that selectively coordinate metal cations of interest in liquid wastes that considers multiple key chemical characteristics, including aqueous solubility, pKa, and coordination bond length. Machine-learning models were designed for the fast and accurate prediction of these characteristics by using graph convolution and transfer-learning techniques. Suitable ligands for Cs/Sr crystallizing separation were identified through the "computational funnel", and several top-ranking, nontoxic, low-cost ligands were selected for experimental verification.

Amperometric Identification of Single Exosomes and Their Dopamine Contents Secreted by Living Cells

Dopamine (DA) is an important neurotransmitter, which not only participates in the regulation of neural processes but also plays critical roles in tumor progression and immunity. However, direct identification of DA-containing exosomes, as well as quantification of DA in single vesicles, is still challenging. Here, we report a nanopipette-assisted method to detect single exosomes and their dopamine contents via amperometric measurement. The resistive-pulse current measured can simultaneously provide accurate information of vesicle translocation and DA contents in single exosomes. Accordingly, DA-containing exosomes secreted from HeLa and PC12 cells under different treatment modes successfully detected the DA encapsulation efficiency and the amount of exosome secretion that distinguish between cell types. Furthermore, a custom machine learning model was constructed to classify the exosome signals from different sources, with an accuracy of more than 99%. Our strategy offers a useful tool for investigating single exosomes and their DA contents, which facilitates the analysis of DA-containing exosomes derived from other untreated or stimulated cells and may open up a new insight to the research of DA biology.

Photoassisted Strategy to Promote Glycerol Electrooxidation to Lactic Acid Coupled with Hydrogen Production

Electrocatalytic oxidation of glycerol (GLY; from a biodiesel byproduct) to lactic acid (LA; the key monomers for polylactic acid; PLA) is considered a sustainable approach for biomass waste upcycling and is coupled with cathodic hydrogen (H₂) production. However, current research still suffer from issues of low current density and low LA selectivity. Herein, we reported a photoassisted electrocatalytic strategy to achieve the selective oxidation of GLY to LA over a gold nanowire (Au NW) catalyst, attaining a high current density of 387 mA cm^-2 at 0.95 V vs RHE, together with a high LA selectivity of 80%, outperforming most of the reported works in the literature. We reveal that the light-assistance strategy plays a dual role, which can both accelerate the reaction rate through the photothermal effect and also promote the adsorption of the middle hydroxyl of GLY over Au NWs to realize the selective oxidation of GLY to LA. As a proof-of-concept, we realized the direct conversion of crude GLY that was extracted from cooking oil to attain LA and coupled it with H₂ production using the developed photoassisted electrooxidation process, revealing the potential of this strategy in practical applications.

Crystallographic Deciphering of Spontaneous Self-Assembly of Achiral Calciphores to Chiral Complexes

Thiapyricins (TPC-A/B, 1 and 2), which are new metallophore scaffolds exhibiting selective divalent cation binding property, were produced in response to metal-deprived conditions by Saccharothrix sp. TRM_47004 isolated from the Lop Nor Salt Lake. TPCs represent a thiazolyl-pyridine skeleton of a calcium-binding natural product, calciphore, owing to the selectivity to calcium ions among diverse metal ions. The thiapyricins exhibited notable co-crystalline characteristics of the apo- and holo-forms with racemic enantiomers comprising a pair of space isomers in a Δ/Λ-form. Therefore, we postulated a mechanism for the four-hierarchical self-assembly of achiral natural products into chiral complexes. Furthermore, their metal-chelating trait aided the adaptation of the host during metal starvation by increasing the production of TPCs. This study presents a structural paradigm of a new calciphore, provides insight into the mechanism of natural product assembly, and highlights the causality between the production of the metallophore and metallic habitats.

Microalgal photoautotrophic growth induces pH decrease in the aquatic environment by acidic metabolites secretion

BACKGROUND

Microalgae can absorb CO₂ during photosynthesis, which causes the aquatic environmental pH to rise. However, the pH is reduced when microalga Euglena gracilis (EG) is cultivated under photoautotrophic conditions. The mechanism behind this unique phenomenon is not yet elucidated.

RESULTS

The present study evaluated the growth of EG, compared to Chlorella vulgaris (CV), as the control group; analyzed the dissolved organic matter (DOM) in the aquatic environment; finally revealed the mechanism of the decrease in the aquatic environmental pH via comparative metabolomics analysis. Although the CV cell density was 28.3-fold that of EG, the secreted-DOM content from EG cell was 49.8-fold that of CV (p-value < 0.001). The main component of EG's DOM was rich in humic acids, which contained more DOM composed of chemical bonds such as N-H, O-H, C-H, C=O, C-O-C, and C-OH than that of CV. Essentially, the 24 candidate biomarkers metabolites secreted by EG into the aquatic environment were acidic substances, mainly lipids and lipid-like molecules, organoheterocyclic compounds, organic acids, and derivatives. Moreover, six potential critical secreted-metabolic pathways were identified.

CONCLUSIONS

This study demonstrated that EG secreted acidic metabolites, resulting in decreased aquatic environmental pH. This study provides novel insights into a new understanding of the ecological niche of EG and the rule of pH change in the microalgae aquatic environment.

An Ensemble Structure and Physiochemical (SPOC) Descriptor for Machine-Learning Prediction of Chemical Reaction and Molecular Properties

Feature representations, or descriptors, are machines' chemical language that largely shapes the prediction capability, generalizability and interpretability of machine learning models. To develop a generally applicable descriptor is highly warranted for chemists to deal with conventional prediction tasks in the context of sparsely distributed and small datasets. Inspired by the chemist's vision on molecules, we presented herein an ensemble descriptor, SPOC, curated on the principles of physical organic chemistry that integrates Structure and Physicochemical property (SPOC) of a molecule. SPOC could be readily constructed by combining molecular fingerprints, representing the structure of a given molecule, and molecular physicochemical properties extracted from RDKit or Mordred molecular descriptors. The applicability of SPOC was fully surveyed in a range of well-structured chemical databases with machine learning tasks varying from regression to classifications.

Comparison of logP and logD correction models trained with public and proprietary data sets

In drug discovery, partition and distribution coefficients, logP and logD for octanol/water, are widely used as metrics of the lipophilicity of molecules, which in turn have a strong influence on the bioactivity and bioavailability of potential drugs. There are a variety of established methods, mostly fragment or atom-based, to calculate logP while logD prediction generally relies on calculated logP and pKa for the estimation of neutral and ionized populations at a given pH. Algorithms such as ClogP have limitations generally leading to systematic errors for chemically related molecules while pKa estimation is generally more difficult due to the interplay of electronic, inductive and conjugation effects for ionizable moieties. We propose an integrated machine learning QSAR modeling approach to predict logD by training the model with experimental data while using ClogP and pKa predicted by commercial software as model descriptors. By optimizing the loss function for the ClogD calculated by the software, we build a correction model that incorporates both descriptors from the software and available experimental logD data. Additionally, we calculate logP from the logD model using the software predicted pKa's. Here, we have trained models using publicly or commercial available logD data to show that this approach can improve on commercial software predictions of lipophilicity. When applied to other logD data sets, this approach extends the domain of applicability of logD and logP predictions over commercial software. Performance of these models favorably compare with models built with a larger set of proprietary logD data.

Rhodium-Catalyzed Stereoselective Deuteration of Benzylic C-H Bonds via Reversible η6 -Coordination

We report a convenient method for benzylic H/D exchange of a wide variety of substrates bearing primary, secondary, or tertiary C-H bonds via a reversible η⁶ -coordination strategy. A doubly cationic [Cp^CF3 Rh^III ]²⁺ catalyst that serves as an arenophile facilitates deprotonation of inert benzylic hydrogen atoms (pK_a >40 in DMSO) without affecting other hydrogen atoms, such as those on aromatic rings or in α-positions of carboxylate groups. Notably, the H/D exchange reactions feature high stereoretention. We demonstrated the potential utility of this method by using it for deuterium labeling of ten pharmaceuticals and their analogues.

In-Situ Electronegativity and the Bridging of Chemical Bonding Concepts

One challenge in chemistry is the plethora of often disparate models for rationalizing the electronic structure of molecules. Chemical concepts abound, but their connections are often frail. This work describes a quantum‐mechanical framework that enables a combination of ideas from three approaches common for the analysis of chemical bonds: energy decomposition analysis (EDA), quantum chemical topology, and molecular orbital (MO) theory. The glue to our theory is the electron energy density, interpretable as one part electrons and one part electronegativity. We present a three‐dimensional analysis of the electron energy density and use it to redefine what constitutes an atom in a molecule. Definitions of atomic partial charge and electronegativity follow in a way that connects these concepts to the total energy of a molecule. The formation of polar bonds is predicted to cause inversion of electronegativity, and a new perspective of bonding in diborane and guanine−cytosine base‐pairing is presented. The electronegativity of atoms inside molecules is shown to be predictive of pK_a.

Stacking Gaussian processes to improve [Formula: see text] predictions in the SAMPL7 challenge

Accurate predictions of acid dissociation constants are essential to rational molecular design in the pharmaceutical industry and elsewhere. There has been much interest in developing new machine learning methods that can produce fast and accurate pKa predictions for arbitrary species, as well as estimates of prediction uncertainty. Previously, as part of the SAMPL6 community-wide blind challenge, Bannan et al. approached the problem of predicting [Formula: see text]s by using a Gaussian process regression to predict microscopic [Formula: see text]s, from which macroscopic [Formula: see text] values can be analytically computed (Bannan et al. in J Comput-Aided Mol Des 32:1165-1177). While this method can make reasonably quick and accurate predictions using a small training set, accuracy was limited by the lack of a sufficiently broad range of chemical space in the training set (e.g., the inclusion of polyprotic acids). Here, to address this issue, we construct a deep Gaussian Process (GP) model that can include more features without invoking the curse of dimensionality. We trained both a standard GP and a deep GP model using a database of approximately 3500 small molecules curated from public sources, filtered by similarity to targets. We tested the model on both the SAMPL6 and more recent SAMPL7 challenge, which introduced a similar lack of ionizable sites and/or environments found between the test set and the previous training set. The results show that while the deep GP model made only minor improvements over the standard GP model for SAMPL6 predictions, it made significant improvements over the standard GP model in SAMPL7 macroscopic predictions, achieving a MAE of 1.5 [Formula: see text].

MolGpka: A Web Server for Small Molecule pKa Prediction Using a Graph-Convolutional Neural Network

pK_a is an important property in the lead optimization process since the charge state of a molecule in physiologic pH plays a critical role in its biological activity, solubility, membrane permeability, metabolism, and toxicity. Accurate and fast estimation of small molecule pK_a is vital during the drug discovery process. We present MolGpKa, a web server for pK_a prediction using a graph-convolutional neural network model. The model works by learning pK_a related chemical patterns automatically and building reliable predictors with learned features. ACD/pK_a data for 1.6 million compounds from the ChEMBL database was used for model training. We found that the performance of the model is better than machine learning models built with human-engineered fingerprints. Detailed analysis shows that the substitution effect on pK_a is well learned by the model. MolGpKa is a handy tool for the rapid estimation of pK_a during the ligand design process. The MolGpKa server is freely available to researchers and can be accessed at https://xundrug.cn/molgpka.