Modeling and predicting chiral stationary phase enantioselectivity: An efficient random forest classifier using an optimally balanced training dataset and an aggregation strategy

Intelligent Recommendation Systems Powered by Consensus Neural Networks: The Ultimate Solution for Finding Suitable Chiral Chromatographic Systems?

The selection of suitable combinations of chiral stationary phases (CSPs) and mobile phases (MPs) for the enantioresolution of chiral compounds is a complex issue that often requires considerable experimental effort and can lead to significant waste. Linking the structure of a chiral compound to a CSP/MP system suitable for its enantioseparation can be an effective solution to this problem. In this study, we evaluate algorithmic tools for this purpose. Our proposed consensus model, which uses multiple optimized artificial neural networks (ANNs), shows potential as an intelligent recommendation system (IRS) for ranking chromatographic systems suitable for the enantioresolution of chiral compounds with different molecular structures. To evaluate the IRS potential in a proof-of-concept stage, 56 structural descriptors for 56 structurally unrelated chiral compounds across 14 different families are considered. Chromatographic systems under study comprise 7 cellulose and amylose derivative CSPs and acetonitrile or methanol aqueous MPs (14 chromatographic systems in all). The ANNs are optimized using a fit-for-purpose version of the chaotic neural network algorithm with competitive learning (CCLNNA), a novel approach not previously applied in the chemical domain. CCLNNA is adapted to define the inner ANN complexity and perform feature selection of the structural descriptors. A customized target function evaluates the correctness of recommending the appropriate CSP/MP system. The ANN-consensus model exhibits no advisory failures and requires only an experimental attempt to verify the IRS recommendation for complete enantioresolution. This outstanding performance highlights its potential to effectively resolve this problem.

Expanding the Horizons of Machine Learning in Nanomaterials to Chiral Nanostructures

Machine learning holds significant research potential in the field of nanotechnology, enabling nanomaterial structure and property predictions, facilitating materials design and discovery, and reducing the need for time-consuming and labor-intensive experiments and simulations. In contrast to their achiral counterparts, the application of machine learning for chiral nanomaterials is still in its infancy, with a limited number of publications to date. This is despite the great potential of machine learning to advance the development of new sustainable chiral materials with high values of optical activity, circularly polarized luminescence, and enantioselectivity, as well as for the analysis of structural chirality by electron microscopy. In this review, an analysis of machine learning methods used for studying achiral nanomaterials is provided, subsequently offering guidance on adapting and extending this work to chiral nanomaterials. An overview of chiral nanomaterials within the framework of synthesis-structure-property-application relationships is presented and insights on how to leverage machine learning for the study of these highly complex relationships are provided. Some key recent publications are reviewed and discussed on the application of machine learning for chiral nanomaterials. Finally, the review captures the key achievements, ongoing challenges, and the prospective outlook for this very important research field.

Enhanced Structure-Based Prediction of Chiral Stationary Phases for Chromatographic Enantioseparation from 3D Molecular Conformations

The accurate prediction of suitable chiral stationary phases (CSPs) for resolving the enantiomers of a given compound poses a significant challenge in chiral chromatography. Previous attempts at developing machine learning models for structure-based CSP prediction have primarily relied on 1D SMILES strings [the simplified molecular-input line-entry system (SMILES) is a specification in the form of a line notation for describing the structure of chemical species using short ASCII strings] or 2D graphical representations of molecular structures and have met with only limited success. In this study, we apply the recently developed 3D molecular conformation representation learning algorithm, which uses rapid conformational analysis and point clouds of atom positions in the 3D space, enabling efficient chemical structure-based machine learning. By harnessing the power of the rapid 3D molecular representation learning and a data set comprising over 300,000 chromatographic enantioseparation records sourced from the literature, our models afford notable improvements for the chemical structure-based choice of appropriate CSP for enantioseparation, paving the way for more efficient and informed decision-making in the field of chiral chromatography.

Recent progress on chiral extractants for enantioselective liquid-liquid extraction

As the demand for enantiopure compounds increases, chiral separation has become increasingly important in many fields. Enantioselective liquid-liquid extraction is an up-and-coming technology for enantiomeric separation because it is highly efficient and easy to be scaled up. The key factor for enantioselective liquid-liquid extraction is the development of novel chiral extractants with high enantiorecognition performance. With successful studies on catalytically active metal complexes as chiral extractants, novel chiral extractants can be screened and designed from the field of asymmetric catalysis. Chiral ionic liquids, sulfobutylether-β-cyclodextrins bonded magnetic nanoparticles and 2,2',3,3'-tetrahydro-1,1'-spirobi[indene]-7,7'-diol (SPINOL) based phosphoric acid host show unique potential ability in enantioselective liquid-liquid extraction and they deserve further study. Brief principles, extraction equipment and solvent systems in enantioselective liquid-liquid extraction are presented in the present paper, and recent progress in development of new chiral extractants in the past decade is mainly reviewed, including metal complexes, cyclodextrins, ionic liquids, tartrate acids and crown ethers.

Recent advances in chiral selectors immobilization and chiral mobile phase additives in liquid chromatographic enantio-separations: A review

For decades now, the separation of chiral enantiomers of drugs has been gaining the interest and attention of researchers. In 1991, the first guidelines for development of chiral drugs were firstly released by the US-FDA. Since then, the development in chromatographic enantioseparation tools has been fast and variable, aiming at creating a suitable environment where the physically and chemically identical enantiomers can be separated. Among those tools, the immobilization of chiral selectors (CS) on different stationary phases and the chiral mobile phase additives (CMPA) which have been progressed and studied extensively. This review article highlights the major advances in immobilization of CS together with their different recognition mechanisms as well as CMPA as a cheaper and successful alternative for chiral stationary phases. Moreover, the role of molecular modeling tool as a pre-step in the choice of CS for evaluating possible interactions with different ligands has been pointed up. Illustrations of reported methods and updates for immobilized CS and CMPA have been included.

New mathematical measures for apprehending complexity of chiral molecules using information entropy

In this paper, we present several new theoretical measures based on information entropy that can be used to analyze the information content of a chiral molecule. Starting from a differentiation between "chiral" and "achiral" portions in a chiral molecule, we define a new concept that allows us to quantify the complexity of chiral constitutional 2D-isomers of C₁₀ to C₂₀ alkanes. Various new chiral and achiral information measures founded on joint entropy, mutual information, and conditional entropy are presented providing an access to a set of regression equations. Then, introducing a case-based measure of entropy, we demonstrate that the distribution of the chiral complexity in these molecules is mostly skewed-right: 60% of the chiral isomers follow a 60/40 distribution rule, which indicates a concentration of chiral complexity in a small number of topological features. Furthermore, by replacing 2D topological distances by 3D distances, the application of these new information measures goes from conformational to racemization and deracemization studies. Interestingly, when the geometrical distances between atoms and the chiral center(s) are taken into account when determining the chiral information entropy, one can observe a significative Pearson correlation coefficient (R = 0.70) between the chiral entropy of 3D molecules and the continuous chirality measure. Finally, we show that our approach is applicable to almost any type of chiral organic chemical structures if in the entropy equation, atoms are represented by their electrotopological state (E-state) index instead of connectivity.

Enantioselectivity in Drug Pharmacokinetics and Toxicity: Pharmacological Relevance and Analytical Methods

Enzymes, receptors, and other binding molecules in biological processes can recognize enantiomers as different molecular entities, due to their different dissociation constants, leading to diverse responses in biological processes. Enantioselectivity can be observed in drugs pharmacodynamics and in pharmacokinetic (absorption, distribution, metabolism, and excretion), especially in metabolic profile and in toxicity mechanisms. The stereoisomers of a drug can undergo to different metabolic pathways due to different enzyme systems, resulting in different types and/or number of metabolites. The configuration of enantiomers can cause unexpected effects, related to changes as unidirectional or bidirectional inversion that can occur during pharmacokinetic processes. The choice of models for pharmacokinetic studies as well as the subsequent data interpretation must also be aware of genetic factors (such as polymorphic metabolic enzymes), sex, patient age, hepatic diseases, and drug interactions. Therefore, the pharmacokinetics and toxicity of a racemate or an enantiomerically pure drug are not equal and need to be studied. Enantioselective analytical methods are crucial to monitor pharmacokinetic events and for acquisition of accurate data to better understand the role of the stereochemistry in pharmacokinetics and toxicity. The complexity of merging the best enantioseparation conditions with the selected sample matrix and the intended goal of the analysis is a challenge task. The data gathered in this review intend to reinforce the importance of the enantioselectivity in pharmacokinetic processes and reunite innovative enantioselective analytical methods applied in pharmacokinetic studies. An assorted variety of methods are herein briefly discussed.

Chiral chromatography method screening strategies: Past, present and future

Method screening is an integral part of chromatographic method development for the separation of racemates. Due to the highly complex retention mechanism of a chiral stationary-phase, it is often difficult, if not impossible, to device predefined method-development steps that can be successfully applied to a wide group of molecules. The standard approach is to evaluate or screen a series of stationary and mobile-phase combinations to increase the chances of detecting a suitable separation condition. Such a process is often the rate-limiting step for high-throughput analyses and purification workflows. To address the problem, several solutions and strategies have been proposed over the years for reduction of net method-screening time. Some of the strategies have been adopted in practice while others remained confined in the literature. The main objective of this review is to revisit, critically discuss and compile the solutions published over the last two decades. We expect that making the diverse set of solutions available in a single document will help assessing the adequacy of existing screening protocols in laboratories conducting chiral separation.

Non-Pessimistic Predictions of the Distributions and Suitability of Metasequoia glyptostroboides under Climate Change Using a Random Forest Model

Metasequoia glyptostroboides Hu & W. C. Cheng, which is a remarkable rare relict plant, has gradually been reduced to its current narrow range due to climate change. Understanding the comprehensive distribution of M. glyptostroboides under climate change on a large spatio-temporal scale is of great significance for determining its forest adaptation. In this study, based on 394 occurrence data and 10 bioclimatic variables, the global potential distribution of M. glyptostroboides under eight different climate scenarios (i.e., the past three, the current one, and the next four) from the Quaternary glacial to the future was simulated by a random forest model built with the biomod2 package. The key bioclimatic variables affecting the distribution of M. glyptostroboides are BIO2 (mean diurnal range), BIO1 (annual mean temperature), BIO9 (mean temperature of driest quarter), BIO6 (min temperature of coldest month), and BIO18 (precipitation of warmest quarter). The result indicates that the temperature affects the potential distribution of M. glyptostroboides more than the precipitation. A visualization of the results revealed that the current relatively suitable habitats of M. glyptostroboides are mainly distributed in East Asia and Western Europe, with a total area of approximately 6.857 × 106 km2. With the intensification of global warming in the future, the potential distribution and the suitability of M. glyptostroboides have a relatively non-pessimistic trend. Whether under the mild (RCP4.5) and higher (RCP8.5) emission scenarios, the total area of suitable habitats will be wider than it is now by the 2070s, and the habitat suitability will increase to varying degrees within a wide spatial range. After speculating on the potential distribution of M. glyptostroboides in the past, the glacial refugia of M. glyptostroboides were inferred, and projections regarding the future conditions of these places are expected to be optimistic. In order to better protect the species, the locations of its priority protected areas and key protected areas, mainly in Western Europe and East Asia, were further identified. Our results will provide theoretical reference for the long-term management of M. glyptostroboides, and can be used as background information for the restoration of other endangered species in the future.

Role of simple descriptors and applicability domain in predicting change in protein thermostability

The melting temperature (Tm) of a protein is the temperature at which half of the protein population is in a folded state. Therefore, Tm is a measure of the thermostability of a protein. Increasing the Tm of a protein is a critical goal in biotechnology and biomedicine. However, predicting the change in melting temperature (dTm) due to mutations at a single residue is difficult because it depends on an intricate balance of forces. Existing methods for predicting dTm have had similar levels of success using generally complex models. We find that training a machine learning model with a simple set of easy to calculate physicochemical descriptors describing the local environment of the mutation performed as well as more complicated machine learning models and is 2-6 orders of magnitude faster. Importantly, unlike in most previous publications, we perform a blind prospective test on our simple model by designing 96 variants of a protein not in the training set. Results from retrospective and prospective predictions reveal the limited applicability domain of each model. This study highlights the current deficiencies in the available dTm dataset and is a call to the community to systematically design a larger and more diverse experimental dataset of mutants to prospectively predict dTm with greater certainty.