What is Wrong with Quantitative Structure–Property Relations Models Based on Three-Dimensional Descriptors?

From molecular descriptors to the developmental toxicity prediction of pesticides/veterinary drugs/bio-pesticides against zebrafish embryo: Dual computational toxicological approaches for prioritization

The escalating introduction of pesticides/veterinary drugs into the environment has necessitated a rapid evaluation of their potential risks to ecosystems and human health. The developmental toxicity of pesticides/veterinary drugs was less explored, and much less the large-scale predictions for untested pesticides, veterinary drugs and bio-pesticides. Alternative methods like quantitative structure-activity relationship (QSAR) are promising because their potential to ensure the sustainable and safe use of these chemicals. We collected 133 pesticides and veterinary drugs with half-maximal active concentration (AC50) as the zebrafish embryo developmental toxicity endpoint. The QSAR model development adhered to rigorous OECD principles, ensuring that the model possessed good internal robustness (R2 > 0.6 and QLOO2 > 0.6) and external predictivity (Rtest2 > 0.7, QFn2 >0.7, and CCCtest > 0.85). To further enhance the predictive performance of the model, a quantitative read-across structure-activity relationship (q-RASAR) model was established using the combined set of RASAR and 2D descriptors. Mechanistic interpretation revealed that dipole moment, the presence of C-O fragment at 10 topological distance, molecular size, lipophilicity, and Euclidean distance (ED)-based RA function were main factors influencing toxicity. For the first time, the established QSAR and q-RASAR models were combined to prioritize the developmental toxicity of a vast array of true external compounds (pesticides/veterinary drugs/bio-pesticides) lacking experimental values. The prediction reliability of each query molecule was evaluated by leverage approach and prediction reliability indicator. Overall, the dual computational toxicology models can inform decision-making and guide the design of new pesticides/veterinary drugs with improved safety profiles.

Deep learning for low-data drug discovery: Hurdles and opportunities

Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches-which are notoriously 'data-hungry'-might fail to live up to their promise. Developing novel approaches to leverage the power of deep learning in low-data scenarios is sparking great attention, and future developments are expected to propel the field further. This mini-review provides an overview of recent low-data-learning approaches in drug discovery, analyzing their hurdles and advantages. Finally, we venture to provide a forecast of future research directions in low-data learning for drug discovery.

Development of a High-Accuracy Statistical Model to Identify the Key Parameter for Methane Adsorption in Metal-Organic Frameworks

The geometrical and topological features of metal-organic frameworks (MOFs) play an important role in determining their ability to capture and store methane (CH4). Methane is a greenhouse gas that has been shown to be more dangerous in terms of contributing to global warming than carbon dioxide (CO2), especially in the first 20 years of its release into the atmosphere. Its accelerated emission increases the rate of global temperature increase and needs to be addressed immediately. Adsorption processes have been shown to be effective and efficient in mitigating methane emissions from the atmosphere by providing an enormous surface area for methane storage. Among all the adsorbents, MOFs were shown to be the best adsorbents for methane adsorption due to their higher favorable steric interactions, the presence of binding sites such as open metal sites, and hydrophobic pockets. These features may not necessarily be present in carbonaceous materials and zeolites. Although many studies have suggested that the main reason for the increased storage efficiencies in terms of methane in the MOFs is the high surface area, there was some evidence in certain research works that methane storage performance, as measured by uptakes and deliveries in gravimetric and volumetric units, was higher for certain MOFs with a lower surface area. This prompted us to find out the most significant property of the MOF, whether it be material-based or pore-based, that has the maximum influence on methane uptake and delivery, using a comprehensive statistical approach that has not previously been employed in the methane storage literature. The approach in our study employed various chemometric techniques, including simple and multiple linear regression (SLR and MLR), combined with different types of multicollinearity diagnostics, partial correlations, standardized coefficients, and changes in regression coefficient estimates and their standard errors, applied to both the SLR and MLR models. The main advantages of this statistical approach are that it is quicker, provides a deeper insight into experimental data, and highlights a single, most important, parameter for MOF design and tuning that can predict and maximize the output storage and capture performance. The significance of our approach is that it was modeled purely based on experimental data, which will capture the real system, as opposed to the molecular simulations employed previously in the literature. Our model included data from ~80 MOFs and eight properties related to the material, pore, and thermodynamics (isosteric adsorption energy). Successful attempts to model the methane sorption process have previously been conducted using thermodynamic approaches and by developing adsorption performance indicators, but these are either too complex or time-consuming and their data covers fewer than 10 MOFs and a maximum of three MOF properties. By comparing the statistical metrics between the models, the most important and statistically significant property of the MOF was determined, which will be crucial when designing MOFs for use in storing and delivering methane.

Predicting the Surface Tension of Deep Eutectic Solvents: A Step Forward in the Use of Greener Solvents

Deep eutectic solvents (DES) are an important class of green solvents that have been developed as an alternative to toxic solvents. However, the large-scale industrial application of DESs requires fine-tuning their physicochemical properties. Among others, surface tension is one of such properties that have to be considered while designing novel DESs. In this work, we present the results of a detailed evaluation of Quantitative Structure-Property Relationships (QSPR) modeling efforts designed to predict the surface tension of DESs, following the Organization for Economic Co-operation and Development (OECD) guidelines. The data set used comprises a large number of structurally diverse binary DESs and the models were built systematically through rigorous validation methods, including ‘mixtures-out’- and ‘compounds-out’-based data splitting. The most predictive individual QSPR model found is shown to be statistically robust, besides providing valuable information about the structural and physicochemical features responsible for the surface tension of DESs. Furthermore, the intelligent consensus prediction strategy applied to multiple predictive models led to consensus models with similar statistical robustness to the individual QSPR model. The benefits of the present work stand out also from its reproducibility since it relies on fully specified computational procedures and on publicly available tools. Finally, our results not only guide the future design and screening of novel DESs with a desirable surface tension but also lays out strategies for efficiently setting up silico-based models for binary mixtures.

Density of Deep Eutectic Solvents: The Path Forward Cheminformatics-Driven Reliable Predictions for Mixtures

Deep eutectic solvents (DES) are often regarded as greener sustainable alternative solvents and are currently employed in many industrial applications on a large scale. Bearing in mind the industrial importance of DES—and because the vast majority of DES has yet to be synthesized—the development of cheminformatic models and tools efficiently profiling their density becomes essential. In this work, after rigorous validation, quantitative structure-property relationship (QSPR) models were proposed for use in estimating the density of a wide variety of DES. These models were based on a modelling dataset previously employed for constructing thermodynamic models for the same endpoint. The best QSPR models were robust and sound, performing well on an external validation set (set up with recently reported experimental density data of DES). Furthermore, the results revealed structural features that could play crucial roles in ruling DES density. Then, intelligent consensus prediction was employed to develop a consensus model with improved predictive accuracy. All models were derived using publicly available tools to facilitate easy reproducibility of the proposed methodology. Future work may involve setting up reliable, interpretable cheminformatic models for other thermodynamic properties of DES and guiding the design of these solvents for applications.

Dapsone is not a Pharmacodynamic Lead Compound for its Aryl Derivatives

BACKGROUND

The relatedness between the linear equations of thermodynamics and QSAR was studied thanks to the recently elucidated crystal structure complexes between sulfonamide pterin conjugates and dihydropteroate synthase (DHPS) together with a published set of thirty- six synthetic dapsone derivatives with their reported entropy-driven activity data. Only a few congeners were slightly better than dapsone.

OBJECTIVE

Our study aimed at demonstrating the applicability of thermodynamic QSAR and to shed light on the mechanistic aspects of sulfone binding to DHPS.

METHODS

To this end ligand docking to DHPS, quantum mechanical properties, 2D- and 3D-QSAR as well as Principle Component Analysis (PCA) were carried out.

RESULTS

The short aryl substituents of the docked pterin-sulfa conjugates were outward oriented into the solvent space without interacting with target residues which explains why binding enthalpy (ΔH) did not correlate with potency. PCA revealed how chemically informative descriptors are evenly loaded on the first three PCs (interpreted as ΔG, ΔH and ΔS), while chemically cryptic ones reflected higher dimensional (complex) loadings.

CONCLUSION

It is safe to utter that synthesis efforts to introduce short side chains for aryl derivatization of the dapsone scaffold have failed in the past. On theoretical grounds we provide computed evidence why dapsone is not a pharmacodynamic lead for drug profiling because enthalpic terms do not change significantly at the moment of ligand binding to target.

In vivo toxicity of nitroaromatic compounds to rats: QSTR modelling and interspecies toxicity relationship with mouse

Nitroaromatic compounds (NACs) in the environment can cause serious public health and environmental problems due to their potential toxicity. This study established quantitative structure-toxicity relationship (QSTR) models for the acute oral toxicity of NACs towards rats following the stringent OECD principles for QSTR modelling. All models were assessed by various internationally accepted validation metrics and the OECD criteria. The best QSTR model contains seven simple and interpretable 2D descriptors with defined physicochemical meaning. Mechanistic interpretation indicated that van der Waals surface area, presence of C-F at topological distance 6, heteroatom content and frequency of C-N at topological distance 9 are main factors responsible for the toxicity of NACs. This proposed model was successfully applied to a true external set (295 compounds), and prediction reliability was analysed and discussed. Moreover, the rat-mouse and mouse-rat interspecies quantitative toxicity-toxicity relationship (iQTTR) models were also constructed, validated and employed in toxicity prediction for true external sets consisting of 67 and 265 compounds, respectively. These models showed good external predictivity that can be used to rapidly predict the rat oral acute toxicity of new or untested NACs falling within the applicability domain of the models, thus being beneficial in environmental risk assessment and regulatory purposes.

Comparative Study of Quinolines and Tetrahydroquinolines Sorption on Various Sorbents from Water-Acetonitrile Solutions

The retention of 16 quinoline and tetrahydroquinoline derivatives was investigated under liquid chromatography conditions using porous graphitized carbon (PGC), octadecyl silica (ODS) and hypercrosslinked polystyrene (HCLP) stationary phases. For most of the analytes, retention on PGC was greater than on ODS, while retention on HCLP was even greater than on both ODS and PGC. The non-linearity of retention dependencies on acetonitrile content in the eluent was observed for compounds containing carboxy, hydrazo and methoxy groups. The relationships between quinolines structure and their retention factors were investigated. It was found that sorption on different sorbents correlated with different descriptors. Retention on ODS was found to be highly correlated with lipophilicity only while on HCLP it depended on both lipophilicity and polarizability of the sorbates. The feature of PGC was a good correlation of retention factors with topological and geometrical parameters. Additionally, ability of PGC to form OH…π bonds with hydroxymethylquinolines was found. The observed regularities allow one to rationally optimize the chromatographic analysis of structurally similar compounds, which is very important for bioactive substances.

Computational modeling approaches to quantitative structure-binding kinetics relationships in drug discovery

Simple comparative correlation analyses and quantitative structure-kinetics relationship (QSKR) models highlight the interplay of kinetic rates and binding affinity as an essential feature in drug design and discovery. The choice of the molecular series, and their structural variations, used in QSKR modeling is fundamental to understanding the mechanistic implications of ligand and/or drug-target binding and/or unbinding processes. Here, we discuss the implications of linear correlations between kinetic rates and binding affinity constants and the relevance of the computational approaches to QSKR modeling.

2D and 3D QSAR Studies on a Series of Antichagasic Fenarimol Derivatives

Chagas disease is one of the most important neglected tropical diseases. Endemic in Latin America, the disease is a global public health problem, affecting several countries in North America, Europe, Asia and Oceania. The disease affects around 8-10 million people worldwide and the limited treatments available present low efficacy and severe side effects, highlighting the urgent need for new therapeutic options. In this work, the authors developed QSAR models for a series of fenarimol derivatives exhibiting anti-T. cruzi activity. The models were constructed using the Hologram QSAR (HQSAR), Comparative Molecular Field Analysis (CoMFA) and Comparative Molecular Similarity Indices Analysis (CoMSIA) methods. The QSAR models presented substantial predictive ability for a series of test set compounds (HQSAR, r2pred = 0.66; CoMFA, r2pred = 0.82; and CoMSIA, r2pred = 0.76), and were valuable to identify key structural features related to the observed trypanocidal activity. The results reported herein are useful for the design of novel derivatives having improved antichagasic properties.

Antiprotozoal Nitazoxanide Derivatives: Synthesis, Bioassays and QSAR Study Combined with Docking for Mechanistic Insight

In view of the serious health problems concerning infectious diseases in heavily populated areas, we followed the strategy of lead compound diversification to evaluate the near-by chemical space for new organic compounds. To this end, twenty derivatives of nitazoxanide (NTZ) were synthesized and tested for activity against Entamoeba histolytica parasites. To ensure drug-likeliness and activity relatedness of the new compounds, the synthetic work was assisted by a quantitative structure-activity relationships study (QSAR). Many of the inherent downsides – well-known to QSAR practitioners – we circumvented thanks to workarounds which we proposed in prior QSAR publication. To gain further mechanistic insight on a molecular level, ligand-enzyme docking simulations were carried out since NTZ is known to inhibit the protozoal pyruvate ferredoxin oxidoreductase (PFOR) enzyme as its biomolecular target.

Examining the predictive accuracy of the novel 3D N-linear algebraic molecular codifications on benchmark datasets

BACKGROUND

Recently, novel 3D alignment-free molecular descriptors (also known as QuBiLS-MIDAS) based on two-linear, three-linear and four-linear algebraic forms have been introduced. These descriptors codify chemical information for relations between two, three and four atoms by using several (dis-)similarity metrics and multi-metrics. Several studies aimed at assessing the quality of these novel descriptors have been performed. However, a deeper analysis of their performance is necessary. Therefore, in the present manuscript an assessment and statistical validation of the performance of these novel descriptors in QSAR studies is performed.

RESULTS

To this end, eight molecular datasets (angiotensin converting enzyme, acetylcholinesterase inhibitors, benzodiazepine receptor, cyclooxygenase-2 inhibitors, dihydrofolate reductase inhibitors, glycogen phosphorylase b, thermolysin inhibitors, thrombin inhibitors) widely used as benchmarks in the evaluation of several procedures are utilized. Three to nine variable QSAR models based on Multiple Linear Regression are built for each chemical dataset according to the original division into training/test sets. Comparisons with respect to leave-one-out cross-validation correlation coefficients[Formula: see text] reveal that the models based on QuBiLS-MIDAS indices possess superior predictive ability in 7 of the 8 datasets analyzed, outperforming methodologies based on similar or more complex techniques such as: Partial Least Square, Neural Networks, Support Vector Machine and others. On the other hand, superior external correlation coefficients[Formula: see text] are attained in 6 of the 8 test sets considered, confirming the good predictive power of the obtained models. For the [Formula: see text] values non-parametric statistic tests were performed, which demonstrated that the models based on QuBiLS-MIDAS indices have the best global performance and yield significantly better predictions in 11 of the 12 QSAR procedures used in the comparison. Lastly, a study concerning to the performance of the indices according to several conformer generation methods was performed. This demonstrated that the quality of predictions of the QSAR models based on QuBiLS-MIDAS indices depend on 3D structure generation method considered, although in this preliminary study the results achieved do not present significant statistical differences among them.

CONCLUSIONS

As conclusions it can be stated that the QuBiLS-MIDAS indices are suitable for extracting structural information of the molecules and thus, constitute a promissory alternative to build models that contribute to the prediction of pharmacokinetic, pharmacodynamics and toxicological properties on novel compounds.Graphical abstractComparative graphical representation of the performance of the novel QuBiLS-MIDAS 3D-MDs with respect to other methodologies in QSAR modeling of eight chemical datasets.

Robust molecular representations for modelling and design derived from atomic partial charges

Ab initio partial charge schemes are identified for molecular modelling purposes, and potential pitfalls of their application are discussed.

Multivariate linear QSPR/QSAR models: Rigorous evaluation of variable selection for PLS

Basic chemometric methods for making empirical regression models for QSPR/QSAR are briefly described from a user's point of view. Emphasis is given to PLS regression, simple variable selection and a careful and cautious evaluation of the performance of PLS models by repeated double cross validation (rdCV). A demonstration example is worked out for QSPR models that predict gas chromatographic retention indices (values between 197 and 504 units) of 209 polycyclic aromatic compounds (PAC) from molecular descriptors generated by Dragon software. Most favorable models were obtained from data sets containing also descriptors from 3D structures with all H-atoms (computed by Corina software), using stepwise variable selection (reducing 2688 descriptors to a subset of 22). The final QSPR model has typical prediction errors for the retention index of ±12 units (95% tolerance interval, for test set objects). Programs and data are provided as supplementary material for the open source R software environment.