Use of 13C NMR chemical shift as QSAR/QSPR descriptor

SpectraFP: a new spectra-based descriptor to aid in cheminformatics, molecular characterization and search algorithm applications

We have developed an algorithm to generate a new spectra-based descriptor, called SpectraFP, in order to digitalize the chemical shifts of ¹³C NMR spectra, as well as potentially important data from other spectroscopic techniques. This descriptor is a fingerprint vector with defined sizes and values of 0 and 1, with the ability to correct chemical shift fluctuations. To explore the applicability of SpectraFP, we outlined two application scenarios: (1) the prediction of six functional groups by machine learning (ML) models and (2) the search for structures based on the similarity between the query spectrum and spectra in an experimental database, both in the SpectraFP format. For each functional group, five ML models were built and validated following the OECD principles: internal and external validations, applicability domains, and mechanistic interpretations. All the models resulted in high goodness-of-fit for the training and test sets with MCC respectively between 0.626 and 0.909 and 0.653 and 0.917, and J ranging from 0.812 to 0.957 and 0.825 to 0.961. Using the SHAP (SHapley Additive exPlanations) approach, the mechanistic interpretations of the models were explored; the results indicated that the most important variables for model decision making were coherent with the expected chemical shifts for each functional group. Several metrics, including Tanimoto, geometric, arithmetic, and Tversky, can be used to perform the similarity calculation for the search algorithm. This algorithm can also incorporate additional variables, such as the correction parameter and the difference between the amount of signals in the query spectrum and the database spectra, while preserving its high performance speed. We hope that our descriptor can link information from spectroscopic/spectrometric techniques with ML models to expand the possibilities in understanding the field of cheminformatics. All databases and algorithms developed for this work are open sources and freely accessible.

Quantitative Structure-Toxicity Relationship in Bioactive Molecules from a Conceptual DFT Perspective

The preclinical drug discovery stage often requires a large amount of costly and time-consuming experiments using huge sets of chemical compounds. In the last few decades, this process has undergone significant improvements by the introduction of quantitative structure-activity relationship (QSAR) modelling that uses a certain percentage of experimental data to predict the biological activity/property of compounds with similar structural skeleton and/or containing a particular functional group(s). The use of machine learning tools along with it has made life even easier for pharmaceutical researchers. Here, we discuss the toxicity of certain sets of bioactive compounds towards Pimephales promelas and Tetrahymena pyriformis in terms of the global conceptual density functional theory (CDFT)-based descriptor, electrophilicity index (ω). We have compared the results with those obtained by using the commonly used hydrophobicity parameter, logP (where P is the n-octanol/water partition coefficient), considering the greater ease of computing the ω descriptor. The Human African trypanosomiasis (HAT) curing activity of 32 pyridyl benzamide derivatives is also studied against Tryphanosoma brucei. In this review article, we summarize these multiple linear regression (MLR)-based QSAR studies in terms of electrophilicity (ω, ω2) and hydrophobicity (logP, (logP)2) parameters.

Materials informatics approach using domain modelling for exploring structure-property relationships of polymers

In the development of polymer materials, it is an important issue to explore the complex relationships between domain structure and physical properties. In the domain structure analysis of polymer materials, ¹H-static solid-state NMR (ssNMR) spectra can provide information on mobile, rigid, and intermediate domains. But estimation of domain structure from its analysis is difficult due to the wide overlap of spectra from multiple domains. Therefore, we have developed a materials informatics approach that combines the domain modeling (http://dmar.riken.jp/matrigica/) and the integrated analysis of meta-information (the elements, functional groups, additives, and physical properties) in polymer materials. Firstly, the ¹H-static ssNMR data of 120 polymer materials were subjected to a short-time Fourier transform to obtain frequency, intensity, and T₂ relaxation time for domains with different mobility. The average T₂ relaxation time of each domain is 0.96 ms for Mobile, 0.55 ms for Intermediate (Mobile), 0.32 ms for Intermediate (Rigid), and 0.11 ms for Rigid. Secondly, the estimated domain proportions were integrated with meta-information such as elements, functional group and thermophysical properties and was analyzed using a self-organization map and market basket analysis. This proposed method can contribute to explore structure–property relationships of polymer materials with multiple domains.

DFT based QSAR study on quinolone-triazole derivatives as antibacterial agents

QSAR modeling was performed on 39 quinolone-triazole derivatives against gram-positive Staphylococcus aureus and gram-negative Pseudomonas aeruginosa bacteria. The molecular structures were optimized using the DFT/B3LYP method and 6-31 G basis set. Molecular descriptors were extracted using quantum mechanical calculations. The hierarchical cluster analysis was performed for a rational subset division. The initial dataset was divided into calibration and validation sets, and modeling was done by stepwise MLR method for each of the two bacteria. Internal and external validation methods confirmed the robustness and predictability of the obtained models. According to the obtained model for S. aureus (R² = 0.889, R²_ext = 0.938, Q²_LOO = 0.853), the four descriptors- partial atomic charges for the N1 atom in triazole and C7 of the quinolone nucleus, 4-carbonyl bond length, and ¹³C-NMR chemical shift of 3-carboxylic acid- were found to be the descriptors controlling the activity. According to the obtained model for P. aeruginosa (R² = 0.957, R²_ext = 0.923, Q²_LOO = 0.909), the O atom's partial charge in carbonyl, LUMO-HOMO energy gap, and logP were found to be the descriptors having the highest correlation with the antibacterial activity. Finally, some new compounds with higher activities were designed and proposed.

Real-time prediction of 1H and 13C chemical shifts with DFT accuracy using a 3D graph neural network

Nuclear magnetic resonance (NMR) is one of the primary techniques used to elucidate the chemical structure, bonding, stereochemistry, and conformation of organic compounds. The distinct chemical shifts in an NMR spectrum depend upon each atom's local chemical environment and are influenced by both through-bond and through-space interactions with other atoms and functional groups. The in silico prediction of NMR chemical shifts using quantum mechanical (QM) calculations is now commonplace in aiding organic structural assignment since spectra can be computed for several candidate structures and then compared with experimental values to find the best possible match. However, the computational demands of calculating multiple structural- and stereo-isomers, each of which may typically exist as an ensemble of rapidly-interconverting conformations, are expensive. Additionally, the QM predictions themselves may lack sufficient accuracy to identify a correct structure. In this work, we address both of these shortcomings by developing a rapid machine learning (ML) protocol to predict ¹H and ¹³C chemical shifts through an efficient graph neural network (GNN) using 3D structures as input. Transfer learning with experimental data is used to improve the final prediction accuracy of a model trained using QM calculations. When tested on the CHESHIRE dataset, the proposed model predicts observed ¹³C chemical shifts with comparable accuracy to the best-performing DFT functionals (1.5 ppm) in around 1/6000 of the CPU time. An automated prediction webserver and graphical interface are accessible online at http://nova.chem.colostate.edu/cascade/. We further demonstrate the model in three applications: first, we use the model to decide the correct organic structure from candidates through experimental spectra, including complex stereoisomers; second, we automatically detect and revise incorrect chemical shift assignments in a popular NMR database, the NMRShiftDB; and third, we use NMR chemical shifts as descriptors for determination of the sites of electrophilic aromatic substitution.

From quantum chemical and experimental NMR data, a 3D graph neural network, CASCADE, has been developed to predict carbon and proton chemical shifts. Stereoisomers and conformers of organic molecules can be correctly distinguished.

The exposome paradigm to predict environmental health in terms of systemic homeostasis and resource balance based on NMR data science

The environment, from microbial ecosystems to recycled resources, fluctuates dynamically due to many physical, chemical and biological factors, the profile of which reflects changes in overall state, such as environmental illness caused by a collapse of homeostasis. To evaluate and predict environmental health in terms of systemic homeostasis and resource balance, a comprehensive understanding of these factors requires an approach based on the "exposome paradigm", namely the totality of exposure to all substances. Furthermore, in considering sustainable development to meet global population growth, it is important to gain an understanding of both the circulation of biological resources and waste recycling in human society. From this perspective, natural environment, agriculture, aquaculture, wastewater treatment in industry, biomass degradation and biodegradable materials design are at the forefront of current research. In this respect, nuclear magnetic resonance (NMR) offers tremendous advantages in the analysis of samples of molecular complexity, such as crude bio-extracts, intact cells and tissues, fibres, foods, feeds, fertilizers and environmental samples. Here we outline examples to promote an understanding of recent applications of solution-state, solid-state, time-domain NMR and magnetic resonance imaging (MRI) to the complex evaluation of organisms, materials and the environment. We also describe useful databases and informatics tools, as well as machine learning techniques for NMR analysis, demonstrating that NMR data science can be used to evaluate the exposome in both the natural environment and human society towards a sustainable future.

Use of 13C-NMR Chemical Shifts; Application of Principal Component Analysis for Categorizing Structurally Similar Methoxyflavones and Correlation Analysis between Chemical Shifts and Cytotoxicity

The ¹³C-NMR spectral data for the 15-carbon flavonoid skeleton in eleven methoxyflavones isolated from Kaempferia parviflora (Zingiberaceae) were processed by principal component analysis (PCA). Based on the PCA score plots, the methoxyflavones were categorized into three groups according to their structural features. The cytotoxicities of the methoxyflavones toward 3T3-L1 murine preadipocyte cells were evaluated by 3-(4,5-dimethylthiazole-2-yl)-5-(3-carboxymethoxyphenyl)-2-(4-sulfophenyl)-2H-tetrazolium (MTT) assay and found to differ according to structure. The relationship between the ¹³C-NMR chemical shifts of the methoxyflavones and their cytotoxicities was investigated using Pearson's correlation analysis. The ¹³C-NMR signal at C-10, a quaternary carbon, was correlated with cytotoxicity. Based on these results, a structural design which lowers the ¹³C-NMR chemical shift at C-10 would be important for the development of cytotoxic compounds. Although quantitative structure-activity and structure-property relationships are well established paradigms for predicting trends among a series of compounds, quantitative property-activity relationships have been relatively unstudied. This approach offers a new strategy for directing structure-activity relationship research.

Signal Deconvolution and Generative Topographic Mapping Regression for Solid-State NMR of Multi-Component Materials

Solid-state nuclear magnetic resonance (ssNMR) spectroscopy provides information on native structures and the dynamics for predicting and designing the physical properties of multi-component solid materials. However, such an analysis is difficult because of the broad and overlapping spectra of these materials. Therefore, signal deconvolution and prediction are great challenges for their ssNMR analysis. We examined signal deconvolution methods using a short-time Fourier transform (STFT) and a non-negative tensor/matrix factorization (NTF, NMF), and methods for predicting NMR signals and physical properties using generative topographic mapping regression (GTMR). We demonstrated the applications for macromolecular samples involved in cellulose degradation, plastics, and microalgae such as Euglena gracilis. During cellulose degradation, ¹³C cross-polarization (CP)-magic angle spinning spectra were separated into signals of cellulose, proteins, and lipids by STFT and NTF. GTMR accurately predicted cellulose degradation for catabolic products such as acetate and CO₂. Using these methods, the ¹H anisotropic spectrum of poly-ε-caprolactone was separated into the signals of crystalline and amorphous solids. Forward prediction and inverse prediction of GTMR were used to compute STFT-processed NMR signals from the physical properties of polylactic acid. These signal deconvolution and prediction methods for ssNMR spectra of macromolecules can resolve the problem of overlapping spectra and support macromolecular characterization and material design.

Exploring the In Vivo and In Vitro Anticancer Activity of Rhenium Isonitrile Complexes

The established platinum-based drugs form covalent DNA adducts to elicit their cytotoxic response. Although they are widely employed, these agents cause toxic side-effects and are susceptible to cancer-resistance mechanisms. To overcome these limitations, alternative metal complexes containing the rhenium(I) tricarbonyl core have been explored as anticancer agents. Based on a previous study ( Chem. Eur. J. 2019, 25, 9206), a series of highly active tricarbonyl rhenium isonitrile polypyridyl (TRIP) complexes of the general formula fac-[Re(CO)3(NN)(ICN)]+, where NN is a chelating diimine and ICN is an isonitrile ligand, that induce endoplasmic reticulum (ER) stress via activation of the unfolded protein response (UPR) pathway are investigated. A total of 11 of these TRIP complexes were synthesized, modifying both the equatorial polypyridyl and axial isonitrile ligands. Complexes with more electron-donating equatorial ligands were found to have greater anticancer activity, whereas the axial ICN ligands had a smaller effect on their overall potency. All 11 TRIP derivatives trigger a similar phenotype that is characterized by their abilities to induce ER stress and activate the UPR. Lastly, we explored the in vivo efficacy of one of the most potent complexes, fac-[Re(CO)3(dmphen)(ptolICN)]+ (TRIP-1a), where dmphen = 2,9-dimethyl-1,10-phenanthroline and ptolICN = para-tolyl isonitrile, in mice. The 99mTc congener of TRIP-1a was synthesized, and its biodistribution in BALB/c mice was investigated in comparison to the parent Re complex. The results illustrate that both complexes have similar biodistribution patterns, suggesting that 99mTc analogues of these TRIP complexes can be used as diagnostic partner agents. The in vivo antitumor activity of TRIP-1a was then investigated in NSG mice bearing A2780 ovarian cancer xenografts. When administered at a dose of 20 mg/kg twice weekly, this complex was able to inhibit tumor growth and prolong mouse survival by 150% compared to the vehicle control cohort.

Zinc-Chelating Mechanism of Sea Cucumber (Stichopus japonicus)-Derived Synthetic Peptides

In this study, three synthetic zinc-chelating peptides (ZCPs) derived from sea cucumber hydrolysates with limited or none of the common metal-chelating amino-acid residues were analyzed by flame atomic absorption spectroscopy, circular dichroism spectroscopy, size exclusion chromatography, zeta-potential, Fourier transform infrared spectroscopy, Raman spectroscopy and nuclear magnetic resonance spectroscopy. The amount of zinc bound to the ZCPs reached maximum values with ZCP:zinc at 1:1, and it was not further increased by additional zinc presence. The secondary structures of ZCPs were slightly altered, whereas no formation of multimers was observed. Furthermore, zinc increased the zeta-potential value by neutralizing the negatively charged residues. Only free carboxyl in C-terminus of ZCPs was identified as the primary binding site of zinc. These results provide the theoretical foundation to understand the mechanism of zinc chelation by peptides.

How medicinal chemists learned about log P

Although log P is now recognized to be a key factor that determines the bioactivity of a molecule, the focus of medicinal chemists on hydrophobicity and log P started with the quantitative structure-activity relationships (QSAR) publications of Hansch and Fujita. Their original publication represents a dramatic change of focus to incorporate consideration of log P after a decade of work unsuccessfully attempting to use the Hammett equation to explain the structure-activity relationships of plant growth regulators. QSAR allows one to explore the quantitative relationship between log P and biological activity even when other factors also influence potency. In particular, Hansch's publications of thousands of QSAR equations demonstrate that a relationship of biological activity with log P is indeed a general phenomenon. Hansch's group also provided data and tools that enable others to explore the relationship between log P and the biological activity of compounds of interest.

The C6H6 NMR repository: An integral solution to control the flow of your data from the magnet to the public

NMR is a mature technique that is well established and adopted in a wide range of research facilities from laboratories to hospitals. This accounts for large amounts of valuable experimental data that may be readily exported into a standard and open format. Yet the publication of these data faces an important issue: Raw data are not made available; instead, the information is slimed down into a string of characters (the list of peaks). Although historical limitations of technology explain this practice, it is not acceptable in the era of Internet. The idea of modernizing the strategy for sharing NMR data is not new, and some repositories exist, but sharing raw data is still not an established practice. Here, we present a powerful toolbox built on recent technologies that runs inside the browser and provides a means to store, share, analyse, and interact with original NMR data. Stored spectra can be streamlined into the publication pipeline, to improve the revision process for instance. The set of tools is still basic but is intended to be extended. The project is open source under the Massachusetts Institute of Technology (MIT) licence.

Chromatographic and Computational Assessment of Lipophilicity of New Anticancer Acetylenequinoline Derivatives

The lipophilicity of a series of anticancer propargylquinoline derivatives is investigated using both chromatographic and computational methods. The parameters of the tested compounds' relative lipophilicity (logkw) are determined experimentally by the high-performance liquid chromatographic method (RP-HPLC, Accucore C18 column), using mixtures of acetonitrile and water as mobile phases. Mobile phase acetonitrile concentrations range between 50 and 80%. The logk values of the investigated compounds are linearly dependent upon the acetonitrile concentration. The analysis led to the calculation of the logkw parameter values for each of the tested compounds. The parameter logkw is discussed in terms of the relationship between structure and lipophilicity and consequently, transformed into the parameter logPHPLC using the calibration curve. The partition coefficients of the tested compounds (logPcalc) are also calculated by selected computer programs. A regression analysis and the sum of ranking differences are used to compare the lipophilic parameters of 15 acetylenequinoline derivatives, which were experimentally obtained (logPHPLC) and calculated using different mathematical methods (logPcalc). The 13C NMR spectra are used to examine the electronic relationships between properties and lipophilicity for the studied compounds. A regression study conducted on 15 compounds exhibits a linear correlation between lipophilicity and electronic properties, expressed as the 13C NMR chemical shift (R2 = 0.98).

The unexpected roles of σ and π orbitals in electron donor and acceptor group effects on the 13C NMR chemical shifts in substituted benzenes

NH₂ and NO₂ group effects on ¹³C NMR chemical shifts in substituted benzenes are explained by σ- instead of π-orbitals.

Effects of electron-donating (R = NH₂) and electron-withdrawing (R = NO₂) groups on ¹³C NMR chemical shifts in R-substituted benzene are investigated by molecular orbital analyses. The ¹³C shift substituent effect in ortho, meta, and para position is determined by the σ bonding orbitals in the aryl ring. The π orbitals do not explain the substituent effects in the NMR spectrum as conventionally suggested in textbooks. The familiar electron donating and withdrawing effects on the π system by NH₂ and NO₂ substituents induce changes in the σ orbital framework, and the ¹³C chemical shifts follow the trends induced in the σ orbitals. There is an implicit dependence of the σ orbital NMR shift contributions on the π framework, via unoccupied π* orbitals, due to the fact that the nuclear shielding is a response property.

Recent Advances in Multinuclear NMR Spectroscopy for Chiral Recognition of Organic Compounds

Nuclear magnetic resonance (NMR) is a powerful tool for the elucidation of chemical structure and chiral recognition. In the last decade, the number of probes, media, and experiments to analyze chiral environments has rapidly increased. The evaluation of chiral molecules and systems has become a routine task in almost all NMR laboratories, allowing for the determination of molecular connectivities and the construction of spatial relationships. Among the features that improve the chiral recognition abilities by NMR is the application of different nuclei. The simplicity of the multinuclear NMR spectra relative to ¹H, the minimal influence of the experimental conditions, and the larger shift dispersion make these nuclei especially suitable for NMR analysis. Herein, the recent advances in multinuclear (¹⁹F, ³¹P, ¹³C, and ⁷⁷Se) NMR spectroscopy for chiral recognition of organic compounds are presented. The review describes new chiral derivatizing agents and chiral solvating agents used for stereodiscrimination and the assignment of the absolute configuration of small organic compounds.

Insights from Theory and Experiment on the Photochromic spiro-Dihydropyrrolo-Pyridazine/Betaine System

We elucidated the photochromic spiro-4a,5-dihydropyrrolo[1,2-b]pyridazine/betaine (DPP/betaine) system by comparing state-of-the-art density functional theory calculations with nanosecond/millisecond UV-vis absorption spectroscopy, as well as steady-state absorption and cyclization kinetics. Time-dependent density functional theory calculations are employed to examine the transformations occurring after photoexcitation. This study shows that the photochromic spiro-4a,5-dihydropyrrolo[1,2-b]pyridazine and spiro-1,8a-dihydroindolizine (DHI) systems react according to similar pathways. However, notable differences exist. Although photoexcitation of the spiro-DPP system also leads to cis-betaines, which then isomerize to trans-betaines, we found two distinct classes of cis isomers (cis-betaine rotamer-1 and cis-betaine rotamer-2), which do not exist in spiro-1,8a-dihydroindolizine. Similar to our previous study on the spiro-DHI/betaine system, a complicated potential-energy landscape between cis and trans isomers exists in the spiro-DPP system, consisting of a network of transition states and intermediates. Because the spiro-DPP/betaine is even more complicated than the spiro-DHI/betaine system, (substituted) photochromic systems featuring a 4a,5-dihydropyrrolo[1,2-b]pyridazine functional unit will require thorough in silico design to function properly as logical gates or in devices for information storage.

Refined Insights in the Photochromic spiro-Dihydroindolizine/Betaine System

We have revisited the photochromic spiro-dihydroindolizine/betaine system by comparing state-of-the-art density functional theory calculations with experimental data. Time-dependent density functional theory calculations are employed to examine the transformations occurring after photoexcitation. This study confirms that photoexcitation of the spiro-dihydroindolizine leads to the formation of the cis-betaine. However, isomerization to the trans-betaine follows through a complicated and formerly unknown potential energy landscape, which consists of a network of transition states and intermediates. The available pathways across this potential energy landscape will determine the kinetics of the forward reaction from the cis-betaine to the trans-betaine and then, even more importantly, the back-reaction. Virtually all practical applications of this optical switch rely on these reactions and, therefore, occur within this landscape. Predicting the network of transition states and intermediates for substituted spiro-dihydroindolizine/betaine systems will enable the in-silico design of optical switches with enhanced performance.

Estimation of the chemical-induced eye injury using a weight-of-evidence (WoE) battery of 21 artificial neural network (ANN) c-QSAR models (QSAR-21): part I: irritation potential

Evaluation of potential chemical-induced eye injury through irritation and corrosion is required to ensure occupational and consumer safety for industrial, household and cosmetic ingredient chemicals. The historical method for evaluating eye irritant and corrosion potential of chemicals is the rabbit Draize test. However, the Draize test is controversial and its use is diminishing - the EU 7th Amendment to the Cosmetic Directive (76/768/EEC) and recast Regulation now bans marketing of new cosmetics having animal testing of their ingredients and requires non-animal alternative tests for safety assessments. Thus, in silico and/or in vitro tests are advocated. QSAR models for eye irritation have been reported for several small (congeneric) data sets; however, large global models have not been described. This report describes FDA/CFSAN's development of 21 ANN c-QSAR models (QSAR-21) to predict eye irritation using the ADMET Predictor program and a diverse training data set of 2928 chemicals. The 21 models had external (20% test set) and internal validation and average training/verification/test set statistics were: 88/88/85(%) sensitivity and 82/82/82(%) specificity, respectively. The new method utilized multiple artificial neural network (ANN) molecular descriptor selection functionalities to maximize the applicability domain of the battery. The eye irritation models will be used to provide information to fill the critical data gaps for the safety assessment of cosmetic ingredient chemicals.

Substituent effect in theoretical VCD spectra

A correlational study shows for the first time a quantitative substituent effect on Vibrational Circular Dichroism intensity.

Enantioselective redox-relay oxidative heck arylations of acyclic alkenyl alcohols using boronic acids

A general, highly selective asymmetric redox-relay oxidative Heck reaction using achiral or racemic acyclic alkenols and boronic acid derivatives is reported. This reaction delivers remotely functionalized arylated carbonyl products from acyclic alkenol substrates, with excellent enantioselectivity under mild conditions, bearing a range of useful functionality. A preliminary mechanistic investigation suggests that the regioselectivity of the initial migratory insertion is highly dependent on the electronic nature of the boronic acid and more subtle electronic effects of the alkenyl alcohol.

Modeling chemical interaction profiles: I. Spectral data-activity relationship and structure-activity relationship models for inhibitors and non-inhibitors of cytochrome P450 CYP3A4 and CYP2D6 isozymes

An interagency collaboration was established to model chemical interactions that may cause adverse health effects when an exposure to a mixture of chemicals occurs. Many of these chemicals—drugs, pesticides, and environmental pollutant—interact at the level of metabolic biotransformations mediated by cytochrome P450 (CYP) enzymes. In the present work, spectral data-activity relationship (SDAR) and structure-activity relationship (SAR) approaches were used to develop machine-learning classifiers of inhibitors and non-inhibitors of the CYP3A4 and CYP2D6 isozymes. The models were built upon 602 reference pharmaceutical compounds whose interactions have been deduced from clinical data, and 100 additional chemicals that were used to evaluate model performance in an external validation (EV) test. SDAR is an innovative modeling approach that relies on discriminant analysis applied to binned nuclear magnetic resonance (NMR) spectral descriptors. In the present work, both 1D ¹³C and 1D ¹⁵N-NMR spectra were used together in a novel implementation of the SDAR technique. It was found that increasing the binning size of 1D ¹³C-NMR and ¹⁵N-NMR spectra caused an increase in the tenfold cross-validation (CV) performance in terms of both the rate of correct classification and sensitivity. The results of SDAR modeling were verified using SAR. For SAR modeling, a decision forest approach involving from 6 to 17 Mold² descriptors in a tree was used. Average rates of correct classification of SDAR and SAR models in a hundred CV tests were 60% and 61% for CYP3A4, and 62% and 70% for CYP2D6, respectively. The rates of correct classification of SDAR and SAR models in the EV test were 73% and 86% for CYP3A4, and 76% and 90% for CYP2D6, respectively. Thus, both SDAR and SAR methods demonstrated a comparable performance in modeling a large set of structurally diverse data. Based on unique NMR structural descriptors, the new SDAR modeling method complements the existing SAR techniques, providing an independent estimator that can increase confidence in a structure-activity assessment. When modeling was applied to hazardous environmental chemicals, it was found that up to 20% of them may be substrates and up to 10% of them may be inhibitors of the CYP3A4 and CYP2D6 isoforms. The developed models provide a rare opportunity for the environmental health branch of the public health service to extrapolate to hazardous chemicals directly from human clinical data. Therefore, the pharmacological and environmental health branches are both expected to benefit from these reported models.