Exploratory machine-learned theoretical chemical shifts can closely predict metabolic mixture signals

Tracking Metabolite Variations during the Degradation of Vegetables in Rice Bran Bed with Intact-State Nuclear Magnetic Resonance Spectroscopy

Fermentation-a process of compound degradation by microorganisms-is a traditional food processing method utilized worldwide for the long-term preservation of fresh foods. In recent years, fermented foods have gained attention as health foods. Fermentation increases the nutritional value of ingredients, producing complex flavors and aromas. To identify unknown components in fermented foods, it is necessary to analyze compounds and conditions nondestructively and comprehensively. We performed intact-state nuclear magnetic resonance (NMR) spectroscopy using intermolecular single quantum coherence (iSQC) to detect the degradation of vegetables directly and nondestructively. We used two types of vegetables and a rice bran bed (nukazuke), which is used for traditional vegetable fermentation in Japan. Major metabolites such as saccharides, organic acids, and amino acids were identified in iSQC-sliced spectra. Comparing NMR signal intensities during degradation revealed the transition of metabolites characteristic of lactic acid fermentation. A pathway-based network analysis showed pathways involved in amino acid metabolism and lactic acid fermentation. Our analytical approach with intact-state NMR spectroscopy using iSQC demonstrated that it may be effective in other experimental systems, allowing for the evaluation of phenomena that have been conventionally overlooked in their true state.

New 1,3,4-Thiadiazole Derivatives as α-Glucosidase Inhibitors: Design, Synthesis, DFT, ADME, and In Vitro Enzymatic Studies

Diabetes is an emerging disorder in the world and is caused due to the imbalance of insulin production as well as serious effects on the body. In search of a better treatment for diabetes, we designed a novel class of 1,3,4-thiadiazole-bearing Schiff base analogues and assessed them for the α-glucosidase enzyme. In the series (1-12), compounds are synthesized and 3 analogues showed excellent inhibitory activity against α-glucosidase enzymes in the range of IC50 values of 18.10 ± 0.20 to 1.10 ± 0.10 μM. In this series, analogues 4, 8, and 9 show remarkable inhibition profile IC50 2.20 ± 0.10, 1.10 ± 0.10, and 1.30 ± 0.10 μM by using acarbose as a standard, whose IC50 is 11.50 ± 0.30 μM. The structure of the synthesized compounds was confirmed through various spectroscopic techniques, such as NMR and HREI-MS. Additionally, molecular docking, pharmacokinetics, cytotoxic evaluation, and density functional theory study were performed to investigate their behavior.

Computation of CCSD(T)-Quality NMR Chemical Shifts via Δ-Machine Learning from DFT

NMR spectroscopy undoubtedly plays a central role in determining molecular structures across different chemical disciplines, and the accurate computational prediction of NMR parameters is highly desirable. In this work, a new Δ-machine learning approach is presented to correct DFT-computed NMR chemical shifts using input features from the calculation and in addition highly accurate reference data at the CCSD(T)/pcSseg-2 level of theory with a basis set extrapolation scheme. The model is trained on a data set containing 1000 optimized and geometrically distorted structures of small organic molecules comprising most elements of the first three periods and containing data for 7090 ¹H and 4230 ¹³C NMR chemical shifts. Applied to the PBE0/pcSseg-2 method, the mean absolute deviation (MAD) on the internal NMR shift test set is reduced by 81% for ¹H and 92% for ¹³C at virtually no additional computational cost. For 12 different DFT functional and basis set combinations, the MAD of the ML-corrected NMR shifts ranges from 0.021 to 0.039 ppm (¹H) and from 0.38 to 1.07 ppm (¹³C). Importantly, the new method consistently outperforms the simple and widely used linear regression correction technique. This behavior is reproduced on three different external benchmark sets, confirming the generality and robustness of the correction scheme, which can easily be applied in DFT-based spectral simulations.

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.

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.

Multiplet analysis by strong-coupling-artifact-suppression 2D J-resolved NMR spectroscopy

Benefitting from the capability of recording scalar (J) couplings and bonding information, 2D J-resolved NMR spectroscopy constitutes an important tool for molecular structure analysis and mixture component identification. Unfortunately, conventional 2D J-resolved experiments generally encounter challenges of insufficient spectral resolution and strong coupling artifacts. In this study, a general NMR approach is exploited to record absorption-mode artifact-free 2D J-resolved spectra. This proposal adopts the advanced triple-spin-echo pure shift yielded by chirp excitation element to eliminate J coupling splittings and preserve chemical shifts along the F2 dimension, and it additionally utilizes the echo-train J acquisition to reveal the multiplet structure along the F1 dimension in accelerated experimental acquisition. Thus, it permits one to extract multiplet structure information from crowded spectral regions in one-shot experiments, with considerable resolution advantage resulting from completely decoupling F2 dimension and absorption-mode presentation, thus facilitating analysis on complex samples. More importantly, this method grants the superior performance on suppressing strong coupling artifacts, which have been affirmed by experiments on a series of chemical samples. As a consequence, this proposed method serves as a useful tool for J coupling measurements and multiplet structure analyses on complex samples that contain crowded NMR resonances and strong coupling spin systems, and it may exhibit broad application potentials in fields of physics, chemistry, and medical science, among others.

Solubility Prediction from Molecular Properties and Analytical Data Using an In-phase Deep Neural Network (Ip-DNN)

Materials informatics is an emerging field that allows us to predict the properties of materials and has been applied in various research and development fields, such as materials science. In particular, solubility factors such as the Hansen and Hildebrand solubility parameters (HSPs and SP, respectively) and Log P are important values for understanding the physical properties of various substances. In this study, we succeeded at establishing a solubility prediction tool using a unique machine learning method called the in-phase deep neural network (ip-DNN), which starts exclusively from the analytical input data (e.g., NMR information, refractive index, and density) to predict solubility by predicting intermediate elements, such as molecular components and molecular descriptors, in the multiple-step method. For improving the level of accuracy of the prediction, intermediate regression models were employed when performing in-phase machine learning. In addition, we developed a website dedicated to the established solubility prediction method, which is freely available at "http://dmar.riken.jp/matsolca/".

Improved Prediction of Carbonless NMR Spectra by the Machine Learning of Theoretical and Fragment Descriptors for Environmental Mixture Analysis

As the first multidimensional NMR approach, 2D J-resolved (2DJ) spectroscopy is distinguished by signal resolution and detection sensitivity with remarkable advantages for the exhaustive evaluation of complex mixtures and environmental samples due to its carbonless feature without the requirement of ¹³C connectivity. Generally, the 2DJ signal assignment of metabolic mixtures is problematic in spite of references to experimental NMR databases, owing to the existence of metabolic "dark matter." In this study, a new method to predict 2DJ spectra was developed with a combination of quantum mechanical (QM) computation and machine learning (ML). The predictive accuracy of J-coupling constants was evaluated using validated data. The root-mean-square deviation (RMSD) for QM computation was 3.52 Hz, while the RMSD for QM + ML was 1.21 Hz, indicating a substantial increase in predictive accuracy. The proposed model was applied to predict the 2DJ spectra of 60 standard substances and 55 components of seawater. Furthermore, two practical environmental samples were used to evaluate the robustness of the constructed predictive model. A J-coupling tree and J-split spectra produced from QM + ML of aliphatic moieties had good consistency with the experimental data, as compared with the theoretical data produced by QM computation. The predicted J-coupling tree for the J-coupling multiplet analysis of freely rotating bonds in the complex mixture, which is traditionally difficult, was interpretable. In addition, in silico identification of the J-split ¹H NMR signals, which was independent of experimental databases, aided in the discovery of new components in a mixture.

Decomposition Factor Analysis Based on Virtual Experiments throughout Bayesian Optimization for Compost-Degradable Polymers

Bio-based polymers have been considered as an alternative to oil-based materials for their “carbon-neutral” environmentally degrative features. However, degradation is a complex system in which environmental factors and preparation conditions are involved, and the relationship between degradation and these factors/conditions has not yet been clarified. Moreover, an efficient system that addresses multiple degradation factors has not been developed for practical use. Thus, we constructed a decomposition degree predictive model to explore degradation factors based on analytical data and experimental conditions. The predictive model was constructed by machine learning using a dataset. The objective variable was the molecular weight, and the explanatory variables were the moisture content in a compost environment, degradation period, degree of crystallinity pre-experiment, and features of solid-state nuclear magnetic resonance spectra. The good accuracy of this predictive model was confirmed by statistical variables. The moisture content in the compost environment was a critical factor for considering initial degradation; specific scores revealed the contribution of degradation factors. Furthermore, the optimum decomposition degree, various analytical values, and experimental conditions were predictable when this predictive model was combined with Bayesian optimization. Information obtained from virtual experiments is expected to promote the material design and development of bio-based plastics.

Relaxometric learning: a pattern recognition method for T2 relaxation curves based on machine learning supported by an analytical framework

Nuclear magnetic resonance (NMR)-based relaxometry is widely used in various fields of research because of its advantages such as simple sample preparation, easy handling, and relatively low cost compared with metabolomics approaches. However, there have been no reports on the application of the T₂ relaxation curves in metabolomics studies involving the evaluation of metabolic mixtures, such as geographical origin determination and feature extraction by pattern recognition and data mining. In this study, we describe a data mining method for relaxometric data (i.e., relaxometric learning). This method is based on a machine learning algorithm supported by the analytical framework optimized for the relaxation curve analyses. In the analytical framework, we incorporated a variable optimization approach and bootstrap resampling-based matrixing to enhance the classification performance and balance the sample size between groups, respectively. The relaxometric learning enabled the extraction of features related to the physical properties of fish muscle and the determination of the geographical origin of the fish by improving the classification performance. Our results suggest that relaxometric learning is a powerful and versatile alternative to conventional metabolomics approaches for evaluating fleshiness of chemical mixtures in food and for other biological and chemical research requiring a nondestructive, cost-effective, and time-saving method.

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.

NMR-TS: de novo molecule identification from NMR spectra

Nuclear magnetic resonance (NMR) spectroscopy is an effective tool for identifying molecules in a sample. Although many previously observed NMR spectra are accumulated in public databases, they cover only a tiny fraction of the chemical space, and molecule identification is typically accomplished manually based on expert knowledge. Herein, we propose NMR-TS, a machine-learning-based python library, to automatically identify a molecule from its NMR spectrum. NMR-TS discovers candidate molecules whose NMR spectra match the target spectrum by using deep learning and density functional theory (DFT)-computed spectra. As a proof-of-concept, we identify prototypical metabolites from their computed spectra. After an average 5451 DFT runs for each spectrum, six of the nine molecules are identified correctly, and proximal molecules are obtained in the other cases. This encouraging result implies that de novo molecule generation can contribute to the fully automated identification of chemical structures. NMR-TS is available at https://github.com/tsudalab/NMR-TS.

Spatial molecular-dynamically ordered NMR spectroscopy of intact bodies and heterogeneous systems

Noninvasive evaluation of the spatial distribution of chemical composition and diffusion behavior of materials is becoming possible by advanced nuclear magnetic resonance (NMR) pulse sequence editing. However, there is room for improvement in the spectral resolution and analytical method for application to heterogeneous samples. Here, we develop applications for comprehensively evaluating compounds and their dynamics in intact bodies and heterogeneous systems from NMR data, including spatial z-position, chemical shift, and diffusion or relaxation. This experiment is collectively named spatial molecular-dynamically ordered spectroscopy (SMOOSY). Pseudo-three-dimensional (3D) SMOOSY spectra of an intact shrimp and two heterogeneous systems are recorded to evaluate this methodology. Information about dynamics is mapped onto two-dimensional (2D) chemical shift imaging spectra using a pseudo-spectral imaging method with a processing tool named SMOOSY processor. Pseudo-2D SMOOSY spectral images can non-invasively assess the different dynamics of the compounds at each spatial z-position of the shrimp's body and two heterogeneous systems.