A framework for automated structure elucidation from routine NMR spectra

Deep Learning-Assisted Spectrum-Structure Correlation: State-of-the-Art and Perspectives

Spectrum-structure correlation is playing an increasingly crucial role in spectral analysis and has undergone significant development in recent decades. With the advancement of spectrometers, the high-throughput detection triggers the explosive growth of spectral data, and the research extension from small molecules to biomolecules accompanies massive chemical space. Facing the evolving landscape of spectrum-structure correlation, conventional chemometrics becomes ill-equipped, and deep learning assisted chemometrics rapidly emerges as a flourishing approach with superior ability of extracting latent features and making precise predictions. In this review, the molecular and spectral representations and fundamental knowledge of deep learning are first introduced. We then summarize the development of how deep learning assist to establish the correlation between spectrum and molecular structure in the recent 5 years, by empowering spectral prediction (i.e., forward structure-spectrum correlation) and further enabling library matching and de novo molecular generation (i.e., inverse spectrum-structure correlation). Finally, we highlight the most important open issues persisted with corresponding potential solutions. With the fast development of deep learning, it is expected to see ultimate solution of establishing spectrum-structure correlation soon, which would trigger substantial development of various disciplines.

Graph to Activation Energy Models Easily Reach Irreducible Errors but Show Limited Transferability

Activation energy characterization of competing reactions is a costly but crucial step for understanding the kinetic relevance of distinct reaction pathways, product yields, and myriad other properties of reacting systems. The standard methodology for activation energy characterization has historically been a transition state search using the highest level of theory that can be afforded. However, recently, several groups have popularized the idea of predicting activation energies directly based on nothing more than the reactant and product graphs, a sufficiently complex neural network, and a broad enough data set. Here, we have revisited this task using the recently developed Reaction Graph Depth 1 (RGD1) transition state data set and several newly developed graph attention architectures. All of these new architectures achieve similar state-of-the-art results of ∼4 kcal/mol mean absolute error on withheld testing sets of reactions but poor performance on external testing sets composed of reactions with differing mechanisms, reaction molecularity, or reactant size distribution. Limited transferability is also shown to be shared by other contemporary graph to activation energy architectures through a series of case studies. We conclude that an array of standard graph architectures can already achieve results comparable to the irreducible error of available reaction data sets but that out-of-distribution performance remains poor.

Automated nuclear magnetic resonance fingerprinting of mixtures

Nuclear magnetic resonance (NMR) spectroscopy is a powerful tool for qualitative and quantitative analysis. However, for complex mixtures, determining the speciation from NMR spectra can be tedious and sometimes even unfeasible. On the other hand, identifying and quantifying structural groups in a mixture from NMR spectra is much easier than doing the same for components. We call this group-based approach "NMR fingerprinting." In this work, we show that NMR fingerprinting can even be performed in an automated way, without expert knowledge, based only on standard NMR spectra, namely, 13C, 1H, and 13C DEPT NMR spectra. Our approach is based on the machine-learning method of support vector classification (SVC), which was trained here on thousands of labeled pure-component NMR spectra from open-source data banks. We demonstrate the applicability of the automated NMR fingerprinting using test mixtures, of which spectra were taken using a simple benchtop NMR spectrometer. The results from the NMR fingerprinting agree remarkably well with the ground truth, which was known from the gravimetric preparation of the samples. To facilitate the application of the method, we provide an interactive website (https://nmr-fingerprinting.de), where spectral information can be uploaded and which returns the NMR fingerprint. The NMR fingerprinting can be used in many ways, for example, for process monitoring or thermodynamic modeling using group-contribution methods-or simply as a first step in species analysis.

Microbiome metabolite quantification methods enabling insights into human health and disease

Many of the health-associated impacts of the microbiome are mediated by its chemical activity, producing and modifying small molecules (metabolites). Thus, microbiome metabolite quantification has a central role in efforts to elucidate and measure microbiome function. In this review, we cover general considerations when designing experiments to quantify microbiome metabolites, including sample preparation, data acquisition and data processing, since these are critical to downstream data quality. We then discuss data analysis and experimental steps to demonstrate that a given metabolite feature is of microbial origin. We further discuss techniques used to quantify common microbial metabolites, including short-chain fatty acids (SCFA), secondary bile acids (BAs), tryptophan derivatives, N-acyl amides and trimethylamine N-oxide (TMAO). Lastly, we conclude with challenges and future directions for the field.

Machine learning-assisted structure annotation of natural products based on MS and NMR data

Covering: up to March 2023Machine learning (ML) has emerged as a popular tool for analyzing the structures of natural products (NPs). This review presents a summary of the recent advancements in ML-assisted mass spectrometry (MS) and nuclear magnetic resonance (NMR) data analysis to establish the chemical structures of NPs. First, ML-based MS/MS analyses that rely on library matching are discussed, which involves the utilization of ML algorithms to calculate similarity, predict the MS/MS fragments, and form molecular fingerprint. Then, ML assisted MS/MS structural annotation without library matching is reviewed. Furthermore, the cases of ML algorithms in assisting structural studies of NPs based on NMR are discussed from four perspectives: NMR prediction, functional group identification, structural categorization and quantum chemical calculation. Finally, the review concludes with a discussion of the challenges and the trends associated with the structural establishment of NPs based on ML algorithms.

Preparative three-dimensional GC and nuclear magnetic resonance for the isolation and identification of two sesquiterpene ethers from Dictyota Dichotoma

Separation science plays a crucial role in the isolation of novel compounds contained in complex matrices. Yet their rationale employment needs preliminary structure elucidation, which usually requires sufficient aliquots of grade substances to characterize the molecule by nuclear magnetic resonance experiments. In this study, two peculiar oxa-tricycloundecane ethers were isolated by means of preparative multidimensional gas chromatography from the brown alga species Dictyota dichotoma (Huds.) Lam., aiming to assign their 3D structures. Density functional theory simulations were carried out to select the correct configurational species matching the experimental NMR data (in terms of enantiomeric couples). In this case, the theoretical approach was crucial as the protonic signal overlap and spectral overcrowding were preventing any other unambiguous structural information. Just after the identification through the density functional theory data matching of the correct relative configuration it was possible to verify an enhanced self-consistency with the experimental data, confirming the stereochemistry. The results obtained further pave the way toward structure elucidation of highly asymmetric molecules, whose configuration cannot be inferred by other means or strategies.

Conditional Molecular Generation Net Enables Automated Structure Elucidation Based on 13C NMR Spectra and Prior Knowledge

Structure elucidation of unknown compounds based on nuclear magnetic resonance (NMR) remains a challenging problem in both synthetic organic and natural product chemistry. Library matching has been an efficient method to assist structure elucidation. However, it is limited by the coverage of libraries. In addition, prior knowledge such as molecular fragments is neglected. To solve the problem, we propose a conditional molecular generation net (CMGNet) to allow input of multiple sources of information. CMGNet not only uses ¹³C NMR spectrum data as input but molecular formulas and fragments of molecules are also employed as input conditions. Our model applies large-scale pretraining for molecular understanding and fine-tuning on two NMR spectral data sets of different granularity levels to accommodate structure elucidation tasks. CMGNet generates structures based on ¹³C NMR data, molecular formula, and fragment information, with a recovery rate of 94.17% in the top 10 recommendations. In addition, the generative model performed well in the generation of various classes of compounds and in the structural revision task. CMGNet has a deep understanding of molecular connectivities from ¹³C NMR, molecular formula, and fragments, paving the way for a new paradigm of deep learning-assisted inverse problem-solving.

Problems, principles and progress in computational annotation of NMR metabolomics data

BACKGROUND

Compound identification remains a critical bottleneck in the process of exploiting Nuclear Magnetic Resonance (NMR) metabolomics data, especially for ¹H 1-dimensional (¹H 1D) data. As databases of reference compound spectra have grown, workflows have evolved to rely heavily on their search functions to facilitate this process by generating lists of potential metabolites found in complex mixture data, facilitating annotation and identification. However, approaches for validating and communicating annotations are most often guided by expert knowledge, and therefore are highly variable despite repeated efforts to align practices and define community standards.

AIM OF REVIEW

This review is aimed at broadening the application of automated annotation tools by discussing the key ideas of spectral matching and beginning to describe a set of terms to classify this information, thus advancing standards for communicating annotation confidence. Additionally, we hope that this review will facilitate the growing collaboration between chemical data scientists, software developers and the NMR metabolomics community aiding development of long-term software solutions.

KEY SCIENTIFIC CONCEPTS OF REVIEW

We begin with a brief discussion of the typical untargeted NMR identification workflow. We differentiate between annotation (hypothesis generation, filtering), and identification (hypothesis testing, verification), and note the utility of different NMR data features for annotation. We then touch on three parts of annotation: (1) generation of queries, (2) matching queries to reference data, and (3) scoring and confidence estimation of potential matches for verification. In doing so, we highlight existing approaches to automated and semi-automated annotation from the perspective of the structural information they utilize, as well as how this information can be represented computationally.

Identifying molecular functional groups of organic compounds by deep learning of NMR data

We preprocess the raw nuclear magnetic resonance (NMR) spectrum and extract key features by using two different methodologies, called equidistant sampling and peak sampling for subsequent substructure pattern recognition. We also provide a strategy to address the imbalance issue frequently encountered in statistical modeling of NMR data set and establish two conventional support vector machine (SVM) and K-nearest neighbor (KNN) models to assess the capability of two feature selections, respectively. Our results in this study show that the models using the selected features of peak sampling outperform those using equidistant sampling. Then we build the recurrent neural network (RNN) model trained by data collected from peak sampling. Furthermore, we illustrate the easier optimization of hyperparameters and the better generalization ability of the RNN deep learning model by detailed comparison with traditional machine learning SVM and KNN models.

Deep Learning-Based Method for Compound Identification in NMR Spectra of Mixtures

Nuclear magnetic resonance (NMR) spectroscopy is highly unbiased and reproducible, which provides us a powerful tool to analyze mixtures consisting of small molecules. However, the compound identification in NMR spectra of mixtures is highly challenging because of chemical shift variations of the same compound in different mixtures and peak overlapping among molecules. Here, we present a pseudo-Siamese convolutional neural network method (pSCNN) to identify compounds in mixtures for NMR spectroscopy. A data augmentation method was implemented for the superposition of several NMR spectra sampled from a spectral database with random noises. The augmented dataset was split and used to train, validate and test the pSCNN model. Two experimental NMR datasets (flavor mixtures and additional flavor mixture) were acquired to benchmark its performance in real applications. The results show that the proposed method can achieve good performances in the augmented test set (ACC = 99.80%, TPR = 99.70% and FPR = 0.10%), the flavor mixtures dataset (ACC = 97.62%, TPR = 96.44% and FPR = 2.29%) and the additional flavor mixture dataset (ACC = 91.67%, TPR = 100.00% and FPR = 10.53%). We have demonstrated that the translational invariance of convolutional neural networks can solve the chemical shift variation problem in NMR spectra. In summary, pSCNN is an off-the-shelf method to identify compounds in mixtures for NMR spectroscopy because of its accuracy in compound identification and robustness to chemical shift variation.

Recognition-Enabled Automated Analyte Identification via 19F NMR

Nuclear magnetic resonance (NMR) is an indispensable tool for structural elucidation and noninvasive analysis. Automated identification of analytes with NMR is highly pursued in metabolism research and disease diagnosis; however, this process is often complicated by the signal overlap and the sample matrix. We herein report a detection scheme based on ¹⁹F NMR spectroscopy and dynamic recognition, which effectively simplifies the detection signal and mitigates the influence of the matrix on the detection. It is demonstrated that this approach can not only detect and differentiate capsaicin and dihydrocapsaicin in complex real-world samples but also quantify the ibuprofen content in sustained-release capsules. Based on the ¹⁹F signals obtained in the detection using a set of three ¹⁹F probes, automated analyte identification is achieved, effectively reducing the odds of misrecognition caused by structural similarity.