Accelerated Pure Shift NMR Spectroscopy with Deep Learning

Pure shift nuclear magnetic resonance (NMR) spectroscopy presents a promising solution to provide sufficient spectral resolution and has been increasingly applied in various branches of chemistry, but the optimal resolution is generally accompanied by long experimental times. We present a proof of concept of deep learning for fast, high-quality, and reliable pure shift NMR reconstruction. The deep learning (DL) protocol allows one to eliminate undersampling artifacts, distinguish peaks with close chemical shifts, and reconstruct high-resolution pure shift NMR spectroscopy along with accelerated acquisition. More meaningfully, the lightweight neural network delivers satisfactory reconstruction performance on personal computers by several hundred simulated data learning, which somewhat lifts the prohibiting demand for a large volume of real training samples and advanced computing hardware generally required in DL projects. Additionally, an M-to-S strategy applicable to common DL cases is further exploited to boost the network generalization capability. As a result, this study takes a meaningful step toward deep learning protocols for broad chemical applications.

REDEN: Interactive multi-fitting decomposition-based NMR peak picking assistant

We present a new program REDEN (Residual Decomposition of NMR peaks) designed to perform identification of peaks in NMR spectra. This integrated, cross-platform, open-source software visually assists with explicit peak picking through decomposition of NMR peaks on the frequency domain data. It provides a distinctive interactive workflow with iPick due to its integration with the POKY suite, providing users with a seamless and efficient experience. The decomposition of peaks operates in a chosen region of an NMR spectrum by multi-fitting simulated peaks with four lineshape fitting options as support, Gaussian, Lorentzian, a fast/optimized Lorentzian, and Pseudo-Voigt. Furthermore, REDEN provides a way to fine-tune for the users in two operating modes (Basic and Advanced). REDEN is pre-built in the POKY suite, which is available from https://poky.clas.ucdenver.edu.

Biomolecular NMR spectroscopy in the era of artificial intelligence

Biomolecular nuclear magnetic resonance (NMR) spectroscopy and artificial intelligence (AI) have a burgeoning synergy. Deep learning-based structural predictors have forever changed structural biology, yet these tools currently face limitations in accurately characterizing protein dynamics, allostery, and conformational heterogeneity. We begin by highlighting the unique abilities of biomolecular NMR spectroscopy to complement AI-based structural predictions toward addressing these knowledge gaps. We then highlight the direct integration of deep learning approaches into biomolecular NMR methods. AI-based tools can dramatically improve the acquisition and analysis of NMR spectra, enhancing the accuracy and reliability of NMR measurements, thus streamlining experimental processes. Additionally, deep learning enables the development of novel types of NMR experiments that were previously unattainable, expanding the scope and potential of biomolecular NMR spectroscopy. Ultimately, a combination of AI and NMR promises to further revolutionize structural biology on several levels, advance our understanding of complex biomolecular systems, and accelerate drug discovery efforts.

Deep-Learning-Based Mixture Identification for Nuclear Magnetic Resonance Spectroscopy Applied to Plant Flavors

Nuclear magnetic resonance (NMR) is a crucial technique for analyzing mixtures consisting of small molecules, providing non-destructive, fast, reproducible, and unbiased benefits. However, it is challenging to perform mixture identification because of the offset of chemical shifts and peak overlaps that often exist in mixtures such as plant flavors. Here, we propose a deep-learning-based mixture identification method (DeepMID) that can be used to identify plant flavors (mixtures) in a formulated flavor (mixture consisting of several plant flavors) without the need to know the specific components in the plant flavors. A pseudo-Siamese convolutional neural network (pSCNN) and a spatial pyramid pooling (SPP) layer were used to solve the problems due to their high accuracy and robustness. The DeepMID model is trained, validated, and tested on an augmented data set containing 50,000 pairs of formulated and plant flavors. We demonstrate that DeepMID can achieve excellent prediction results in the augmented test set: ACC = 99.58%, TPR = 99.48%, FPR = 0.32%; and two experimentally obtained data sets: one shows ACC = 97.60%, TPR = 92.81%, FPR = 0.78% and the other shows ACC = 92.31%, TPR = 80.00%, FPR = 0.00%. In conclusion, DeepMID is a reliable method for identifying plant flavors in formulated flavors based on NMR spectroscopy, which can assist researchers in accelerating the design of flavor formulations.

Advances in the Application of Artificial Intelligence-Based Spectral Data Interpretation: A Perspective

The interpretation of spectral data, including mass, nuclear magnetic resonance, infrared, and ultraviolet-visible spectra, is critical for obtaining molecular structural information. The development of advanced sensing technology has multiplied the amount of available spectral data. Chemical experts must use basic principles corresponding to the spectral information generated by molecular fragments and functional groups. This is a time-consuming process that requires a solid professional knowledge base. In recent years, the rapid development of computer science and its applications in cheminformatics and the emergence of computer-aided expert systems have greatly reduced the difficulty in analyzing large quantities of data. For expert systems, however, the problem-solving strategy must be known in advance or extracted by human experts and translated into algorithms. Gratifyingly, the development of artificial intelligence (AI) methods has shown great promise for solving such problems. Traditional algorithms, including the latest neural network algorithms, have shown great potential for both extracting useful information and processing massive quantities of data. This Perspective highlights recent innovations covering all of the emerging AI-based spectral interpretation techniques. In addition, the main limitations and current obstacles are presented, and the corresponding directions for further research are proposed. Moreover, this Perspective gives the authors' personal outlook on the development and future applications of spectral interpretation.

Quantification of MR spectra by deep learning in an idealized setting: Investigation of forms of input, network architectures, optimization by ensembles of networks, and training bias

PURPOSE

The aims of this work are (1) to explore deep learning (DL) architectures, spectroscopic input types, and learning designs toward optimal quantification in MR spectroscopy of simulated pathological spectra; and (2) to demonstrate accuracy and precision of DL predictions in view of inherent bias toward the training distribution.

METHODS

Simulated 1D spectra and 2D spectrograms that mimic an extensive range of pathological in vivo conditions are used to train and test 24 different DL architectures. Active learning through altered training and testing data distributions is probed to optimize quantification performance. Ensembles of networks are explored to improve DL robustness and reduce the variance of estimates. A set of scores compares performances of DL predictions and traditional model fitting (MF).

RESULTS

Ensembles of heterogeneous networks that combine 1D frequency-domain and 2D time-frequency domain spectrograms as input perform best. Dataset augmentation with active learning can improve performance, but gains are limited. MF is more accurate, although DL appears to be more precise at low SNR. However, this overall improved precision originates from a strong bias for cases with high uncertainty toward the dataset the network has been trained with, tending toward its average value.

CONCLUSION

MF mostly performs better compared to the faster DL approach. Potential intrinsic biases on training sets are dangerous in a clinical context that requires the algorithm to be unbiased to outliers (i.e., pathological data). Active learning and ensemble of networks are good strategies to improve prediction performances. However, data quality (sufficient SNR) has proven as a bottleneck for adequate unbiased performance-like in the case of MF.

Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data

PURPOSE

While the recommended analysis method for magnetic resonance spectroscopy data is linear combination model (LCM) fitting, the supervised deep learning (DL) approach for quantification of MR spectroscopy (MRS) and MR spectroscopic imaging (MRSI) data recently showed encouraging results; however, supervised learning requires ground truth fitted spectra, which is not practical. Moreover, this work investigates the feasibility and efficiency of the LCM-based self-supervised DL method for the analysis of MRS data.

METHOD

We present a novel DL-based method for the quantification of relative metabolite concentrations, using quantum-mechanics simulated metabolite responses and neural networks. We trained, validated, and evaluated the proposed networks with simulated and publicly accessible in-vivo human brain MRS data and compared the performance with traditional methods. A novel adaptive macromolecule fitting algorithm is included. We investigated the performance of the proposed methods in a Monte Carlo (MC) study.

RESULT

The validation using low-SNR simulated data demonstrated that the proposed methods could perform quantification comparably to other methods. The applicability of the proposed method for the quantification of in-vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly.

CONCLUSION

The proposed model-constrained deep neural networks trained in a self-supervised manner can offer fast and efficient quantification of MRS and MRSI data. Our proposed method has the potential to facilitate clinical practice by enabling faster processing of large datasets such as high-resolution MRSI datasets, which may have thousands of spectra.

Rapid estimation approach for glycosylated serum protein of human serum based on the combination of deep learning and TD-NMR technology

Rapid and precise estimation of glycosylated serum protein (GSP) of human serum is of great importance for the treatment and diagnosis of diabetes mellitus. In this study, we propose a novel method for estimation of GSP level based on the combination of deep learning and time domain nuclear magnetic resonance (TD-NMR) transverse relaxation signal of human serum. Specifically, a principal component analysis (PCA)-enhanced one-dimensional convolutional neural network (1D-CNN) is proposed to analyze the TD-NMR transverse relaxation signal of human serum. The proposed algorithm is proved by accurate estimation of GSP level for the collected serum samples. Furthermore, the proposed algorithm is compared with 1D-CNN without PCA, long short-term memory network (LSTM) and some conventional machine learning algorithms. The results indicate that PCA-enhanced 1D-CNN (PC-1D-CNN) has the minimum error. This study proves that proposed method is feasible and superior to estimate GSP level of human serum using TD-NMR transverse relaxation signals.

Model-informed unsupervised deep learning approaches to frequency and phase correction of MRS signals

PURPOSE

A supervised deep learning (DL) approach for frequency and phase correction (FPC) of MRS data recently showed encouraging results, but obtaining transients with labels for supervised learning is challenging. This work investigates the feasibility and efficiency of unsupervised deep learning-based FPC.

METHODS

Two novel deep learning-based FPC methods (deep learning-based Cr referencing and deep learning-based spectral registration), which use a priori physics domain knowledge, are presented. The proposed networks were trained, validated, and evaluated using simulated, phantom, and publicly accessible in vivo MEGA-edited MRS data. The performance of our proposed FPC methods was compared with other generally used FPC methods, in terms of precision and time efficiency. A new measure was proposed in this study to evaluate the FPC method performance. The ability of each of our methods to carry out FPC at varying SNR levels was evaluated. A Monte Carlo study was carried out to investigate the performance of our proposed methods.

RESULTS

The validation using low-SNR manipulated simulated data demonstrated that the proposed methods could perform FPC comparably with other methods. The evaluation showed that the deep learning-based spectral registration over a limited frequency range method achieved the highest performance in phantom data. The applicability of the proposed method for FPC of GABA-edited in vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly.

CONCLUSIONS

The proposed physics-informed deep neural networks trained in an unsupervised manner with complex data can offer efficient FPC of large MRS data in a shorter time.

Deconvolution of 1D NMR spectra: A deep learning-based approach

The analysis of nuclear magnetic resonance (NMR) spectra to detect peaks and characterize their parameters, often referred to as deconvolution, is a crucial step in the quantification, elucidation, and verification of the structure of molecular systems. However, deconvolution of 1D NMR spectra is a challenge for both experts and machines. We propose a robust, expert-level quality deep learning-based deconvolution algorithm for 1D experimental NMR spectra. The algorithm is based on a neural network trained on synthetic spectra. Our customized pre-processing and labeling of the synthetic spectra enable the estimation of critical peak parameters. Furthermore, the neural network model transfers well to the experimental spectra and demonstrates low fitting errors and sparse peak lists in challenging scenarios such as crowded, high dynamic range, shoulder peak regions as well as broad peaks. We demonstrate in challenging spectra that the proposed algorithm is superior to expert results.

A study on multi-exponential inversion of nuclear magnetic resonance relaxation data using deep learning

Nuclear magnetic resonance (NMR) is a powerful tool for formation evaluation in the oil industry to determine parameters, such as pore structure, fluid saturation, and permeability of porous materials, which are critical to reservoir engineering. The inversion of the measured relaxation data is an ill-posed problem and may lead to deviations of inversion results, which may degrade the accuracy of further data analysis and evaluation. This paper proposes a deep learning method for multi-exponential inversion of NMR relaxation data to improve accuracy. Simulated NMR data are first constructed using a priori knowledge based on the signal parameters and Gaussian distribution. These data are then used to train the neural network designed to consider noise characteristics, signal decay characteristics, signal energy variations, and non-negative features of the T₂ spectra. With the validation from simulated data, the models introduced by multi-scale convolutional neural network (CNN) and attention mechanism outperform other approaches in terms of denoising and T₂ inversion. Finally, NMR measurements of rock cores are used to compare the effectiveness of the attention multi-scale convolutional neural network (ATT-CNN) model in practical applications. The results demonstrate that the proposed method based on deep learning has better performance than the regularization method.

NMR spectrum reconstruction as a pattern recognition problem

A new deep neural network based on the WaveNet architecture (WNN) is presented, which is designed to grasp specific patterns in the NMR spectra. When trained at a fixed non-uniform sampling (NUS) schedule, the WNN benefits from pattern recognition of the corresponding point spread function (PSF) pattern produced by each spectral peak resulting in the highest quality and robust reconstruction of the NUS spectra as demonstrated in simulations and exemplified in this work on 2D ¹H-¹⁵N correlation spectra of three representative globular proteins with different sizes: Ubiquitin (8.6 kDa), Azurin (14 kDa), and Malt1 (44 kDa). The pattern recognition by WNN is also demonstrated for successful virtual homo-decoupling in a 2D methyl ¹H-¹³C - HMQC spectrum of MALT1. We demonstrate using WNN that prior knowledge about the NUS schedule, which so far was not been fully exploited, can be used for designing new powerful NMR processing techniques that surpass the existing algorithmic methods.

The rise of the machines in chemistry

The use of artificial intelligence and, more specifically, deep learning methods in chemistry is becoming increasingly common. Applications in informatics fields, such as cheminformatics and proteomics, structural biology, and spectroscopy, including NMR, are on the rise. Recent developments in model architectures, such as graph convolutional neural networks and transformers, have been enabled by advancements in computational hardware and software. However, model architectures with more predictive power often require larger amounts of training data, which can be challenging to acquire, but this requirement can be mitigated through techniques like pretraining and fine-tuning. In spite of these successes, challenges remain, such as normalization and scaling of data, availability of experimentally acquired data, and model explainability.

A pilot study for fragment identification using 2D NMR and deep learning

This paper presents a proof of concept of a method to identify substructures in 2D NMR spectra of mixtures using a bespoke image-based convolutional neural network application. This is done using HSQC and HMBC spectra separately and in combination. The application can reliably detect substructures in pure compounds, using a simple network. Results indicate that it can work for mixtures when trained on pure compounds only. HMBC data and the combination of HMBC and HSQC show better results than HSQC alone in this pilot study.

Rapid protein assignments and structures from raw NMR spectra with the deep learning technique ARTINA

Nuclear Magnetic Resonance (NMR) spectroscopy is a major technique in structural biology with over 11,800 protein structures deposited in the Protein Data Bank. NMR can elucidate structures and dynamics of small and medium size proteins in solution, living cells, and solids, but has been limited by the tedious data analysis process. It typically requires weeks or months of manual work of a trained expert to turn NMR measurements into a protein structure. Automation of this process is an open problem, formulated in the field over 30 years ago. We present a solution to this challenge that enables the completely automated analysis of protein NMR data within hours after completing the measurements. Using only NMR spectra and the protein sequence as input, our machine learning-based method, ARTINA, delivers signal positions, resonance assignments, and structures strictly without human intervention. Tested on a 100-protein benchmark comprising 1329 multidimensional NMR spectra, ARTINA demonstrated its ability to solve structures with 1.44 Å median RMSD to the PDB reference and to identify 91.36% correct NMR resonance assignments. ARTINA can be used by non-experts, reducing the effort for a protein assignment or structure determination by NMR essentially to the preparation of the sample and the spectra measurements.

SpecDB: A relational database for archiving biomolecular NMR spectral data

NMR is a valuable experimental tool in the structural biologist's toolkit to elucidate the structures, functions, and motions of biomolecules. The progress of machine learning, particularly in structural biology, reveals the critical importance of large, diverse, and reliable datasets in developing new methods and understanding in structural biology and science more broadly. Biomolecular NMR research groups produce large amounts of data, and there is renewed interest in organizing these data to train new, sophisticated machine learning architectures and to improve biomolecular NMR analysis pipelines. The foundational data type in NMR is the free-induction decay (FID). There are opportunities to build sophisticated machine learning methods to tackle long-standing problems in NMR data processing, resonance assignment, dynamics analysis, and structure determination using NMR FIDs. Our goal in this study is to provide a lightweight, broadly available tool for archiving FID data as it is generated at the spectrometer, and grow a new resource of FID data and associated metadata. This study presents a relational schema for storing and organizing the metadata items that describe an NMR sample and FID data, which we call Spectral Database (SpecDB). SpecDB is implemented in SQLite and includes a Python software library providing a command-line application to create, organize, query, backup, share, and maintain the database. This set of software tools and database schema allow users to store, organize, share, and learn from NMR time domain data. SpecDB is freely available under an open source license at https://github.rpi.edu/RPIBioinformatics/SpecDB.

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.

Proton magnetic resonance spectroscopy thermometry: Impact of separately acquired full water or partially suppressed water data on quantification and measurement error

In proton magnetic resonance spectroscopy (¹ H MRS) thermometry, separately acquired full water and partially suppressed water are commonly used for measuring temperature. This paper compares these two approaches. Single-voxel ¹ H MRS data were collected on a 3-T GE scanner from 26 human subjects. Every subject underwent five continuous MRS sessions, each separated by a 2-min phase. Each MRS session lasted 13 min and consisted of two free induction decays (FIDs) without water suppression (with full water [FW or w]) and 64 FIDs with partial water suppression (with partially suppressed water [PW or w']). Frequency differences between the two FWs, the first two PWs, the second FW and the first PW (FW₂ , PW₁ ), or between averaged water ( wav' ) and N-acetylaspartate (NAA), were measured. Intrasubject and intersubject variations of the frequency differences were used as a metric for the error in temperature measurement. The intrasubject variations of frequency differences between FW₂ and PW₁fw2-fw1' , calculated from the five MRS sessions for each subject, were larger than those between the two FWs or between the first two PWs (p = 1.54 x 10^-4 and p = 1.72 x 10^-4 , respectively). The mean values of intrasubject variations of fw2-fw1' for all subjects were 4.7 and 4.5 times those of fw2-fw1 and fw2'-fw1' , respectively. The intrasubject variations of the temperatures based on frequency differences, fw2-fNAA or ( fw1'-fNAA ), were about 2.5 times greater than those based on averaged water and NAA frequencies (fwav'-fNAA ). The mean temperature measured from (fwav'-fNAA ) (n = 26) was 0.29°C lower than that measured from fw2-fNAA and was 0.83°C higher than that from ( fw1'-fNAA ). It was concluded that the use of separately acquired unsuppressed or partially suppressed water signals may result in large errors in frequency and, consequently, temperature measurement.

Novelty Detection for Metabolic Dynamics Established On Breast Cancer Tissue Using 2D NMR TOCSY Spectra

•

Automatic novelty detection of metabolites of 2D-TOCSY NMR spectra.

•

Metabolic profiling of the dynamics changes in Breast cancer tissue sample.

•

Accurate and fast automatic multicomponent peak assignment of 2D NMR spectrum.

•

One- and multi- novelty detection of metabolites.

Most metabolic profiling approaches focus only on identifying pre-known metabolites on NMR TOCSY spectrum using configured parameters. However, there is a lack of tasks dealing with automating the detection of new metabolites that might appear during the dynamic evolution of biological cells. Novelty detection is a category of machine learning that is used to identify data that emerge during the test phase and were not considered during the training phase. We propose a novelty detection system for detecting novel metabolites in the 2D NMR TOCSY spectrum of a breast cancer-tissue sample. We build one- and multi-class recognition systems using different classifiers such as, Kernel Null Foley-Sammon Transform, Kernel Density Estimation, and Support Vector Data Description. The training models were constructed based on different sizes of training data and are used in the novelty detection procedure. Multiple evaluation measures were applied to test the performance of the novelty detection methods. Depending on the training data size, all classifiers were able to achieve 0% false positive rates and total misclassification error in addition to 100% true positive rates. The median total time for the novelty detection process varies between 1.5 and 20 seconds, depending on the classifier and the amount of training data. The results of our novel metabolic profiling method demonstrate its suitability, robustness and speed in automated metabolic research.

Towards autonomous analysis of chemical exchange saturation transfer experiments using deep neural networks

Macromolecules often exchange between functional states on timescales that can be accessed with NMR spectroscopy and many NMR tools have been developed to characterise the kinetics and thermodynamics of the exchange processes, as well as the structure of the conformers that are involved. However, analysis of the NMR data that report on exchanging macromolecules often hinges on complex least-squares fitting procedures as well as human experience and intuition, which, in some cases, limits the widespread use of the methods. The applications of deep neural networks (DNNs) and artificial intelligence have increased significantly in the sciences, and recently, specifically, within the field of biomolecular NMR, where DNNs are now available for tasks such as the reconstruction of sparsely sampled spectra, peak picking, and virtual decoupling. Here we present a DNN for the analysis of chemical exchange saturation transfer (CEST) data reporting on two- or three-site chemical exchange involving sparse state lifetimes of between approximately 3-60 ms, the range most frequently observed via experiment. The work presented here focuses on the ¹H CEST class of methods that are further complicated, in relation to applications to other nuclei, by anti-phase features. The developed DNNs accurately predict the chemical shifts of nuclei in the exchanging species directly from anti-phase ¹H^N CEST profiles, along with an uncertainty associated with the predictions. The performance of the DNN was quantitatively assessed using both synthetic and experimental anti-phase CEST profiles. The assessments show that the DNN accurately determines chemical shifts and their associated uncertainties. The DNNs developed here do not contain any parameters for the end-user to adjust and the method therefore allows for autonomous analysis of complex NMR data that report on conformational exchange.

Fundamental and practical aspects of machine learning for the peak picking of biomolecular NMR spectra

Rapid progress in machine learning offers new opportunities for the automated analysis of multidimensional NMR spectra ranging from protein NMR to metabolomics applications. Most recently, it has been demonstrated how deep neural networks (DNN) designed for spectral peak picking are capable of deconvoluting highly crowded NMR spectra rivaling the facilities of human experts. Superior DNN-based peak picking is one of a series of critical steps during NMR spectral processing, analysis, and interpretation where machine learning is expected to have a major impact. In this perspective, we lay out some of the unique strengths as well as challenges of machine learning approaches in this new era of automated NMR spectral analysis. Such a discussion seems timely and should help define common goals for the NMR community, the sharing of software tools, standardization of protocols, and calibrate expectations. It will also help prepare for an NMR future where machine learning and artificial intelligence tools will be common place.

Neural Network Method for Diffusion-Ordered NMR Spectroscopy

Diffusion-ordered NMR spectroscopy (DOSY) presents an essential tool for the analysis of compound mixtures by revealing intrinsic diffusion behaviors of the mixed components. For the interpretation of the diffusion information, intrinsically designed algorithms for a DOSY spectrum reconstruction are required. The estimated diffusion coefficients are desired to have consistency for all the spectral signals from the same molecule and good separation of signals from different molecules. For this purpose, we propose a novel method that adopts a coordinated multiexponential fitting to ensure the consistency of diffusion coefficients and apply a sparse constraint to enhance the robustness. A lightweight neural network is applied as an optimizer to solve this highly nonlinear and nonconvex optimization problem. The proposed method provides estimated diffusion coefficients with excellent distinguishment between species and outperforms the state-of-the-art reconstruction algorithms, such as the Laplacian inversion and the multivariate fitting methods.

DEEP picker is a deep neural network for accurate deconvolution of complex two-dimensional NMR spectra

The analysis of nuclear magnetic resonance (NMR) spectra for the comprehensive and unambiguous identification and characterization of peaks is a difficult, but critically important step in all NMR analyses of complex biological molecular systems. Here, we introduce DEEP Picker, a deep neural network (DNN)-based approach for peak picking and spectral deconvolution which semi-automates the analysis of two-dimensional NMR spectra. DEEP Picker includes 8 hidden convolutional layers and was trained on a large number of synthetic spectra of known composition with variable degrees of crowdedness. We show that our method is able to correctly identify overlapping peaks, including ones that are challenging for expert spectroscopists and existing computational methods alike. We demonstrate the utility of DEEP Picker on NMR spectra of folded and intrinsically disordered proteins as well as a complex metabolomics mixture, and show how it provides access to valuable NMR information. DEEP Picker should facilitate the semi-automation and standardization of protocols for better consistency and sharing of results within the scientific community.

iPick: Multiprocessing software for integrated NMR signal detection and validation

Peak picking is a critical step in biomolecular NMR spectroscopy. The program, iPick, presented here provides a scripting tool and a graphical user interface (GUI), which allow the user to perform interactive and intuitive peak picking and validation. The click-and-run GUI requires no computer programming skills, while the scripting tool can be used by more advanced users to customize the application. If used with a multi-core CPU, the multiprocessing feature of iPick reduces the processing time significantly by invoking parallel computing. The GUI is a plugin, compatible with the popular NMRFAM-SPARKY software package and its newly released successor, the POKY software. Features implemented in iPick include automated noise level detection and threshold setting, cross-validation against multiple spectra, and a method for quantifying peak reliability. The iPick software is cross-platform, open-source, and freely available from https://github.com/pokynmr/ipick.

Computer Assisted Structure Elucidation (CASE): Current and future perspectives

The first efforts for the development of methods for Computer-Assisted Structure Elucidation (CASE) were published more than 50 years ago. CASE expert systems based on one-dimensional (1D) and two-dimensional (2D) Nuclear Magnetic Resonance (NMR) data have matured considerably by now. The structures of a great number of complex natural products have been elucidated and/or revised using such programs. In this article, we discuss the most likely directions in which CASE will evolve. We act on the premise that a synergistic interaction exists between CASE, new NMR experiments, and methods of computational chemistry, which are continuously being improved. The new developments in NMR experiments (long-range correlation experiments, pure-shift methods, coupling constants measurement and prediction, residual dipolar couplings [RDCs]), and residual chemical shift anisotropies [RCSAs], evolution of density functional theory (DFT), and machine learning algorithms will have an influence on CASE systems and vice versa. This is true also for new techniques for chemical analysis (Atomic Force Microscopy [AFM], "crystalline sponge" X-ray analysis, and micro-Electron Diffraction [micro-ED]), which will be used in combination with expert systems. We foresee that CASE will be utilized widely and become a routine tool for NMR spectroscopists and analysts in academic and industrial laboratories. We believe that the "golden age" of CASE is still in the future.

POKY: a software suite for multidimensional NMR and 3D structure calculation of biomolecules

SUMMARY

The need for an efficient and cost-effective method is compelling in biomolecular NMR. To tackle this problem, we have developed the Poky suite, the revolutionized platform with boundless possibilities for advancing research and technology development in signal detection, resonance assignment, structure calculation and relaxation studies with the help of many automation and user interface tools. This software is extensible and scalable by scripting and batching as well as providing modern graphical user interfaces and a diverse range of modules right out of the box.

AVAILABILITY AND IMPLEMENTATION

Poky is freely available to non-commercial users at https://poky.clas.ucdenver.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

RTExtract: time-series NMR spectra quantification based on 3D surface ridge tracking

MOTIVATION

Time-series nuclear magnetic resonance (NMR) has advanced our knowledge about metabolic dynamics. Before analyzing compounds through modeling or statistical methods, chemical features need to be tracked and quantified. However, because of peak overlap and peak shifting, the available protocols are time consuming at best or even impossible for some regions in NMR spectra.

RESULTS

We introduce Ridge Tracking-based Extract (RTExtract), a computer vision-based algorithm, to quantify time-series NMR spectra. The NMR spectra of multiple time points were formulated as a 3D surface. Candidate points were first filtered using local curvature and optima, then connected into ridges by a greedy algorithm. Interactive steps were implemented to refine results. Among 173 simulated ridges, 115 can be tracked (RMSD < 0.001). For reproducing previous results, RTExtract took less than 2 h instead of ∼48 h, and two instead of seven parameters need tuning. Multiple regions with overlapping and changing chemical shifts are accurately tracked.

AVAILABILITY AND IMPLEMENTATION

Source code is freely available within Metabolomics toolbox GitHub repository (https://github.com/artedison/Edison_Lab_Shared_Metabolomics_UGA/tree/master/metabolomics_toolbox/code/ridge_tracking) and is implemented in MATLAB and R.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy

Since the concept of deep learning (DL) was formally proposed in 2006, it has had a major impact on academic research and industry. Nowadays, DL provides an unprecedented way to analyze and process data with demonstrated great results in computer vision, medical imaging, natural language processing, and so forth. Herein, applications of DL in NMR spectroscopy are summarized, and a perspective for DL as an entirely new approach that is likely to transform NMR spectroscopy into a much more efficient and powerful technique in chemistry and life sciences is outlined.

NMR signal processing, prediction, and structure verification with machine learning techniques

Machine learning (ML) methods have been present in the field of NMR since decades, but it has experienced a tremendous growth in the last few years, especially thanks to the emergence of deep learning (DL) techniques taking advantage of the increased amounts of data and available computer power. These algorithms are successfully employed for classification, regression, clustering, or dimensionality reduction tasks of large data sets and have been intensively applied in different areas of NMR including metabonomics, clinical diagnosis, or relaxometry. In this article, we concentrate on the various applications of ML/DL in the areas of NMR signal processing and analysis of small molecules, including automatic structure verification and prediction of NMR observables in solution.

Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learning

Nuclear magnetic resonance (NMR) spectroscopy serves as an indispensable tool in chemistry and biology but often suffers from long experimental times. We present a proof-of-concept of the application of deep learning and neural networks for high-quality, reliable, and very fast NMR spectra reconstruction from limited experimental data. We show that the neural network training can be achieved using solely synthetic NMR signals, which lifts the prohibiting demand for a large volume of realistic training data usually required for a deep learning approach.

Boosting resolution in NMR spectroscopy by chemical shift upscaling

Resolution is an essential challenge in NMR spectroscopy. Narrow chemical shift range and extensive signal splittings due to scalar couplings often give rise to spectral congestion and even overlap in NMR spectra. Magnetic field strength is directly responsible for spectral resolution as higher magnetic field strength offers better signal dispersion. However, the process of further increasing magnetic field strength of NMR instruments is slow and expensive. Methodology aimed at resolution issue has long been developing. Here, we present a chemical shift upscaling method, in which chemical shifts are upscaled by a given factor while scalar couplings are unchanged. As a result, signal dispersion and hence the resolution are improved. Therefore, it is possible to separate multiplets which originally overlap with each other and to extract their integrals for quantitative analysis. Improved signal dispersion and the preservation of scalar couplings also facilitate multiplet analysis and signal assignment. Chemical shift upscaling offers a method for enhancing resolution limited by magnetic field strength.

NV center based nano-NMR enhanced by deep learning

The growing field of nano nuclear magnetic resonance (nano-NMR) seeks to estimate spectra or discriminate between spectra of minuscule amounts of complex molecules. While this field holds great promise, nano-NMR experiments suffer from detrimental inherent noise. This strong noise masks to the weak signal and results in a very low signal-to-noise ratio. Moreover, the noise model is usually complex and unknown, which renders the data processing of the measurement results very complicated. Hence, spectra discrimination is hard to achieve and in particular, it is difficult to reach the optimal discrimination. In this work we present strong indications that this difficulty can be overcome by deep learning (DL) algorithms. The DL algorithms can mitigate the adversarial effects of the noise efficiently by effectively learning the noise model. We show that in the case of frequency discrimination DL algorithms reach the optimal discrimination without having any pre-knowledge of the physical model. Moreover, the DL discrimination scheme outperform Bayesian methods when verified on noisy experimental data obtained by a single Nitrogen-Vacancy (NV) center. In the case of frequency resolution we show that this approach outperforms Bayesian methods even when the latter have full pre-knowledge of the noise model and the former has none. These DL algorithms also emerge as much more efficient in terms of computational resources and run times. Since in many real-world scenarios the noise is complex and difficult to model, we argue that DL is likely to become a dominant tool in the field.

Convolutional Neural Network Analysis of Two-Dimensional Hyperfine Sublevel Correlation Electron Paramagnetic Resonance Spectra

A machine learning approach is presented for analyzing complex two-dimensional hyperfine sublevel correlation electron paramagnetic resonance (HYSCORE EPR) spectra with the proficiency of an expert spectroscopist. The computer vision algorithm requires no training on experimental data; rather, all of the spin physics required to interpret the spectra are learned from simulations alone. This approach is therefore applicable even when insufficient experimental data exist to train the algorithm. The neural network is demonstrated to be capable of utilizing the full information content of two-dimensional ¹⁴N HYSCORE spectra to predict the magnetic coupling parameters and their underlying probability distributions that were previously inaccessible. The predicted hyperfine ( a, T) and ¹⁴N quadrupole ( K, η) coupling constants deviate from the previous manual analyses of the experimental spectra on average by 0.11 MHz, 0.09 MHz, 0.19 MHz, and 0.09, respectively.

Application of Dirichlet process mixture model to the identification of spin systems in protein NMR spectra

Analysis of structure, function and interactions of proteins by NMR spectroscopy usually requires the assignment of resonances to the corresponding nuclei in protein. This task, although automated by methods such as FLYA or PINE, is still frequently performed manually. To facilitate the manual sequence-specific chemical shift assignment of complex proteins, we propose a method based on Dirichlet process mixture model (DPMM) that performs automated matching of groups of signals observed in NMR spectra to corresponding nuclei in protein sequence. The model has been extensively tested on 80 proteins retrieved from the BMRB database and has shown superior performance to the reference method.