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

Abstract

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.

Automated Determination of Nuclear Magnetic Resonance Chemical Shift Perturbations in Ligand Screening Experiments: The PICASSO Web Server

“…Thus, there is no need for a specific software upstream. Peak picking can be performed through the software interface of the spectrometer, the NMR processing package adopted in the lab, or a separate peak picking tool. , …”

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

“…The latter can be achieved by separately applying the peak picker to each row and each column and then reconcile the results to obtain the peak positions in 2D or higher dimensions. This strategy can be further refined to avoid false positives for the accurate identification of shoulder peaks as implemented in DEEP Picker (Li et al 2021). The performance of DEEP Picker is exemplified in Fig.…”

“…In fact, some kind of cutoff is also used by traditional peak pickers. The LPAC can be defined as a fraction of the amplitude of average true positive peaks or as a multiple of the mean noise amplitude σ noise of the noise floor in a peak-free region of the spectrum, which can be automatically obtained by a robust global noise estimator (Li et al 2021). The optimal LPAC may vary from protein to protein or even from sample to sample of the same protein as the amounts of impurities and degraded protein may vary and depend on the sample condition, including age as well as storage conditions and measurement temperature.…”

“…This technology has been made broadly accessible by means of DNN frameworks, such as TensorFlow (Abadi et al 2016) and PyTorch (Paszke et al 2017). Most recently, we trained a deep neural network, called DEEP Picker, for the accurate analysis of 2D NMR spectra of challenging protein and metabolomics samples (Li et al 2021). During this project, a series of fundamental questions came into focus, such as what constitutes reasonable expectations for a peak picker, what role machine learning can play, how peak-pickers should be trained, how their performance should be assessed, and whether there are limits for the automation of peak picking.…”

SpecDB: A Relational Database for Archiving Biomolecular NMR Spectra Data

“…NMR spectroscopy has a rich history of developing and applying machine learning at all stages in the experimental pipeline 7,8 . High impact examples include predicting protein torsion angles 9 , chemical shift prediction 10 , NMR spectral peak picking 11,12 , and reconstruction of non-uniformly sampled free induction decays (FIDs) [13][14][15] . Additionally, there have been efforts to organize NMR data into datasets suitable for machine learning, like the RefDB dataset with re-referenced chemical shifts 16 .…”