Browse
Submit Data
Databases
API
Help

Dataset Information

15 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

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.

SUBMITTER: Li DW

PROVIDER: S-EPMC8410766 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Deconvolution of Complex 1D NMR Spectra Using Objective Model Selection.

Project description:Fluorine (19F) NMR has emerged as a useful tool for characterization of slow dynamics in 19F-labeled proteins. One-dimensional (1D) 19F NMR spectra of proteins can be broad, irregular and complex, due to exchange of probe nuclei between distinct electrostatic environments; and therefore cannot be deconvoluted and analyzed in an objective way using currently available software. We have developed a Python-based deconvolution program, decon1d, which uses Bayesian information criteria (BIC) to objectively determine which model (number of peaks) would most likely produce the experimentally obtained data. The method also allows for fitting of intermediate exchange spectra, which is not supported by current software in the absence of a specific kinetic model. In current methods, determination of the deconvolution model best supported by the data is done manually through comparison of residual error values, which can be time consuming and requires model selection by the user. In contrast, the BIC method used by decond1d provides a quantitative method for model comparison that penalizes for model complexity helping to prevent over-fitting of the data and allows identification of the most parsimonious model. The decon1d program is freely available as a downloadable Python script at the project website (https://github.com/hughests/decon1d/).

| S-EPMC4524620 | biostudies-literature

Deconvolution of two-dimensional NMR spectra by fast maximum likelihood reconstruction: application to quantitative metabolomics.

Project description:We have developed an algorithm called fast maximum likelihood reconstruction (FMLR) that performs spectral deconvolution of 1D-2D NMR spectra for the purpose of accurate signal quantification. FMLR constructs the simplest time-domain model (e.g., the model with the fewest number of signals and parameters) whose frequency spectrum matches the visible regions of the spectrum obtained from identical Fourier processing of the acquired data. We describe the application of FMLR to quantitative metabolomics and demonstrate the accuracy of the method by analysis of complex, synthetic mixtures of metabolites and liver extracts. The algorithm demonstrates greater accuracy (0.5-5.0% error) than peak height analysis and peak integral analysis with greatly reduced operator intervention. FMLR has been implemented in a Java-based framework that is available for download on multiple platforms and is interoperable with popular NMR display and processing software. Two-dimensional (1)H-(13)C spectra of mixtures can be acquired with acquisition times of 15 min and analyzed by FMLR in the range of 2-5 min per spectrum to identify and quantify constituents present at concentrations of 0.2 mM or greater.

| S-EPMC3114465 | biostudies-literature

Using Deep Neural Networks to Reconstruct Non-uniformly Sampled NMR Spectra.

Project description:Non-uniform and sparse sampling of multi-dimensional NMR spectra has over the last decade become an important tool to allow for fast acquisition of multi-dimensional NMR spectra with high resolution. The success of non-uniform sampling NMR hinge on both the development of algorithms to accurately reconstruct the sparsely sampled spectra and the design of sampling schedules that maximise the information contained in the sampled data. Traditionally, the reconstruction tools and algorithms have aimed at reconstructing the full spectrum and thus 'fill out the missing points' in the time-domain spectrum, although other techniques are based on multi-dimensional decomposition and extraction of multi-dimensional shapes. Also over the last decade, machine learning, deep neural networks, and artificial intelligence have seen new applications in an enormous range of sciences, including analysis of MRI spectra. As a proof-of-principle, it is shown here that simple deep neural networks can be trained to reconstruct sparsely sampled NMR spectra. For the reconstruction of two-dimensional NMR spectra, reconstruction using a deep neural network performs as well, if not better than, the currently and widely used techniques. It is therefore anticipated that deep neural networks provide a very valuable tool for the reconstruction of sparsely sampled NMR spectra in the future to come.

| S-EPMC6859195 | biostudies-literature

Deep neural network based tissue deconvolution of circulating tumor cell RNA.

Project description:Prior research has shown that the deconvolution of cell-free RNA can uncover the tissue origin. The conventional deconvolution approaches rely on constructing a reference tissue-specific gene panel, which cannot capture the inherent variation present in actual data. To address this, we have developed a novel method that utilizes a neural network framework to leverage the entire training dataset. Our approach involved training a model that incorporated 15 distinct tissue types. Through one semi-independent and two complete independent validations, including deconvolution using a semi in silico dataset, deconvolution with a custom normal tissue mixture RNA-seq data, and deconvolution of longitudinal circulating tumor cell RNA-seq (ctcRNA) data from a cancer patient with metastatic tumors, we demonstrate the efficacy and advantages of the deep-learning approach which were exerted by effectively capturing the inherent variability present in the dataset, thus leading to enhanced accuracy. Sensitivity analyses reveal that neural network models are less susceptible to the presence of missing data, making them more suitable for real-world applications. Moreover, by leveraging the concept of organotropism, we applied our approach to trace the migration of circulating tumor cell-derived RNA (ctcRNA) in a cancer patient with metastatic tumors, thereby highlighting the potential clinical significance of early detection of cancer metastasis.

| S-EPMC10625696 | biostudies-literature

Deep generative neural network for accurate drug response imputation.

Project description:Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational autoencoder (VAE) model to compress thousands of genes into latent vectors in a low-dimensional space. We then demonstrate that these encoded vectors could accurately impute drug response, outperform standard signature-gene based approaches, and appropriately control the overfitting problem. We apply rigorous quality assessment and validation, including assessing the impact of cell line lineage, cross-validation, cross-panel evaluation, and application in independent clinical data sets, to warrant the accuracy of the imputed drug response in both cell lines and cancer samples. Specifically, the expression-regulated component (EReX) of the observed drug response achieves high correlation across panels. Using the well-trained models, we impute drug response of The Cancer Genome Atlas data and investigate the features and signatures associated with the imputed drug response, including cell line origins, somatic mutations and tumor mutation burdens, tumor microenvironment, and confounding factors. In summary, our deep learning method and the results are useful for the study of signatures and markers of drug response.

| S-EPMC7979803 | biostudies-literature

Deep Convolutional Neural Network with Deconvolution and a Deep Autoencoder for Fault Detection and Diagnosis.

Project description:In chemical plants and other industrial facilities, the rapid and accurate detection of the root causes of process faults is essential for the prevention of unknown accidents. This study focused on deep learning while considering the different phenomena that can occur in industrial facilities. A deep convolutional neural network with deconvolution and a deep autoencoder (DDD) is proposed. DDD assesses the process dynamics and the nonlinearity between process variables. During the operation of DDD, fault detection is carried out using the reconstruction error between the data reconstructed through the model and the input data. After a process fault is detected, the magnitude of the contribution of each process variable to the detected process fault is calculated by applying gradient-weighted class activation mapping to the established network. The effectiveness of DDD in fault detection and diagnosis was verified through experiments on the Tennessee Eastman process dataset, demonstrating that it can achieve improved performance compared to the conventional fault detection and diagnosis.

| S-EPMC8772318 | biostudies-literature

Accurate deep neural network inference using computational phase-change memory.

Project description:In-memory computing using resistive memory devices is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. However, due to device variability and noise, the network needs to be trained in a specific way so that transferring the digitally trained weights to the analog resistive memory devices will not result in significant loss of accuracy. Here, we introduce a methodology to train ResNet-type convolutional neural networks that results in no appreciable accuracy loss when transferring weights to phase-change memory (PCM) devices. We also propose a compensation technique that exploits the batch normalization parameters to improve the accuracy retention over time. We achieve a classification accuracy of 93.7% on CIFAR-10 and a top-1 accuracy of 71.6% on ImageNet benchmarks after mapping the trained weights to PCM. Our hardware results on CIFAR-10 with ResNet-32 demonstrate an accuracy above 93.5% retained over a one-day period, where each of the 361,722 synaptic weights is programmed on just two PCM devices organized in a differential configuration.

| S-EPMC7235046 | biostudies-literature

Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network.

Project description:The ability to predict tandem mass (MS/MS) spectra from peptide sequences can significantly enhance our understanding of the peptide fragmentation process and could improve peptide identification in proteomics. However, current approaches for predicting high-energy collisional dissociation (HCD) spectra are limited to predict the intensities of expected ion types, that is, the a/b/c/x/y/z ions and their neutral loss derivatives (referred to as backbone ions). In practice, backbone ions only account for <70% of total ion intensities in HCD spectra, indicating many intense ions are ignored by current predictors. In this paper, we present a deep learning approach that can predict the complete spectra (both backbone and nonbackbone ions) directly from peptide sequences. We made no assumptions or expectations on which kind of ions to predict but instead predicting the intensities for all possible m/z. Training this model needs no annotations of fragment ion nor any prior knowledge of the fragmentation rules. Our analyses show that the predicted 2+ and 3+ HCD spectra are highly similar to the experimental spectra, with average full-spectrum cosine similarities of 0.820 (±0.088) and 0.786 (±0.085), respectively, very close to the similarities between the experimental replicated spectra. In contrast, the best-performed backbone only models can only achieve an average similarity below 0.75 and 0.70 for 2+ and 3+ spectra, respectively. Furthermore, we developed a multitask learning (MTL) approach for predicting spectra of insufficient training samples, which allows our model to make accurate predictions for electron transfer dissociation (ETD) spectra and HCD spectra of less abundant charges (1+ and 4+).

| S-EPMC8057055 | biostudies-literature

Simultaneous detection and deconvolution of congested NMR spectra containing three isotopically labeled species.

Project description:We present a procedure for isolating subspectra corresponding to individual protein or peptide components in a ternary mixture or complex. Each of the three-component species is labeled differently: species A uniformly with 15N, species B uniformly with 15N and 13C, and species C uniformly with 15N but selectively with 13C' or 13Calpha. By using the dual carbon label selective HSQC (DCLS-HSQC) pulse sequence and exploiting differences in 1J 15N-13C coupling patterns to filter selected 15N resonances from detection during a constant time period, a subspectrum from each species can be generated from three spectra acquired from a single sample. Many important biological pathways involve dynamic interactions among members of multicomponent protein assemblies, and this approach offers a powerful way to monitor such processes.

| S-EPMC2662704 | biostudies-literature

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

Project description: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.

| S-EPMC8300483 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data