A pilot study for fragment identification using 2D NMR and deep learning
Explore this paper's citation graph
Summary
HMBC data and the combination of HMBC and HSQC show better results than HSQC alone in this pilot study, and results indicate that it can work for mixtures when trained on pure compounds only.
- Type
- preprint
- Published
- 2021-03-18
- Cited by
- 23
- References
- 49
- Access
- Open access
- OpenAlex
- https://openalex.org/W3137032621
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:232320719
Keywords
Heteronuclear single quantum coherence spectroscopy, Bespoke, Convolutional neural network, Identification (biology), Fragment (logic)
References
- Digital Image Processing
- Proposed minimum reporting standards for chemical analysis
- Facilitating quality control for spectra assignments of small organic molecules: nmrshiftdb2 – a free in‐house NMR database with integrated LIMS for academic service laboratories
- Pattern recognition methods and applications in biomedical magnetic resonance
- Do We Need More Training Data?
- Identification and structure elucidation by NMR spectroscopy
- Progress on an open source computer-assisted structure elucidation suite (SENECA)
- MASS SPECTROMETRY IMAGING FOR DRUGS AND METABOLITES
- Web Server Suite for Complex Mixture Analysis by Covariance NMR
- The Future of NMR-Based Metabolomics
- Comprehensive Metabolite Identification Strategy using Multiple 2D NMR Spectra of a Complex Mixture Implemented in the COLMARm Web Server
- Small Molecule Accurate Recognition Technology (SMART) to Enhance Natural Products Research
- NMRNet: a deep learning approach to automated peak picking of protein NMR spectra
- Propagating annotations of molecular networks using in silico fragmentation
- Bayesian networks for mass spectrometric metabolite identification via molecular fingerprints
- Identification of Unknown Metabolomics Mixture Compounds by Combining NMR, MS, and Cheminformatics
- Deciphering complex metabolite mixtures by unsupervised and supervised substructure discovery and semi-automated annotation from MS/MS spectra
- Deep Learning on Small Datasets without Pre-Training using Cosine Loss
- An integrated approach for mixture analysis using MS and NMR techniques.
- Triplet NOAH supersequences optimised for small molecule structure characterisation
Cited by
- A data-oriented approach to making new molecules as a student experiment: AI-enabling FAIR publication of NMR data for organic esters.
- Deep Learning-Based Method for Compound Identification in NMR Spectra of Mixtures
- Automated analysis for multiplet identification from ultra-high resolution 2D- 1H, 13C-HSQC NMR spectra
- Direct deduction of chemical class from NMR spectra
- Exploring Image Processing Tools To Unravel Complex 1H–13C Heteronuclear Single-Quantum Correlation Nuclear Magnetic Resonance Spectra: A Demonstration for Pyrolysis Liquids
- Machine learning-assisted structure annotation of natural products based on MS and NMR data.
- DeepSAT: Learning Molecular Structures from Nuclear Magnetic Resonance Data
- Structure Seer – a machine learning model for chemical structure elucidation from node labelling of a molecular graph
- Advanced technologies targeting isolation and characterization of natural products
- Can Graph Machines Accurately Estimate 13C NMR Chemical Shifts of Benzenic Compounds?
- Nuclear Magnetic Resonance and Artificial Intelligence
- Deep learning and its applications in nuclear magnetic resonance spectroscopy.
- Advances in AI-based strategies and tools to facilitate natural product and drug development
- Automated Determination of the Molecular Substructure from Nuclear Magnetic Resonance Spectra Using Neural Networks
- Recent advances in computational NMR of organic compounds, natural products, and carbohydrates. Theory and applications
- Structure characterization with NMR molecular networking
- VirMolAnalyte: An AI-Driven In Silico Metabolite Annotation Tool.
- Interpreting 2D-NMR spectra using Grad-CAM
- Statistical methods in the NMR spectral analysis
- NMR-Challenge for LLMs: Evaluating Chemical Reasoning in Humans and AI
Related papers
- Fast profiling of metabolite mixtures using chemometric analysis of a speeded-up 2D heteronuclear correlation NMR experiment
- Simultaneous acquisition of two 2D HSQC spectra with different 13C spectral widths.
- QQ‐HSQC: a quick, quantitative heteronuclear correlation experiment for NMR spectroscopy
- Interleaved Dual NMR Acquisition of Equivalent Transfer Pathways in TOCSY and HSQC Experiments.
- Structural studies of complicated natural products by new NMR techniques
- Computer assisted assignment of 13C or 15N edited 3D-NOESY-HSQC spectra using back calculated and experimental spectra.
- Unsymmetrical covariance processing of COSY or TOCSY and HSQC NMR data to obtain the equivalent of HSQC‐COSY or HSQC‐TOCSY spectra
- Quantitative, equal carbon response HSQC experiment, QEC-HSQC.