Structure characterization with NMR molecular networking
Bibliographic record
Abstract
Nuclear Magnetic Resonance (NMR) is among the most widely used techniques for structure determination, yet automated workflows remain underdeveloped compared to mass spectrometry. In this work, we introduce NMR molecular networking and apply it to Heteronuclear Single Quantum Coherence (HSQC) spectra, a key 2D-NMR experiment for structure elucidation. We adapt core principles of MS² networking such as transitivity across multiple spectra, dereplication, and annotation propagation to NMR-driven workflows. First, we develop a modified Hungarian distance metric for HSQC peak matching. Benchmarks show that using this metric, traditional spectral lookup with this score recovers ~70-80% of available structural similarity, but efficiency does not improve when increasing the size of the spectral library. Second, we establish NMR molecular networking using HSQC spectra to propagate annotations and dereplicate compounds. Case studies of experimental natural product spectra demonstrate that annotation transitivity within networks accelerates and improves identification of unknowns. Third, we introduce algorithmic molecular networking, which integrates graph topology metrics to correct inefficient rankings and reduce false positives. Together, these approaches define the first generalizable framework for NMR molecular networking, enabling scalable, high-throughput annotation for natural product discovery and drug development. Nuclear Magnetic Resonance (NMR) is crucial for structure determination, yet automated workflows remain underdeveloped compared to mass spectrometry (MS). Here, the authors introduce NMR molecular networking for HSQC spectra, adapting core principle of MS2 networking, enhancing annotation and dereplication through innovative algorithms, which significantly improve the identification of unknown metabolites.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".