Machine Learning-Based Bioactivity Classification of Natural Products Using LC-MS/MS Metabolomics
Bibliographic record
Abstract
The rediscovery of known drug classes represents a major challenge in natural products drug discovery. Compound rediscovery inhibits the ability of researchers to explore novel natural products and wastes significant amounts of time and resources. This study introduces a novel machine learning framework that can effectively characterize the bioactivity of natural products by leveraging liquid chromatography tandem mass spectrometry and untargeted metabolomics analysis. This accelerates natural product drug discovery by addressing the challenge of dereplicating previously discovered bioactive compounds. Utilizing the SIRIUS 5 metabolomics software suite and in-silico -generated fragmentation spectra, we have trained a ML model capable of predicting a compound’s drug class. This approach enables the rapid identification of bioactive scaffolds from LC-MS/MS data, even without reference experimental spectra. The model was trained on a diverse set of molecular fingerprints generated by SIRIUS 5 to effectively classify compounds based on their core pharmacophores. Our model robustly classified 21 diverse bioactive drug classes, achieving accuracies greater than 93% on experimental spectra. This study underscores the potential of ML combined with MFPs to dereplicate bioactive natural products based on pharmacophore, streamlining the discovery process and expediting improved methods of isolating novel antibacterial and antifungal agents.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".