Bayesian optimization of separation gradients to maximize the performance of untargeted LC-MS
Bibliographic record
Abstract
Abstract Liquid chromatography (LC) with gradient elution is a routine practice for separating complex chemical mixtures in mass spectrometry (MS)-based untargeted analysis. Despite its prevalence, systematic optimization of LC gradients has remained challenging. Here we develop a Bayesian optimization method, BAGO, for autonomous and efficient LC gradient optimization. BAGO is an active learning strategy that discovers the optimal gradient using limited experimental data. From over 100,000 plausible gradients, BAGO locates the optimal LC gradient within ten sample analyses. We validated BAGO on six biological studies of different sample matrices and LC columns, showing that BAGO can significantly improve quantitative performance, tandem MS spectral coverage, and spectral purity. For instance, the optimized gradient increases the count of annotated compounds meeting quantification criteria by up to 48.5%. Furthermore, applying BAGO in a Drosophila metabolomics study, an additional 57 metabolites and 126 lipids were annotated. The BAGO algorithms were implemented into user-friendly software for everyday laboratory practice and a Python package for its flexible extension.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".