Advancing Reversed-Phase Chromatography Analytics of Influenza Vaccines Using Machine Learning Approaches on a Diverse Range of Antigens and Formulations
Bibliographic record
Abstract
One concern in the yearly re-formulation of influenza vaccines is the time-consuming manufacturing of vaccine potency reagents, particularly for emergency responses. The continuous evaluation of modern techniques such as reversed-phase (RP) chromatography is an asset for streamlining this process. One challenge with RP methods, however, is the need to re-optimize methods for antigens that show poor separation, which can be highly dependent on analyst experience and available data. In this study, we leveraged a large RP dataset of influenza antigens to explore machine learning (ML) approaches of classifying challenging separations for computer-assisted method re-optimization across years, products, and analysts. Methods: To address recurring chromatographic issues—such as poor resolution, strain co-elution, and signal absence—we applied data augmentation techniques to correct class imbalance and trained multiple supervised ML classifiers to distinguish between these peak profiles. Results: With data augmentation, several ML models demonstrated promising accuracy in classifying chromatographic profiles according to the provided labels. These models effectively distinguished patterns indicative of separation issues in real-world data. Conclusions Our findings highlight the potential of ML as a computer assisted tool in the evaluation of vaccine quality, offering a scalable and objective approach to chromatogram classification. By reducing reliance on manual interpretation, ML can expedite the optimization of analytical methods, which is particularly needed for rapid responses. Future research involving larger, inter-laboratory datasets will further elucidate the utility of ML in vaccine analysis.
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 | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".