Predicting the Ionization Behavior of Drugs in Tissue in MALDI and MALDI-2 Mass Spectrometry Imaging Using Machine Learning
Bibliographic record
Abstract
Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) and its most common application, MALD-MS imaging (MSI), are widely used techniques in the analysis of intact biomolecules. In the context of pharmaceutical research, MALDI-MSI is often used to investigate the distribution of drugs and their metabolites within tissue section. While postionization strategies such as MALDI-2 have helped to increase signal intensities, ion yields in MALDI(-2) analysis are notoriously hard to predict. In many cases, this can complicate the planning and execution of pharmaceutical studies with regard to the expected limits of detection. To mitigate these challenges, we present a first approach to utilizing machine learning (ML) for the prediction of ionization efficiency. For this, we use data from a previously published data set containing MALDI and MALDI-2 data in positive and negative ion modes of ca. 1200 drug-like compounds acquired under imaging like conditions. To identify the optimal mode of action, we tested six different ML models and utilized selected physicochemical properties and 2-dimensional structures, both available for all employed compounds, for teaching. Subsequent SHAP analysis confirmed the involvement of a large number of parameters in the prediction as opposed to a dominant role of the presence or absence of a limited number of functional groups. In this, our proof-of-concept study highlights the usefulness of the multifactorial nature of ML to predict ion yields in MALDI(-2)-MSI. Beyond pharmacological application, the approach could, in the future, also assist in predicting ionizability in general MALDI-/MALDI-2-MSI measurements.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".