B3clf: A Resampling-Integrated Machine Learning Framework to Predict Blood-Brain Barrier Permeability
Bibliographic record
Abstract
Developing accurate, computationally efficient, and reliable predictive models for small molecules' blood-brain barrier (BBB) permeability is challenging due to the class imbalance often found in collections of reference data. We use resampling techniques to address class imbalance and build 24 types of machine learning models, which we developed using comprehensive hyperparameter optimizations. We evaluated our model against those from previous studies, which provides insight into optimal classification models and resampling techniques that are relevant beyond BBB permeability. In addition to classifying unknown compounds on the basis of BBB permeability, the predicted probabilities are provided to facilitate further improvements and comparative benchmarking, and to report the models' confidence in their predictions. To disseminate our findings, we developed B3clf, a highly efficient, user-friendly tool that facilitates BBB permeability prediction, which can be accessed as open-source software https://github.com/theochem/B3clf or as a web app https://huggingface.co/spaces/QCDevs/b3clf. The newly curated external dataset for BBB is hosted at https://github.com/theochem/B3DB.
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 | 0.005 | 0.014 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".