Guided Ensemble Stacking Method for Predicting Biological Activities of Compounds
Bibliographic record
Abstract
ABSTRACT Machine learning (ML)‐driven quantitative structure–activity relationship (QSAR) modeling has gained significant attention for predicting compound biological activity based on compounds' structural, chemical, and physical properties because of the advancement of ML techniques. However, traditional ML‐QSAR models often suffer from biases due to algorithm selection and limitations in training data. Additionally, these approaches root in deducing biological activities purely from compounds' structural information and disregard their pharmacokinetic (PK) properties, a key factor contributing to the 15% failure rate in clinical trials, limiting their applicability in drug discovery. To address these challenges, we propose a guided ensemble‐based ML approach that integrates a supervised data preparation strategy with an ensemble stacking method, leveraging the strengths of multiple ML algorithms. By incorporating PK properties, our approach enhances prediction reliability. Specifically, we developed two ensemble stacking models: The classification model predicts the biological activity type, “inhibition” versus “activation,” based on compound features, while the regression model predicts bioactivity values. The classification model achieved an accuracy exceeding 0.85, while the regression model attained an R 2 above 0.77, demonstrating superior performance over traditional QSAR models. These results highlight the potential of our approach in improving drug discovery pipelines by enhancing predictive accuracy and addressing key QSAR limitations.
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 | 0.002 |
| 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 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".