Pose Ensemble Graph Neural Networks to Improve Docking Performances
Bibliographic record
Abstract
Training data material and trained model of DockBox2 (DBX2). DBX2 is an innovative approach that encodes ensembles of computational docking poses into a graph neural network (GNN) architecture, leveraging energy-based features derived from molecular docking. The model is jointly trained on the PDBbind database to predict binding pose likelihood at the node level and binding affinity at the graph level.The training data for DBX2 was prepared by derived from the PDBbind v2016 dataset. Molecular docking simulations were performed using the DockBox (DBX) package, which integrates AutoDock, Vina, and DOCK software. The generated binding poses were subjected to energy minimization using AmberTools 17, followed by rescoring with the AutoDock, Vina, DOCK, and DSX scoring functions.The results are summarized in the Training_validation.csv file, which was used to generate graphs (graphs.pkl) for training the DBX2 model. Files include: model.h5: The trained DBX2 model. Filtered_Training_validation.csv: CSV file containing all training and validation data. graphs.pkl: Pickle file with all DBX2 graph data. Info.csv: A CSV file containing the pKd/pKi values and associated protein families for each PDB entry from the PDBbind v2016 dataset.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.004 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.018 | 0.011 |
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".