GraphBAN: An inductive graph-based approach for enhanced prediction of compound-protein interactions
Bibliographic record
Abstract
Understanding compound-protein interactions is crucial for early drug discovery, offering insights into molecular mechanisms and potential therapeutic effects of compounds. Here, we introduce GraphBAN, a graph-based framework that inductively predicts these interactions using compound and protein feature information. GraphBAN effectively handles inductive link predictions for unseen nodes, providing a robust solution for predicting interactions between entirely unseen compounds and proteins. This capability enables GraphBAN to transcend the constraints of traditional methods that are typically limited to known contexts. GraphBAN employs a knowledge distillation architecture through a teacher-student learning model. The teacher block leverages network structure information, while the student block focuses on node attributes, enhancing learning and prediction accuracy. Additionally, GraphBAN incorporates a domain adaptation module, increasing its effectiveness across different dataset domains. Empirical tests on five benchmark datasets demonstrate that GraphBAN outperforms ten baseline models, while a case study analysis with the Pin1 protein further supports the model’s effectiveness in real world scenarios, making it as a promising tool for early drug discovery. The authors in this work develop GraphBAN, a graph-based deep learning model, that predicts compound-protein interactions for both new, unseen, and existing, known data. It outperforms ten baseline models, and a case study highlights its potential to discover valuable drug candidates.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".