EDLMPPI: Learning the Protein Language of Proteome-wide Protein-protein Binding Sites via Explainable Ensemble Deep Learning
Bibliographic record
Abstract
Abstract Protein-protein interactions (PPIs) govern cellular pathways and processes, by significantly influencing the functional expression of proteins. Therefore, accurate identification of protein-protein interaction binding sites has become a key step in the functional analysis of proteins. We develop an ensemble deep learning model (EDLMPPI)-based protein-protein interaction site identification method. In particular, we propose to apply a transformer structure-based dynamic word embedding model (ProtT5) to extract potential associations between protein primary structures, capturing their functional and structural properties from readily available sequence data alone. After that, EDLMPPI is based on BiLSTM in order to sufficiently learn the contextual associations between features and to preserve the contextual information through a capsule network to further improve the generalization performance. To address the unbalanced dataset, we employ ensemble learning to train multiple models and then integrate them to further enhance the performance of the algorithm. Evaluation results show that EDLMPPI can achieve the best results on all datasets. Meanwhile, we compared EDLMPPI with other PPI site prediction models and observed that EDLMPPI outperformed the state-of-the-art models by nearly 10% in terms of average accuracy. In addition, the biological and interpretable analyses provide new insights into proteins binding site identification and characterization mechanisms from different perspectives.
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 | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".