Join Persistent Homology (JPH)-Based Machine Learning for Metalloprotein–Ligand Binding Affinity Prediction
Bibliographic record
Abstract
With the crucial role of metalloproteins in respiration, oxidative stress protection, photosynthesis, and drug metabolism, the design and discovery of drugs that can target metalloproteins are extremely important. Recently, enormous potential has been shown by topological data analysis (TDA) and TDA-based machine learning models in various steps of drug design and discovery. Here, we propose, for the first time, join persistent homology (JPH) and JPH-based machine learning models for metalloprotein-ligand binding affinity prediction. Mathematically, dramatically different from persistent homology and extended persistent homology, our JPH employs a set of filtration functions to generate a multistage filtration for the join of the original simplicial complex and a specially designed test simplicial complex. From the featurization perspective, our JPH-based molecular descriptors can provide a more comprehensive characterization of the intrinsic topological information of the data. Our JPH descriptors are combined with the gradient boosting tree (GBT) model for metalloprotein-ligand binding affinity prediction. The benchmark dataset for metalloprotein-ligand complexes from PDBbind-v2020 is employed for the validation and comparison of our model. It has been found that our JPH-GBT model can outperform all of the existing models, as far as we know. This demonstrates the great potential of our join persistent homology in the characterization of molecular structures and functions.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| 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".