Enter a peptide sequence and let our 9 ML/DL ensemble predict antioxidant activity.
Enter a peptide sequence and select one or more models, then click Predict.
Download our curated antioxidant peptide database —— AoXpDb.
Comprehensive metadata for all peptides including sequences, activities, and physicochemical properties.
⬇ Download XLSXAll peptide sequences in standard FASTA format, ready for embedding or alignment tools.
⬇ Download FASTAComplete dataset in CSV format with binary labels for use in machine learning pipelines.
⬇ Download CSVIf you use AoXpDb or this prediction tool in your research, please cite the following publication.
We developed an AI-driven multilayer strategy combined with a curated dataset for mining antioxidant peptides from yak bone collagen hydrolysates. This tool provides access to the trained prediction models and the AoXpDb database introduced in the study.
When using the AoXpDb online predictor to screen peptides for antioxidant activity.
When downloading and using the AoXpDb dataset (FASTA, CSV, or metadata).
When benchmarking our models (LR, RF, KNN, SVM, MLP, XGB, LGBM, CNN, LSTM) in your own work.
A curated database and AI prediction platform for antioxidant peptides derived from yak bone collagen hydrolysates.
All sequences are encoded using Meta's ESM-2 protein language model (esm2_t6_8M_UR50D, 320-dimensional). Mean pooling across residues produces fixed-length feature vectors for classification.
Traditional ML models were optimized via 10-fold GridSearchCV (accuracy-scored). CNN and LSTM models used 10-fold CV with Adam optimizer across a grid of learning rates and hidden dimensions.
AoXpDb contains curated antioxidant and non-antioxidant peptide sequences from yak bone collagen hydrolysates. Training used balanced embeddings to address class imbalance.
| Model | Full Name | Type | Hyperparameter Search |
|---|