Fig 1.
Overview of the PepAnno platform’s functionalities.
The platform is organized into three main modules: (A) Feature Calculation: Peptide feature calculation, encompassing basic information and physicochemical properties. (B) Structure Prediction: Structure prediction, which includes calculating scores for secondary structure elements and predicting tertiary structures. (C) Function Prediction: Bioactive function prediction, covering seven key activities with structural interpretability attention.
Table 1.
Ablation Study on the AVP Task (5-Fold Cross-Validation).
Fig 2.
Length-stratified evaluation on the AVP independent test set.
Table 2.
Residue-level mechanistic interpretation of PepAnno predictions for HNP-1.
Table 3.
Detailed information of datasets collected from publications.
Fig 3.
(A) Overall performance (AUC, ACC, and F1-score) of the proposed model across seven peptide categories on the independent test dataset.
(B) Radar chart comparisons of PepAnno and existing tools on the AVP and ACP categories. PepAnno is highlighted for clarity.
Fig 4.
(A) Comprehensive multi-functional prediction of HNP-1 by PepAnno.
(B) Residue-level attention patterns of HNP-1 across seven functional prediction heads.
Fig 5.
Backend workflow of the PepAnno platform.
The process involves: (1) User data input (peptide sequences and parameters) followed by preprocessing. (2) Calculation of various peptide physicochemical features using toolkits. (3) Tertiary structure prediction of peptides. (4) Input of processed data into functional prediction model. (5) Final output of three main data files: comprehensive feature data, structural information, and integrated prediction results for all functions.
Fig 6.
The overall illustration of PepAnno’s structure-aware multi-view geometric deep learning framework.