How to Use ParaSurf

ParaSurf is a deep learning framework that predicts paratope binding sites by analyzing molecular surfaces of antibodies/nanobodies to identify antigen-binding regions across the entire Fab/Fv domain.

The submission workflow is tailored around inputs such as Input Structure, which keeps computational setup aligned with experimental context.

The 1.0 results page exposes analysis sections like Predicted Binding Site Residue and Predicted Binding Site Atoms, output artifacts such as parasurf_pred.pdb, and interactive views including protein viewer and results table1 for rapid annotation prioritization and export-ready reporting.

ParaSurf is a deep learning framework that predicts paratope binding sites by analyzing molecular surfaces of antibodies/nanobodies to identify antigen-binding regions across the entire Fab/Fv domain. Combining geometric shape, chemical properties, and electrostatic force fields, ParaSurf employs a hybrid 3D ResNet-Transformer architecture to capture both local and global structural contexts. ParaSurf addresses class imbalance and generalizes to framework residues, enabling antigen-agnostic predictions for therapeutic antibody design and immune interaction studies.

Core capabilities include Predicts antibody-binding sites across the entire Fab region, including CDR loops and framework residues, using balanced sampling to mitigate class imbalance., Integrates geometric, chemical, and electrostatic surface features (AMBER/CHARMM force fields) for comprehensive interaction modeling., and Employs a hybrid 3D ResNet-Transformer architecture to capture multi-scale spatial patterns from local atomic environments to global structural contexts., which directly shape how outputs should be interpreted for this method.

In practice, interpretation proceeds through inputs (Input Structure), result sections (Predicted Binding Site Residue and Predicted Binding Site Atoms), files (parasurf_pred.pdb), and visual components (protein viewer and results table1), which makes ParaSurf outputs easier to triage and act on across large job batches.

• Study-fit inputs: ParaSurf accepts Input Structure, reducing preprocessing friction and preserving experimental context.
• Protocol control: Researchers can tune Predicts antibody-binding sites across the entire Fab region, including CDR loops and framework residues, using balanced sampling to mitigate class imbalance., Integrates geometric, chemical, and electrostatic surface features (AMBER/CHARMM force fields) for comprehensive interaction modeling., and Employs a hybrid 3D ResNet-Transformer architecture to capture multi-scale spatial patterns from local atomic environments to global structural contexts. to match assay constraints, confidence thresholds, and downstream validation plans.
• Readable evidence: Results are presented through Predicted Binding Site Residue and Predicted Binding Site Atoms, parasurf_pred.pdb, and protein viewer and results table1, improving cross-run comparison and scientific communication.
• Faster iteration: Managed execution on Neurosnap removes infrastructure overhead so teams can focus on sequence annotation and function-focused filtering rather than deployment and environment maintenance.