positional-encoding-for-spectral-sequences - Positional encoding for mass spectrum tensors in IDSL_MINT
Embeds ordinal and sequential information into mass spectrum m/z-intensity pairs for transformer encoder layers in IDSL_MINT.
Tags
Updated: 2026-09-17Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Compute sinusoidal positional encodings
- Add positional encodings to embeddings
- Prepare spectrum input tensors
- Broadcast encodings across batch dimension
Inputs
- Input spectrum feature tensor
- Model dimension (d_model)
- Maximum spectrum length
Outputs
- Positional encoding added spectrum tensor
- Positional encoding matrix
Requirements
- Python
- PyTorch
- RDKit