# SaProt 650M structure-aware protein language model weights

## Facts

- Provider: Westlake University (westlake-repl)
- License: MIT (https://github.com/westlake-repl/SaProt/blob/main/LICENSE)
- Size: 8 files
- Format: JSON (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/westlake-repl/SaProt_650M_AF2
- Access: public, readable without an account
- Category: Biology
- Source: https://openreview.net/forum?id=6MRm3G4NiU
- Page: https://scigantic.com/archive/ff7d5b7a-d120-5ffb-ba30-85fa4a6ebc24
- Keywords: Biology, protein structure, protein language model, JSON, Hugging Face

## About

Open weights for SaProt 650M, a structure-aware protein language model from Westlake University. Its vocabulary pairs each amino acid with a Foldseek 3Di structure token, so a protein is read as a sequence of residue plus local-structure tokens, and the model was pretrained on AlphaFold2-predicted structures. With structure tokens as input it outperforms sequence-only models on many fitness and function tasks; sequence-only input works but needs fine-tuning. The mounted repo holds SaProt_650M_AF2.pt (esm-style checkpoint), pytorch_model.bin with config.json and vocab.txt for transformers (EsmForMaskedLM), each about 2.6 GB. Pair it with the AlphaFold DB or PDB archives to build structure tokens next to the data. MIT licence.

## Load the data

```python
import os, json
base = "/mnt/archive"   # this model repo, mounted read-only
files = sorted(os.listdir(base)); print(files)
print(json.dumps(json.load(open(os.path.join(base, "config.json"))), indent=1)[:800])
print("SaProt_650M_AF2.pt", os.path.getsize(os.path.join(base, "SaProt_650M_AF2.pt")) // 2**20, "MB")
```

Written for a Scigantic notebook, where /mnt/archive (SCIGANTIC_MOUNT_PATH) is the mounted dataset.

## Data structure

File types in sampled files: JSON

Example file: `SaProt_650M_AF2.pt`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ff7d5b7a-d120-5ffb-ba30-85fa4a6ebc24
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ff7d5b7a-d120-5ffb-ba30-85fa4a6ebc24
- Over MCP: `get_schema_card` with id `ff7d5b7a-d120-5ffb-ba30-85fa4a6ebc24` at https://api.scigantic.com/mcp

## Related topics

- [JSON datasets](https://scigantic.com/topics/json)
- [Protein structure datasets](https://scigantic.com/topics/protein-structure)
- [Biology datasets](https://scigantic.com/topics/biology)
- [Protein language model datasets](https://scigantic.com/topics/protein-language-model)
