# Researchers release ProBEiT, a 400M-parameter protein model

Digest AI · Research · published 2026-10-26T00:00:00Z

Canonical: https://digestai.news/story/researchers-release-probeit-a-400m-parameter-protein-model

## Summary

Researchers have introduced ProBEiT, a multimodal protein language model designed to integrate structural information with amino-acid sequences. The architecture uses an implicit mixture-of-experts scheme with deterministic routing to process discrete, tokenized structures alongside sequence data. This approach aims to improve the prediction of protein function and mutational effects without the high computational costs associated with larger models.

ProBEiT was trained on 1.7 million proteins from the AlphaFoldDB. With 400 million parameters, the model reportedly surpasses larger baselines across six tasks involving fitness prediction and functional annotation. The authors note that ProBEiT achieves strong accuracy early in the continual training period, which reduces overall computational requirements compared to billion-scale models.

In experimental tests, the model was applied to thermostability engineering of glycerol-3-phosphate oxidase. It successfully identified optimized variants with positive epistatic effects. The study, published in Nature Machine Learning, suggests that tightly coupling structural context with sequence modeling in a modality-specialized framework enables efficient protein engineering.

## Key points

- ProBEiT is a 400 million-parameter multimodal model trained on 1.7 million AlphaFoldDB proteins.
- It uses an implicit mixture-of-experts scheme to jointly encode sequences and tokenized structures.
- The model outperforms larger baselines on six tasks and identifies optimized protein variants in experiments.

## Why it matters

ProBEiT offers a more efficient way to predict protein function and engineering outcomes by combining sequence and structure data, potentially lowering the computational barrier for protein design research.

## Sources

1. [Efficient structural information integration into protein language models with implicit mixture-of-experts ProBEiT](https://nature.com/articles/s42003-026-10816-6) (Nature Machine Learning, 2026-10-26, primary source)

## Cite

Digest AI, "Researchers release ProBEiT, a 400M-parameter protein model", 26 October 2026, https://digestai.news/story/researchers-release-probeit-a-400m-parameter-protein-model

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-release-probeit-a-400m-parameter-protein-model.json