# Drug Companies’ Data Boosts AI Protein Models

Digest AI · Generative AI & Models · published 2026-09-14T00:00:00Z

Canonical: https://digestai.news/story/drug-companies-data-boosts-ai-protein-models

## Summary

For drug discovery, protein-folding models like AlphaFold face a data shortage. To improve these AI tools, pharmaceutical companies are sharing proprietary datasets of proteins interacting with drugs. A consortium trained an open-source model on over 20,000 such structures and found it outperformed public models by significantly improving prediction accuracy. This suggests that making more of this internal data publicly available could enhance AI’s utility in drug development. The initiative, called the AISB Network, involves multiple companies fine-tuning a model on their specific datasets while keeping proprietary information confidential.

## Key points

- Pharmaceutical companies share proprietary protein-ligand interaction data
- OpenFold3 model trained on more than 20,000 internal structures outperforms public models
- AISB Network fine-tunes OpenFold3 on company-specific datasets

## Why it matters

This collaboration could lead to more accurate AI predictions for drug interactions, potentially accelerating the drug discovery process.

## Sources

1. [Drug firms’ secret data supercharge AI protein models](https://nature.com/articles/d41586-026-02882-x) (Nature Machine Learning, 2026-09-14, primary source)

## Cite

Digest AI, "Drug Companies’ Data Boosts AI Protein Models", 14 September 2026, https://digestai.news/story/drug-companies-data-boosts-ai-protein-models

---

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/drug-companies-data-boosts-ai-protein-models.json