# PottsMPNN

Published articles for PottsMPNN.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## PottsMPNN uses machine learning to improve computational protein design

DevFeed: [PottsMPNN uses machine learning to improve computational protein design](<https://devfeed.tech/articles/looking-beyond-natural-sequences-37963.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/looking-beyond-natural-sequences-0827>)

Author: Lillian Eden | Department of Biology

Published: 2026-08-27T19:20:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-in-biology](<https://devfeed.tech/tags/ai-in-biology.md>), [amino-acids](<https://devfeed.tech/tags/amino-acids.md>), [amy-keating](<https://devfeed.tech/tags/amy-keating.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [biological-engineering](<https://devfeed.tech/tags/biological-engineering.md>), [biology](<https://devfeed.tech/tags/biology.md>), [computational-protein-design](<https://devfeed.tech/tags/computational-protein-design.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [foster-birnbaum](<https://devfeed.tech/tags/foster-birnbaum.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mit-department-of-biology](<https://devfeed.tech/tags/mit-department-of-biology.md>), [native-sequence-recovery](<https://devfeed.tech/tags/native-sequence-recovery.md>), [novel-protein-design](<https://devfeed.tech/tags/novel-protein-design.md>), [pottsmpnn](<https://devfeed.tech/tags/pottsmpnn.md>), [proteins](<https://devfeed.tech/tags/proteins.md>), [research](<https://devfeed.tech/tags/research.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [school-of-science](<https://devfeed.tech/tags/school-of-science.md>)

### AI overview

Researchers developed PottsMPNN, a machine-learning framework for computational protein design that incorporates physical principles governing protein structure and stability. The framework evaluates generated sequences by their likelihood of folding into desired structures and by its ability to predict mutation effects, rather than by how closely they match naturally occurring sequences.

### Source excerpt

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.