Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912349217095680 |
|---|---|
| author | Ghafarollahi, Alireza Buehler, Markus J. |
| author_facet | Ghafarollahi, Alireza Buehler, Markus J. |
| contents | Advances in artificial intelligence (AI) promise autonomous discovery, yet most systems still resurface knowledge latent in their training data. We present Sparks, a multi-modal multi-agent AI model that executes the entire discovery cycle that includes hypothesis generation, experiment design and iterative refinement to develop generalizable principles and a report without human intervention. Applied to protein science, Sparks uncovered two previously unknown phenomena: (i) a length-dependent mechanical crossover whereby beta-sheet-biased peptides surpass alpha-helical ones in unfolding force beyond ~80 residues, establishing a new design principle for peptide mechanics; and (ii) a chain-length/secondary-structure stability map revealing unexpectedly robust beta-sheet-rich architectures and a "frustration zone" of high variance in mixed alpha/beta folds. These findings emerged from fully self-directed reasoning cycles that combined generative sequence design, high-accuracy structure prediction and physics-aware property models, with paired generation-and-reflection agents enforcing self-correction and reproducibility. The key result is that Sparks can independently conduct rigorous scientific inquiry and identify previously unknown scientific principles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19017 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles Ghafarollahi, Alireza Buehler, Markus J. Artificial Intelligence Materials Science Soft Condensed Matter Machine Learning Biomolecules Advances in artificial intelligence (AI) promise autonomous discovery, yet most systems still resurface knowledge latent in their training data. We present Sparks, a multi-modal multi-agent AI model that executes the entire discovery cycle that includes hypothesis generation, experiment design and iterative refinement to develop generalizable principles and a report without human intervention. Applied to protein science, Sparks uncovered two previously unknown phenomena: (i) a length-dependent mechanical crossover whereby beta-sheet-biased peptides surpass alpha-helical ones in unfolding force beyond ~80 residues, establishing a new design principle for peptide mechanics; and (ii) a chain-length/secondary-structure stability map revealing unexpectedly robust beta-sheet-rich architectures and a "frustration zone" of high variance in mixed alpha/beta folds. These findings emerged from fully self-directed reasoning cycles that combined generative sequence design, high-accuracy structure prediction and physics-aware property models, with paired generation-and-reflection agents enforcing self-correction and reproducibility. The key result is that Sparks can independently conduct rigorous scientific inquiry and identify previously unknown scientific principles. |
| title | Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles |
| topic | Artificial Intelligence Materials Science Soft Condensed Matter Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2504.19017 |