Emyx model achieves efficient all-atom protein generation

Researchers have developed Emyx, a new conditional flow matching model designed for efficient and accurate all-atom protein generation. This model, with 140 million parameters, utilizes a streamlined architecture that reduces training costs and increases sample diversity compared to existing methods. Emyx outperforms larger models like Proteína-Complexa and RFdiffusion3 on the AME enzyme design benchmark, achieving better success rates in catalytic geometry accuracy and structural novelty while requiring significantly less training time. AI

IMPACT This model could accelerate computational enzyme design by providing a more efficient and effective tool for generating novel protein structures.

RANK_REASON The cluster contains a research paper detailing a new model for protein generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Emyx
• Gotit.pub
• Hugging Face
• IArxiv
• Proteína-Complexa
• RFdiffusion3
• ScienceCast

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →