Suppr超能文献

使用Protpardelle-1c进行条件蛋白质结构生成。

Conditional Protein Structure Generation with Protpardelle-1c.

作者信息

Lu Tianyu, Shuai Richard, Kouba Petr, Li Zhaoyang, Chen Yilin, Shirali Akio, Kim Jinho, Huang Po-Ssu

机构信息

Department of Bioengineering, Stanford University.

Department of Biophysics, Stanford University.

出版信息

bioRxiv. 2025 Aug 18:2025.08.18.670959. doi: 10.1101/2025.08.18.670959.

Abstract

We present Protpardelle-1c, a collection of protein structure generative models with robust motif scaffolding and support for multi-chain complex generation under hotspot-conditioning. Enabling sidechain-conditioning to a backbone-only model increased Protpardelle-1c's MotifBench score from 4.97 to 28.16, outperforming RFdiffusion's 21.27. The crop-conditional all-atom model achieved 208 unique solutions on the La-Proteina all-atom motif scaffolding benchmark, on par with La-Proteina while having ~10 times fewer parameters. At 22M parameters, Protpardelle-1c enables rapid sampling, taking 40 minutes to sample all 3000 MotifBench backbones on an NVIDIA A100-80GB, compared to 31 hours for RFdiffusion.

摘要

我们展示了Protpardelle-1c,这是一组蛋白质结构生成模型,具有强大的基序支架功能,并支持在热点条件下生成多链复合物。对仅主干模型启用侧链条件后,Protpardelle-1c的MotifBench分数从4.97提高到28.16,超过了RFdiffusion的21.27。作物条件全原子模型在La-Proteina全原子基序支架基准测试中获得了208个独特的解决方案,与La-Proteina相当,但参数数量减少了约10倍。Protpardelle-1c有2200万个参数,能够快速采样,在NVIDIA A100-80GB上对所有3000个MotifBench主干进行采样需要40分钟,而RFdiffusion则需要31小时。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/60bd/12393353/bd3ed2f360be/nihpp-2025.08.18.670959v1-f0001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验