Proteina可生成长达800残基的蛋白质骨架，支持结构层次控制。
Proteina: Scaling Flow-based Protein Structure Generative Models
- 基于分层折叠标签的流模型，参数量达此前5倍
- 生成蛋白在分布上与参考集相似度提升，最长可达800残基
- 支持二级结构引导与特定折叠生成，适合蛋白设计研究
近期基于扩散和流的蛋白质结构生成模型已成为从头蛋白设计的强大工具。本文提出Proteina，一种大规模流模型驱动的蛋白质主链生成器，采用分层折叠类别标签进行条件控制，并使用定制化的可扩展变压器架构，参数量达到先前模型的5倍。为有效量化性能，引入一组新指标，直接衡量生成蛋白与参考集之间的分布相似性，补充现有评估方法。我们进一步探索了数百万合成蛋白质结构的训练数据扩展，并改进了适配于蛋白质主链生成的训练与采样方案，包括针对蛋白质主链的LoRA微调策略、无分类器指导和自适应指导等新方法，以及调整后的训练目标。Proteina在从头蛋白质主链设计任务中达到当前最优性能，可生成长度空前（最高800残基）且多样、可设计的蛋白质。分层条件控制提供了新级别的调控能力，支持高层级二级结构引导及低层级折叠特异性生成。
原文摘要 · Abstract (English)
Recently, diffusion- and flow-based generative models of protein structures have emerged as a powerful tool for de novo protein design. Here, we develop Proteina, a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on a tailored scalable transformer architecture with up to 5x as many parameters as previous models. To meaningfully quantify performance, we introduce a new set of metrics that directly measure the distributional similarity of generated proteins with reference sets, complementing existing metrics. We further explore scaling training data to millions of synthetic protein structures and explore improved training and sampling recipes adapted to protein backbone generation. This includes fine-tuning strategies like LoRA for protein backbones, new guidance methods like classifier-free guidance and autoguidance for protein backbones, and new adjusted training objectives. Proteina achieves state-of-the-art performance on de novo protein backbone design and produces diverse and designable proteins at unprecedented length, up to 800 residues. The hierarchical conditioning offers novel control, enabling high-level secondary-structure guidance as well as low-level fold-specific generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。