PulseAugur
中
实时 01:32:35
English(EN) HyInv Technical Report

HyInv 模型以提高的精度加速蛋白质序列设计

研究人员开发了 HyInv,一种新的图网络模型,用于逆向蛋白质折叠,可以为给定的蛋白质骨架设计多样化且折叠良好的氨基酸序列。HyInv 使用 Hyra 2.0 研究代理进行训练,并利用分组草稿重写采样器来提高重折叠分数,同时保持序列多样性。与现有方法相比,这种优化实现可以在 NVIDIA H20 GPU 上显著更快地设计序列,并且在多个基准数据集上的性能优于 ProteinMPNN 和 ProteinZero V2 等其他基线。 AI

影响 该模型通过实现更快、更准确的蛋白质序列设计,有可能加速药物发现和蛋白质工程。

排序理由 该项目描述了一个新模型及其在基准数据集上的性能,属于研究类别。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

HyInv 模型以提高的精度加速蛋白质序列设计

本文如何被排名

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目描述了一个新模型及其在基准数据集上的性能,属于研究类别。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    HyInv 技术报告

    Inverse folding designs amino-acid sequences for a given protein backbone, and screening needs many candidates that are both diverse and well folded. We present HyInv, a 1.96-million-parameter backbone-conditioned graph network with an encoder-decoder architecture, trained by Hyr…