https://fupcode.com/blog/categories/%E7%A7%91%E7%A0%94%E7%AC%94%E8%AE%B0/南冥鹏影Hugo 0.168.0 & FixIt v1.0.0-beta.4zh-CNThu, 17 Sep 2026 17:00:00 +0800https://fupcode.com/blog/posts/research-notes/paper-review-redial/Thu, 17 Sep 2026 17:00:00 +0800https://fupcode.com/blog/posts/research-notes/paper-review-redial/科研笔记通过单点突变观察 embedding 的变化，直接提取 RNA 语言模型中的结构耦合信号，并用逐层分析和消融检验模型冗余。https://fupcode.com/blog/posts/research-notes/paper-review-trrna2/Thu, 30 Apr 2026 17:05:46 +0800https://fupcode.com/blog/posts/research-notes/paper-review-trrna2/科研笔记<p>trRosettaRNA2 利用二级结构 (SS) 做了两件很有意思的工作</p> <ol> <li>让SS加权于attention</li> <li>通过多 SS 条件输入实现 RNA 构象分布</li> </ol> <h2 class="heading-element" id="ss加权于attention"><span>SS加权于attention</span> <a href="#ss%e5%8a%a0%e6%9d%83%e4%ba%8eattention" class="heading-mark"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z"></path></svg></a> </h2><p><img loading="lazy" src='https://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs42256-026-01223-x/MediaObjects/42256_2026_1223_Fig1_HTML.png?as=webp' alt="ss"></p>https://fupcode.com/blog/posts/research-notes/paper-review-rhofold/Sat, 15 Nov 2025 17:07:04 +0800https://fupcode.com/blog/posts/research-notes/paper-review-rhofold/科研笔记<h2 class="heading-element" id="模型架构"><span>模型架构</span> <a href="#%e6%a8%a1%e5%9e%8b%e6%9e%b6%e6%9e%84" class="heading-mark"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z"></path></svg></a> </h2><p>RhoFold+是一个全可微分的端到端框架，从RNA序列输入直接输出全原子3D结构。架构分为几个关键模块：</p>