Molence· @MolenceBio · X·· 17 天前AI 评分54
AI 导读
Molence Bio 在 Mol-1-constraint 约束模式下,用文献与单体结构给出的三个残基位点假设,使三个案例的 DockQ 分别从 0.014 升至 0.874、0.011 升至 0.739、0.200 升至 0.863。作者称这些例子说明稀疏的生物学假设可以引导复杂预测。该系列前一条推文称 base model 与 Mol-1-constraint 均可在 https://lab.molence.com 获取,并给出四个基准上 DockQ > 0.23 的成功率变化,如 FoldBench-AB 从 75.0% 升至 88.3%、AF3-AB 从 62.7% 升至 84.2%。
正文 · 原文
15/15 📍 Three residues can provide a useful structural clue.
In three case studies, we supplied three-residue site hypotheses informed by literature and monomer structures.
With Mol-1-constraint, DockQ improved:
• 0.014 → 0.874
• 0.011 → 0.739
• 0.200 → 0.863
These examples show how sparse biological hypotheses can guide complex prediction.
#AIforScience
14/15 📍 An epitope can be an input to prediction. With epitope information, Mol-1-constraint improves antibody–antigen success at DockQ > 0.23 across all four benchmarks: • FoldBench-AB: 75.0% → 88.3% • AF3-AB: 62.7% → 84.2% • PXMeter-AB: 58.3% → 77.5% • MolBench-AB-26: 57.3% → 79.4% Both the base model and Mol-1-constraint are available at https://lab.molence.com #AIforScience在 X 查看被引用的帖子
来源:Molence · x.com