Boosting AND/OR-based computational protein design: dynamic heuristics and generalizable UFO
Boosting AND/OR-based computational protein design: dynamic heuristics and generalizable UFO
复制标题
DOI：
10.48550/arxiv.2309.00408
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
B. Pezeshki;Radu Marinescu;A. Ihler;R. Dechter
中科院分区：
文献类型：
--
作者：
B. Pezeshki;Radu Marinescu;A. Ihler;R. Dechter
科学计算经历了一场由神经网络等技术进步所带来的激增。然而，某些重要的任务不太适合这些技术，受益于传统推理方案的创新。其中一项任务是蛋白质的重新设计。最近，一种新的重新设计算法AOBB-K* 被引入，并且在小蛋白质重新设计问题上与最先进的BBK* 竞争。然而，AOBB-K* 没有很好地扩展。在这项工作中，我们专注于扩展AOBB-K*，并引入三个新版本：AOBB-K*-B（增强），AOBB-K*-DH（动态编译）和AOBB-K*-UFO（下溢优化），显着增强可扩展性。
Scientific computing has experienced a surge empowered by advancements in technologies such as neural networks. However, certain important tasks are less amenable to these technologies, benefiting from innovations to traditional inference schemes. One such task is protein re-design. Recently a new re-design algorithm, AOBB-K*, was introduced and was competitive with state-of-the-art BBK* on small protein re-design problems. However, AOBB-K* did not scale well. In this work we focus on scaling up AOBB-K* and introduce three new versions: AOBB-K*-b (boosted), AOBB-K*-DH (with dynamic heuristics), and AOBB-K*-UFO (with underflow optimization) that significantly enhance scalability.