人工智能蛋白质结构设计算法研究进展
陈志航, 季梦麟, 戚逸飞

Research progress of artificial intelligence in protein design
Zhihang CHEN, Menglin JI, Yifei QI
表1 固定骨架序列设计模型在CATH 4.2测试集上的序列恢复率和困惑度75
Table 1 The sequence recovery rate and perplexity of fixed-backbone sequence design models on CATH 4.2 test set

模型

Models

恢复率%(↑)

Recovery % (↑)

困惑度(↓)

Perplexity (↓)

GraphTrans35.826.63
StructGNN[76]37.16.49
GVP-GNN-large39.206.17
GVP-GNN-Transformer38.306.44
GVP-GNN-Transformer+AF251.604.01
ProteinMPNN45.964.61
ProDesign50.224.69
PiFold[77]50.224.62
LM-DESIGN[75](PiFold)55.654.52