Skip to main content

Table 7 Computational efficiency comparison of CLAPE-SMB with other models on the UniProtSMB

From: Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

 

CLAPE-SMB

DeepProSite

GraphBind

P2Rank

GPU

NVIDIA A100-PCIE-40 GB

CPU

Intel(R) Xeon(R) Silver 4210R CPU @ 2.40 GHz

Data preparation time

0.91 s / sequence

2.56 s / sequence

 ~ 4 min / sequence

N/A

Training time

 ~ 15 min / epoch

 ~ 3 min / epoch

 ~ 200 min / epoch

N/A

Inference time

191 sequence / s

51 sequence / s

 ~ 3 s / sequence

 ~ 10 s / sequence