Skip to main content
. 2025 Aug 26;26(4):bbaf391. doi: 10.1093/bib/bbaf391

Figure 2.

Evaluation results on different design tasks (a) A bar graph illustrating the overall recovery rates on Test Set 1, showing performance metrics across different methods. (b) A bar graph presenting the evaluation results on Test Set 2. (c) A bar graph displaying the evaluation results on Test Set 3. (d) Three bar graphs summarizing the AlphaFold3 results for the designed sequences on Test Set 1, including key metrics such as pLDDT, PAE, and IPTM. (e) Four scatter plots illustrate AlphaFold2 scores (PAE, pLDDT, and iPTM) and TM-scores for three models: ProteinMPNN_b, ProteinMPNN_mean, and ProDualNet across 38 design cases in Test Set 3, highlighting performance differences in various cases.

Evaluation results in different design tasks. (a) Global recovery on Test Set 1. (b) Evaluation results on Test Set 2, featuring conformational changes. (c) Evaluation results on Test Set 3, with varying interface combinations. (d) AlphaFold3 results for the designed sequence on Test Set 1. (e) Comparison of AlphaFold2 scores (PAE, pLDDT, iPTM, and TM-score) between ProteinMPNN_b, ProteinMPNN_mean, and ProDualNet across 38 design cases in Test Set 3.