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

Figure 4.

Functional Scoring and Mutational Fitness Evaluation of ProDualNet (a) A bar graph comparing the effectiveness of the top-k% selection strategy in predicting functional dual-target sequences, showing the proportion of positive sequences identified by the different model. (b) A similarity matrix visualization illustrating the sequence similarity among the dual-target test set for GCGR and GLP-1R, with darker shades indicating higher similarity. (c) A scatter plot comparing ProDualNet dual agonist sequence rank scores (x-axis) with AlphaFold3 rank scores (y-axis). (d) A scatter plot showing the Spearman correlation coefficients for 65 sets of protein mutation data from the ProteinGym Stability database, each set containing multiple mutant sequences per protein. (e) A scatter plot evaluating higher-order mutations across 65 sets of protein mutation data from the ProteinGym Stability database. (f) A box plot summarizing the overall evaluation of 298 sets of protein mutation data from the DMS stability dataset. (g) A scatter plot displaying affinity evaluation for 11 sets of mutant sequences from the SKEMPI V2 database. (h) A scatter plot assessing the relationship between model-predicted scores (x-axis) and true binding free energy (y-axis) across 1877 single-point and 675 multi-point mutations in 11 proteins.

Functional scoring and mutational fitness evaluation of ProDualNet. (a) Comparative analysis of positive dual-target sequences using the top-k% selection strategy to assess the model’s ability to predict functionality. (b) Sequence similarity in the GCGR/GLP-1R dual-target test set. (c) Comparison of ProDualNet dual agonist sequence rank scores with AlphaFold3 rank scores. (d) Overall Spearman correlation coefficient evaluation of 65 sets of protein mutation data in the Proteingym stability database, each set containing multiple mutant sequences for a protein. (e) Higher-order mutation evaluation of 65 sets of protein mutation data in the Proteingym stability database. (f) Overall evaluation of 298 sets of protein mutation data in the DMS stability dataset. (g) Affinity evaluation of 11 sets of mutant sequences in the SKEMPI V2 database. (h) Evaluation of the relationship between model-predicted scores and binding free energy for 1,877 single-point mutations and 675 multi-point mutations across 11 proteins.