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

Figure 1.

Model Framework, Fusion Strategy Framework, and Evaluation Framework (a) A schematic representation illustrating the ProDualNet pretraining process, which utilizes a standard training strategy. The diagram shows the flow of data and the key components involved in the pretraining phase. (b) An illustration of the ProDualNet fine-tuning process for dual-target tasks. This subfigure features a shared encoder–decoder structure and highlights the recycling strategy based on the protein language model ESM2. (c) An overview of various dual-target modeling strategies. This part visually compares different approaches, showcasing their unique characteristics. (d) A subfigure is shown of three distinct test sets, each based on different criteria.

Model framework, fusion strategy framework, and evaluation framework. (a) Schematic representation of ProDualNet pretraining using a standard training strategy. (b) ProDualNet fine-tuning for dual-target tasks, employing a shared encoder–decoder structure and the protein language model ESM2-based recycling strategy. (c) Overview of different dual-target modeling strategies. (d) Three test sets based on different evaluation criteria.