The ability to generate proteins with desired functions is a central goal of computational biology.
Although natural language can express diverse design objectives, existing protein generation methods often support only narrow tasks or make limited use of biological constraints.
InstructPro2: A New Approach
We develop InstructPro2 to translate natural-language design objectives into protein sequences while incorporating task-specific biological context.
A text encoder captures the design instructions, while dedicated ligand and antigen encoders provide biological context to the sequence-generating decoder.
Pretraining and Adaptation
For pretraining, we assemble InstructPro2Bench, comprising 205.7 million
We subsequently adapt the model to ligand-binding protein and antibody design.
Performance on Functional Protein Generation Benchmarks
On functional protein generation benchmarks, InstructPro2 outperforms Pinal, the strongest baseline, achieving a functional recovery F1 of 74.8 versus 62.2 and lowering global RMSD from 5.33A to 3.04A.
Performance on Antibody Design
For antibody design, the model obtains a DockQ score of 0.39.
Performance on Ligand-binding Protein Design
Ligand-binding protein design reaches a docking success rate of 72.6%.
Significance of the Findings
These findings highlight how integrating language-based instructions with biological conditioning can extend protein generation to distinct design settings.