Progressive Multi-Modality Learning for Inverse Protein Folding
This work addresses the data scarcity bottleneck in protein design for computational biology, offering an incremental improvement through a novel multi-modality approach.
The authors tackled the problem of limited generalization in inverse protein folding due to scarce structure-sequence data by proposing MMDesign, a multi-modality transfer learning framework that combines pretrained structural and contextual modules, achieving consistent outperformance over baselines on public benchmarks with only a small training dataset.
While deep generative models show promise for learning inverse protein folding directly from data, the lack of publicly available structure-sequence pairings limits their generalization. Previous improvements and data augmentation efforts to overcome this bottleneck have been insufficient. To further address this challenge, we propose a novel protein design paradigm called MMDesign, which leverages multi-modality transfer learning. To our knowledge, MMDesign is the first framework that combines a pretrained structural module with a pretrained contextual module, using an auto-encoder (AE) based language model to incorporate prior protein semantic knowledge. Experimental results, only training with the small dataset, demonstrate that MMDesign consistently outperforms baselines on various public benchmarks. To further assess the biological plausibility, we present systematic quantitative analysis techniques that provide interpretability and reveal more about the laws of protein design.