Global-Context Aware Generative Protein Design for Structure-to-sequence Translation

Anonymous

Abstract: The linear sequence of amino acids determines protein structure and function. Protein design, known as the inverse of protein structure prediction, aims to obtain a novel protein sequence that will fold into the defined structure. Recent works on computational protein design have studied designing sequences for the desired backbone structure with local positional information and achieved competitive performance. However, similar local environments in different backbone structures may result in different amino acids, which indicates the global context of protein structure matters. Thus, we propose the Global-Context Aware generative protein design method (GCA), consisting of local and global modules. While local modules focus on relationships between neighbor amino acids, global modules explicitly capture non-local contexts. Experimental results demonstrate that GCA achieves state-of-the-art performance on structure-based protein design. Our code and pretrained model will be released.

Paper Type: short

Research Area: NLP Applications