Answers are grounded in this paper and cite their sources.
The primary goal of protein engineering has always been to create molecules with optimal functions and characteristics. One of the most exciting avenues of research in this field is de novo protein design. This approach facilitates the synthesis of entirely new molecules without relying on existing protein, thereby offering a novel method for generating molecular entities that were previously unimaginable. The application of artificial intelligence in this field has been a significant advancement. By leveraging machine learning algorithms trained on extensive sequence and structure datasets, scientists have been able to make de novo protein design a practical reality. In this paper, we will delve into the key artificial intelligence innovations that have driven this progress and explore how they unlock groundbreaking opportunities. These advancements, we believe, have the potential to push beyond the current state of the art, enabling us to design proteins strategically and robustly. Moreover, they offer solutions to pressing societal challenges, such as developing new therapeutics, creating sustainable biomaterials, or engineering enzymes for environmental remediation. • This review summarized the challenges faced in protein design from a biological perspective. • This paper introduced the state-of-the-art de novo protein design techniques from different design perspectives. • It suggested for future improvements in the integration of artificial intelligence with protein design.
No takes yet. Share an insight, caveat, or question.
Yao et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: