The article "Sparks of Function by De novo Protein Design" by Alexander E. Chu, Tianyu Lu, and Po-Ssu Huang, published in *Nature Biotechnology*, reviews the advancements in de novo protein design, which aims to create new proteins from scratch based on specified functions. The authors highlight the central dogma of protein design, which involves mapping functional goals to structural motifs, designing protein structures, and sampling sequences to achieve the desired function. Recent advances in deep learning have enabled more efficient and accurate structure modeling and design, leading to the creation of functional proteins. The review discusses the application of machine learning to extract functional motifs from natural proteins and design them from scratch. It also explores the use of generative models and deep learning to design protein structures and sequences, emphasizing the importance of sequence and structure co-design. The authors conclude by discussing the challenges and future directions in protein design, including the need for biophysical understanding and the exploration of dynamic protein structures.The article "Sparks of Function by De novo Protein Design" by Alexander E. Chu, Tianyu Lu, and Po-Ssu Huang, published in *Nature Biotechnology*, reviews the advancements in de novo protein design, which aims to create new proteins from scratch based on specified functions. The authors highlight the central dogma of protein design, which involves mapping functional goals to structural motifs, designing protein structures, and sampling sequences to achieve the desired function. Recent advances in deep learning have enabled more efficient and accurate structure modeling and design, leading to the creation of functional proteins. The review discusses the application of machine learning to extract functional motifs from natural proteins and design them from scratch. It also explores the use of generative models and deep learning to design protein structures and sequences, emphasizing the importance of sequence and structure co-design. The authors conclude by discussing the challenges and future directions in protein design, including the need for biophysical understanding and the exploration of dynamic protein structures.