蛋白質在生物體內扮演著極其重要的角色，從訊號傳遞到基因表達調控都都有參與。蛋白質的形狀與其功能亦息息相關，因此，我們需要好好了解蛋白質序列和結構之間的關係，以提高我們預測和設計蛋白質功能的能力。自從AlphaFold在2021年問世以來，利用豐富的蛋白質數據庫（PDB）等序列-結構資料，許多深度學習技術已經大幅提升了我們處理複雜蛋白質功能的能力。例如設計蛋白質結合劑、增強蛋白質穩定性和設計新型酶。在BTBA這個seminar上，Andy和Joshua會講解深度學習如何促進蛋白質設計的基本概念，並提供一些具體的生物技術案例，幫助解答生物問題。是個非常難得深入淺出蛋白質結構以及AlphaFold使用的機會唷!
Proteins are indispensable in nearly all biological processes, including signaling transduction and gene expression regulation. The structure a protein adopts is closely linked to its function, underscoring the need for a comprehensive mapping of the high-dimensional protein sequence-structure relationship. This would significantly enhance our ability to predict and design protein functions. In 2021, AlphaFold was launched, and since then, numerous deep learning techniques leveraging rich sequence-structure databases like Protein Data Bank (PDB) have remarkably improved our capacity to tackle complex protein function tasks. These include protein binder design, protein stability enhancement, and de novo enzyme design. During this seminar, Andy and Joshua will provide an introduction to the fundamental concepts of how deep learning facilitates protein design, and present practical examples of its use in biotechnology and addressing biological questions.