本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2011
摘要
生物 systems contain complex metabolic pathways with many 非線性ities and synergies that make them difficult to predict from first principles. 蛋白質 synthesis is a canonical example of such a pathway. Here we show how cell-free 蛋白質 synthesis may be improved through a series of iterated high-throughput experiments guided by a machine-learning algorithm implementing a form of 演化ary design of experiments (Evo-DoE). The algorithm predicts fruitful experiments from 統計 models of the previous experimental results, combined with 隨機 exploration of the experimental space. The desired experimental response, or 演化ary fitness, was defined as the yield of the target product, and new experimental conditions were discovered to have similar to 350% greater yield than the standard. An analysis of the best experime
※ 此為已發表論文，全文需透過期刊付費取得