基于统计语言模型及动态规划算法的蛋白质表达载体的优化设计

摘要

In order to solve the problem of time consuming and error pronein selecting optimal "brick"to assemble functional protein expression vector,based on statistical language model (SLM),a dynamic program-ming algorithm of protein expression vector was carried out.By collecting the statistical parameters of BioBrick standard parts and transforming the assembling process into SLM,a dynamic programming algorithm could be performed to choose suitable parts to compose the final genetic construction.The result showed this method had high accuracy,redundant operations could be reduced and the time and cost required for conducting bio-logical experiment could be minimized.The method could be not only used to optimize a design in a synthetic biological robotic platform,but also independently used to automate the DNA assembly process in synthetic biology.It could also be iterated and then give out different optimized results for consideration.%针对合成生物学基因片段组装中选择最优“零件”组装功能性蛋白质表达载体费时且易出错的问题，提出一种基于引入统计语言模型（SLM）与动态规划算法的蛋白质表达载体设计方法。该方法通过统计合成生物学标准“零件”（BioBrick）的参数，将基础“零件”组装过程转化为 SLM，用动态规划算法找到最优路径，以实现蛋白质表达载体的设计。实验结果证明该方法准确率高，可以减少真实装配过程的冗余操作，节省时间和费用，可用来优化其他合成生物学软件设计结果，也可独立使用来模拟装配合成生物学基因片段产生蛋白质表达载体，还可被迭代从而给出不同的优化结果供选择。