Praluent和Repatha的专利检索与数据挖掘

The patent search and data mining of Praluent and Repatha

针对重磅炸弹级新药Praluent和Repatha,通过多库联检,采集了两药的全部专利数据;利用Java编程结合Excel进行数据清洗,使用SQL建立了两药的专利数据库。利用多项式回归分析,拟合了专利申请趋势线并预测专利增长趋势;结合药物专利一般生长规律,给出Praluent和Repatha专利布局网络;同时,通过聚类分析,给出Repatha在美国的专利语义网络并绘制了专利地图。最后,通过多维统计分析绘制了多张图表,进一步解读Praluent和Repatha的专利布局现状与趋势。研究结果为枯草溶菌素转化酶9(PCSK9)抑制剂其他系列药物和后期仿制药的研发提供了珍贵的医药竞争情报。

Firstly,this paper collected all the patent data of the blockbuster new drugs Praluent and Repatha by using multiple database search. After cleansing,I established a database by SQL. Using the database,polynomial regression analysis,trended line fitted patent application,given Praluent/Repatha patent status of the network layout. Meanwhile,through data mining clustering analysis,set Praluent for the training set,built a patent map in the United States on Repatha. Finally,the paper carried out the dimension combination,drew lots of patent graphs of two drugs through statistical analysis,and further interpretation of the status and trends of Praluent and Repatha＇s patent layout. The results of the study provided precious information for other inhibitors drugs and generic imitation planning and development process regulation.