Charaniya Salim, Hu Wei-Shou, Karypis George
Department of Chemical Engineering and Materials Science, University of Minnesota, 421 Washington Avenue SE, Minneapolis, MN 55455-0132, USA.
Trends Biotechnol. 2008 Dec;26(12):690-9. doi: 10.1016/j.tibtech.2008.09.003. Epub 2008 Oct 30.
Modern biotechnology production plants are equipped with sophisticated control, data logging and archiving systems. These data hold a wealth of information that might shed light on the cause of process outcome fluctuations, whether the outcome of concern is productivity or product quality. These data might also provide clues on means to further improve process outcome. Data-driven knowledge discovery approaches can potentially unveil hidden information, predict process outcome, and provide insights on implementing robust processes. Here we describe the steps involved in process data mining with an emphasis on recent advances in data mining methods pertinent to the unique characteristics of biological process data.
现代生物技术生产工厂配备了精密的控制、数据记录和存档系统。这些数据蕴含着丰富的信息，可能有助于揭示过程结果波动的原因，无论关注的结果是生产率还是产品质量。这些数据还可能提供进一步改善过程结果的方法线索。数据驱动的知识发现方法有可能揭示隐藏信息、预测过程结果，并为实施稳健过程提供见解。在此，我们描述了过程数据挖掘所涉及的步骤，重点是与生物过程数据独特特征相关的数据挖掘方法的最新进展。
