A logic-reasoning based system to harness bioprocess experimental data and knowledge for design

Bioprocess design requires substantial resources during the experimental investigation of the options for each bioprocess step. This is both time-consuming and expensive. The amount of data available has increased exponentially since the expansion of new biological drug development. Data are heterogeneous, sometimes inconsistent and incomplete, making them difficult to be systematically utilised for analysis for any new bioprocess design. In this paper, we report a novel computational method that harnesses the bioprocess experimental data to assist design decision making, and perhaps identify further needed experiments. First, we develop a new data representation structure to capture the experimental data systematically. Then the ontology for modelling the relationship of data properties is created. A computational system has been developed to search relevant data, or to predict required process conditions, or to suggest a new set of experiments for process development. A prototype for harnessing centrifugation experimental data has been built, and is then used to illustrate the method and demonstrate the type of results that can be obtained. Evaluations show that such a system has significant potential to mine the relevant experimental data to assist new drug bioprocess development, which should reduce process development time and cost.

► Developed a new data representation structure to capture the experimental data systematically. ► Created ontology for modelling the relationship of data properties. ► Established a computational system to search relevant data based to predict required process conditions and to suggest a new set of experiments for process development. ► Demonstrated centrifugation data and knowledge system and its evaluation.