New evolutions in two-dimensional electrophoresis in the century of AI and open innovation.

By developing the equipment and constructing sample-specific pretreatment methods, we have developed a two-dimensional electrophoresis (2DE) method for the social implementation with (1) high-throughput, (2) high sensitivity, and (3) high reproducibility performance. Furthermore, by taking advantage of the fact that the data obtained by 2DE are images that are compatible with machine learning and the high-throughput performance of the previously developed method, we have succeeded in AI-aided proteomic disease diagnosis using 2DE images of sepsis patient sera. In machine learning, the accuracy and quality (the types of things that can be discriminated) improve as the amount of data increases, and since the 2DE system can in principle be miniaturized, and the practical application of the system can foster big data, it is expected that proteomics will be implemented in society using general-purpose 2DE in the near future. This paper introduces the results of the authors' research and development to date and discusses new developments in 2DE driven by open innovation accelerated by AI. [ABSTRACT FROM AUTHOR]