Search

Recent rapid progress in big data and breakthrough AI technologies have brought about significant changes in the medical field as well. Although biomedical literature databases contain so many articles that it is impossible to read them all, AI technology based on neural networks has dramatically advanced and is now able to efficiently process such vast amounts of literature information in a short time. Since drug discovery research requires up-to-date and extensive knowledge of various disciplines, it is necessary to proactively incorporate AI technology to seamlessly obtain the information needed. In this article, we introduce our effort to use the rapidly growing literature data and the latest AI technologies to drug discovery research. Conventional search engines take an enormous amount of time to identify and understand sentences describing the subject matter of interest in the retrieved articles. We developed and validated our new search tool that not only has a conventional keyword search function, but also enables conceptual search for disease mechanisms using sentences. We will also describe problems that we have identified through actual use of the tool. Finally, since literature data is expected to increase and efforts to determine how to efficiently analyze and obtain desired findings using AI will become even more active, we will discuss expectations for future technological advances and issues that need to be resolved.

The ever-increasing rate of drug discovery data has complicated data analysis and potentially compromised data quality due to factors such as data handling errors. Parallel to this concern is the rise in blatant scientific misconduct. Combined, these problems highlight the importance of developing a method that can be used to systematically assess data quality. Benford's law has been used to discover data manipulation and data fabrication in various fields. In the authors' previous studies, it was demonstrated that the distribution of the corresponding activity and solubility data followed Benford's law distribution. It was also shown that too intense a selection of training data sets of regression model can disrupt Benford's law. Here, the authors present the application of Benford's law to a wider range of drug discovery data such as microarray and sequence data. They also suggest that Benford's law could also be applied to model building and reliability for structure-activity relationship study. Finally, the authors propose a protocol based on Benford's law which will provide researchers with an efficient method for data quality assessment. However, multifaceted quality control such as combinatorial use with data visualization may also be needed to further improve its reliability.