In recent decades, biomedical researchers are facing a new challenge that grows exponentially. The challenge is how to handle the large volume of biological data automatically generated by various whole-cell study methods such as genomics, microarrays, and proteomics. These new methods provide enormous opportunities for rapid advances in biomedical research and medicine because they allow scientists to study living beings in a global scale with greater speed. However, analyzing the data generated by these new methods can be a daunting task and often requires the development of specialized data extraction and conversion computer programs. Because only a few scientists are well trained both in life sciences and computer science, there exists a bottleneck between the great research opportunities these volume data can provide us, and the actual advances scientists can achieve from using them. In this project, we propose to develop an auto-programming tool for biomedical scientists to help them handle the large amount of data in their research. This tool will observe the visual extraction and conversion of sample data by users via a graphical user interlace, i.e., through the point, click and drag operations familiar to most computer users. After that, it will be able to automatically generate computer programs that can carry out the same data extraction and conversion tasks for its users, on any new data. That is to say, by seeing a few examples of a user's data extraction and conversion needs, this tool can automatically turn that into computer solutions. Using this tool will be easy and will not require any sophisticated computer science training because it does the programming job for its users automatically. This tool can have the broadest applicability in all biomedical research areas where textual format data are generated and processed with computational technologies. Therefore, this tool will provide great enabling power to biomedical scientists to help them make rapid advances in biomedical research and medicine.
This project is supported by theMay 25, 2007nstitutes of Health Grant 4R33GM066400.
|