- GW Home
- About GW
- University Life
- News & Events
- Faculty And Staff
Early Detection of Complex Diseases: Software Finds Hidden Signals in Time Series DataTechnology #014-049-zeng
Questions about this technology? Ask a Technology Manager
- Image Gallery
- Chen Zeng Department of Physics
- Chenghang Du Department of Physics
- Managed By
- Brian Coblitz Sr. Licensing Associate firstname.lastname@example.org (202) 994-4345
- Patent Protection
System and Method for Predicting Transformative Events in Multivariable SystemsUS Patent Pending 2016-0283442
GW researchers developed software to identify early signals of critical transition events using time series microarray data. The tools can be applied to identify tell-tale signs of disease onset that otherwise would seem insignificant.
For diseases with acute onset of symptoms, early detection and timely intervention may be necessary for favorable clinical outcomes. Time series microarray is a powerful technology that reveals changes in gene expression profile over time and holds much potential as a diagnostic tool.
The software analyzes large time series microarray data sets to identify groups of key genes (‘nucleation sites’) whose collective temporal expression patterns precede onset of a disease. While the individual genes of the nucleation sites are weak signals on their own, as a group, they can be a powerful predictor of the onset of a disease. Additionally, unlike most traditional time series algorithms, the present invention can be applied to longer term processes and among large number of variables.
Using the software, the researchers were able to identify ‘nucleation sites’ in disease models by analyzing a publicly available time series microarray data. In addition, the researchers successfully validated the predictive power of the software for influenza in healthy human volunteers (See Figure).
The principle behind this invention can also be used to predict complex and sudden events from large data set in other contexts, such as in the field of economics.
Prediction of onset and progress of complex diseases based on time series microarray data.
Other contexts where time series data sets are available, and major event prediction is important (e.g. internet social media, internet, economics.)
Higher predictive power from clustering of weak signals.
Can be used for longer time frames than traditional time series software.
Can be used for broader range of variables than traditional time series software.