A Collaborative Multiagent System for Mining Transcriptional Regulatory Elements
暂无分享,去创建一个
Identification of transcriptional regulatory elements offers a key means of insight into regulation mechanisms. However, the number of known regulatory elements is inadequate and state-of-the-art identification methods are inaccurate. Moreover, it is difficult for a biologist to select interdependent tools, and existing systems ignore overall performance issues. Agent technology can provide solutions through its information integration and coordination capabilities. TREMAgent is the first multiagent-based system for mining transcriptional regulatory elements. It uses novel algorithms combined with biological domain knowledge (for example, protein functional site information) to achieve superior accuracy and collaborate with existing tools using agent technology. The autonomous problem-solving capability of agents enables the system to provide the appropriate workflow rather than having users select interdependent tools. Experiments on the real data sets show that TREMAgent can provide superior accuracy and flexible services, promising excellent potential for bioinformatics.
[1] Michael Luck,et al. Agents in bioinformatics, computational and systems biology , 2006, Briefings Bioinform..
[2] William Stafford Noble,et al. Assessing computational tools for the discovery of transcription factor binding sites , 2005, Nature Biotechnology.
[3] Yu-Dong Cai,et al. Automatic transcription factor classifier based on functional domain composition. , 2006, Biochemical and biophysical research communications.