Abstract | ||
---|---|---|
As genomic and proteomic data is collected from high- throughput methods on a daily basis, subcellular com- ponents are identified and their in vitro behavior is char- acterized. However, much less is known of their in vivo activity because of the complex subcellular milieu they operate within. A component's milieu is determined by the biological pathways it participates in, and hence, the mechanisms by which it is regulated. We believe AI planning technology provides a modeling formalism for the task of biological pathway discovery, such that hypothetical pathways can be generated, queried and qualitatively simulated. The task of signal transduction pathway discovery is re-cast as a planning problem, one in which the initial and final states are known and cellu- lar processes captured as abstract operators that mod- ify the cellular environment. Thus, a valid plan that transforms the initial state into a goal state is a hypo- thetical pathway that prescribes the order of signaling events that must occur to effect the goal state. The plan- ner is driven by data that is stored within a knowledge base and retrieved from heterogeneous sources (includ- ing gene expression, protein-protein interaction and lit- erature mining) by a multi-agent information gathering system. We demonstrate the combined technology by translating the well-known EGF pathway into the plan- ning formalism and deploying the Fast-Forward planner to reconstruct the pathway directly from the knowledge base. |
Year | Venue | Keywords |
---|---|---|
2003 | ICAPS | planning and scheduling with complex domain models,applications of planning and scheduling,signal transduction pathway,gene expression,high throughput,multi agent system,domain model,protein protein interaction,ai planning,knowledge base |
Field | DocType | Citations |
Computer science,Multi-agent system,Artificial intelligence,Computational biology,Formalism (philosophy),Knowledge base,Machine learning,Automated planning and scheduling,Biological pathway | Conference | 12 |
PageRank | References | Authors |
0.69 | 13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Salim Khan | 1 | 99 | 6.80 |
William Gillis | 2 | 27 | 1.60 |
Carl Schmidt | 3 | 16 | 1.18 |
Keith Decker | 4 | 1610 | 206.60 |