Fast Algorithms for Mining Association Rules in Large Databases
VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
| Hi-index | 0.00 |
Protein-protein interactions are critical to many biological processes, extending from the formation of cellular macromolecular structures and enzymatic complexes to the regulation of signal transduction pathways. With the availability of complete genome sequences, several groups have begun large-scale identification and characterization of such interactions, relying mostly on high-throughput two-hybrid systems. We collaborate with one such group, led by Marc Vidal, whose aim is the construction of a protein-protein interaction map for C. elegans. In this paper we first describe WISTdb, a database designed to store the interaction data generated in Marc Vidal's laboratory. We then describe InterDB, a multi-organism prediction-oriented database of protein-protein interactions. We finally discuss our current approaches, based on inductive logic programming and on a data mining technique, for extracting predictive rules from the collected data.