An automated ILP server in the eld

The identiication of evolutionary related (homologous) proteins , is a key problem in molecular biology. Here we present a inductive logic programming based method, Homology Induction (HI), which acts as a lter for existing sequence similarity searches to improve their performance in the detection of remote protein homologies. HI performs a PSI-BLAST search to generate positive, negative, and uncertain examples , and collects descriptions of these examples. It then learns rules to discriminate the positive and negative examples. The rules are used to lter the uncertain examples in the "twilight zone". HI uses a multi-table database of 51,430,710 prefabricated facts from a variety of biological sources, and the inductive logic programming system Aleph to induce rules. Hi was tested on an independent set of protein sequences with equal or less than 40 per cent sequence similarity (PDB40D). ROC analysis is performed showing that HI can signiicantly improve existing similarity searches. The method is automated and can be used via a web/mail interface.