The molecular feature miner MolFea
Year: 2003
Type: book-chapter
Abstract: Inductive databases are a new generation of databases, that are capable of dealing with data but also with patterns or regularities within the data. A user can generate, manipulate and search for patterns of interest using an inductive query language. Data mining then becomes an interactive querying process. The inductive database framework is especially interesting for bio- and chemoinformatics, because of the large and complex databases that exist in these domains, and the lack of methods to gain scientific knowledge from them. In this article we present an example for inductive databases: Molfea is the Molecular Feature Miner that mines for linear fragments in the 2D-structure of chemical compounds. In the methodological part we will explain the inner working of the Molfea algorithm, using a simple example. In the second part we will present applications to the NCI DTP AIDS Antiviral Screen database and several benchmark Structure-Activity Relationship problems in toxicology.
Source: Lirias
Authors: Christoph Helma, Stefan Krämer, Luc De Raedt
Institution: University of Freiburg
Language: English
Subfield: Drug Discovery
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W96200431
