Editing Quantitative structure–activity relationship (section)

=== Data mining approach ===

Computer SAR models typically calculate a relatively large number of features. Because those lack structural interpretation ability, the preprocessing steps face a [[feature selection]] problem (i.e., which structural features should be interpreted to determine the structure-activity relationship). Feature selection can be accomplished by visual inspection (qualitative selection by a human); by data mining; or by molecule mining.

A typical [[data mining]] based prediction uses e.g. [[support vector machine]]s, [[decision tree]]s, [[artificial neural network]]s for [[inductive reasoning|inducing]] a predictive learning model.

[[Molecule mining]] approaches, a special case of [[structured data mining]] approaches, apply a similarity matrix based prediction or an automatic fragmentation scheme into molecular substructures. Furthermore, there exist also approaches using [[Maximum common subgraph isomorphism problem|maximum common subgraph]] searches or [[graph kernel]]s.<ref name="isbn0-521-58519-8">{{cite book | vauthors = Gusfield D | title = Algorithms on strings, trees, and sequences: computer science and computational biology | publisher = Cambridge University Press | location = Cambridge, UK | year = 1997 | isbn = 978-0-521-58519-4 }}</ref><ref name="isbn0-8247-2397-X">{{cite book | vauthors = Helma C | title = Predictive toxicology | publisher = Taylor & Francis | location = Washington, DC | year = 2005  | isbn = 978-0-8247-2397-2 }}</ref>

[[File:QSAR-protocol.jpg|thumb|500px|right|QSAR protocol]]