The famous mutagenity data set of 230 compounds [1] encoded by topological descriptors [2] was processed by GUHA method.
Basic ideas of GUHA (General Unary Hypotheses Automaton) method were given in [3] already in 1966. The aim of GUHA method is to generate hypotheses on relations among properties of the objects which are in some sense interesting.
The hypothesis is generally composed of two parts: antecedent (A) and succedent (S). Antecedent and succedent are tied together by so called generalized quantifier, which describes the relation between them. Given antecedent and succedent, frequencies of four possible combinations can be computed and expressed in compressed form as so called four-fold table (ff-table):
Keywords
- Nitro Compound
- Generalize Quantifier
- Topological Index
- Topological Descriptor
- Molecular Orbital Energy
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.