Untitled

Srinivasan, Ashwin; King, Ross D.

doi:10.1023/a:1009815821645

Cited by 53 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is arguably the most important theoretical area in machine learning [27]. One very successful practical approach to this problem is to apply ILP as a pre-processing step to learn suitable propositional descriptors (attributes), and then to use standard QSAR approaches [7,8]. Recent work has also taken the alternative approach of using statistical procedures as background knowledge [7].…”

Section: Inductive Logic Programmingmentioning

confidence: 99%

“…They generated rules which are easy to understand such as: ''A compound is highly mutagenic if it has an aliphatic carbon atom attached by a single bond to a carbon atom which is in a six-membered aromatic ring''. Much work has been done to improve ILPs ability to solve SAR problems; generation of indicator variables to provide quantitative estimates of the activity [7,8], building pharmacophore models [9,10], dealing naturally with multiple conformations [10], performing structure-based drug design [11] and improvements in algorithms to reduce search space [12,13]. However, no non-trivial improvements have been applied to the original atom/ bond representation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Representation of molecular structure using quantum topology with inductive logic programming in structure–activity relationships

Buttingsrud

Ryeng

King

et al. 2006

J Comput Aided Mol Des

Self Cite

View full text Add to dashboard Cite

The requirement of aligning each individual molecule in a data set severely limits the type of molecules which can be analysed with traditional structure activity relationship (SAR) methods. A method which solves this problem by using relations between objects is inductive logic programming (ILP). Another advantage of this methodology is its ability to include background knowledge as 1st-order logic. However, previous molecular ILP representations have not been effective in describing the electronic structure of molecules. We present a more unified and comprehensive representation based on Richard Bader's quantum topological atoms in molecules (AIM) theory where critical points in the electron density are connected through a network. AIM theory provides a wealth of chemical information about individual atoms and their bond connections enabling a more flexible and chemically relevant representation. To obtain even more relevant rules with higher coverage, we apply manual postprocessing and interpretation of ILP rules. We have tested the usefulness of the new representation in SAR modelling on classifying compounds of low/high mutagenicity and on a set of factor Xa inhibitors of high and low affinity.

show abstract