An investigation of clustering as a tool in Quantitative Structure Activity Relationships (QSARs)
The aim of the research presented was to evaluate systematically the EINECS (European Inventory of Existing Commercial Substances) database and to unravel some latent structure in the EINECS data. The database was split into small manageable groups of chemicals with similar composition and properties, which were then used for property prediction or testing. QSARs were employed as a standard means of testing the properties. The resulting models of each group were compared and the optimal level on which the models were most robust was detected.
Bibliographic Reference: Paper presented: 6th Workshop QSAR 94 - Quantitative Structure Activity Relationships in Environmental Science, Belgirate (NO), September 13-17, 1994
Availability: Available from (1) as Paper EN 38610 ORA
Record Number: 199411178 / Last updated on: 1994-11-25
Original language: en
Available languages: en