Clustering files of chemical structures using the Székely–Rizzo generalization of Ward's method

摘要: Ward's method is extensively used for clustering chemical structures represented by 2D fingerprints. This paper compares Ward clusterings of 14 datasets (containing between 278 and 4332 molecules) with those obtained using the Szekely–Rizzo method, a generalization method. The clusters resulting from these two methods were evaluated extent to which various classifications able group active molecules together, novel criterion effectiveness. Analysis total 1400 (Ward methods, different datasets, 5 fingerprints 10 distance coefficients) demonstrated general superiority coefficient first described Soergel performed extremely well in experiments, this was also case when it simulated virtual screening experiments.