Skip to main content


Open-source compound mining framework ChemmineR

Research Achievements

Open-source compound mining framework ChemmineR

ChemmineR is the first open-source compound mining framework for the popular statistical programming environment R ( This tool was developed as a new component of the ChemMine ( With guidance from computer scientists and biologists, associates Cao and Charisi developed this program suite with functions for structural similarity searching and clustering of compound libraries with a wide spectrum of algorithms and utilities for managing complex compound datasets. The package offers visualization functions for compound clusters and sub-structures. Its integration with ChemMine allows bidirectional communications between the two services. ChemmineR also provides easy access to useful statistical methods, machine learning algorithms and graphic utilities. Workshops are regularly held on use of these tools, which are actively used by IGERT fellows and internationally. ChemMine pages received ~60,000 hits in 2008.