Molecule mining is the process of data mining, or extracting and discovering patterns, as applied to molecules. Since molecules may be represented by molecular graphs, this is strongly related to graph mining and structured data mining. The main problem is how to represent molecules while discriminating the data instances. One way to do this is chemical similarity metrics, which has a long tradition in the field of cheminformatics.

Typical approaches to calculate chemical similarities use chemical fingerprints, but this loses the underlying information about the molecule topology. Mining the molecular graphs directly avoids this problem. So does the inverse QSAR problem which is preferable for vectorial mappings.

Coding(Moleculei,Moleculej≠i)

Kernel methods Marginalized graph kernelH. Kashima, K. Tsuda, A. Inokuchi, Marginalized Kernels Between Labeled Graphs, The 20th International Conference on Machine Learning (ICML2003), 2003. PDF Optimal assignment kernelH. Fröhlich, J. K. Wegner, A. Zell, Optimal Assignment Kernels For Attributed Molecular Graphs, The 22nd International Conference on Machine Learning (ICML 2005), Omnipress, Madison, WI, USA, 2005, 225-232. PDFH. Fröhlich, J. K. Wegner, A. Zell, Assignment Kernels For Chemical Compounds, International Joint Conference on Neural Networks 2005 (IJCNN'05), 2005, 913-918. CiteSeer Pharmacophore kernel C++ (and R) implementation combining the marginalized graph kernel between labeled graphs extensions of the marginalized kernel Tanimoto kernels graph kernels based on tree patterns kernels based on pharmacophores for 3D structure of molecules

Maximum common graph methods MCS-HSCS (Highest Scoring Common Substructure (HSCS) ranking strategy for single MCS) Small Molecule Subgraph Detector (SMSD)- is a Java-based software library for calculating Maximum Common Subgraph (MCS) between small molecules. This will help us to find similarity/distance between two molecules. MCS is also used for screening drug like compounds by hitting molecules, which share common subgraph (substructure).

Coding(Moleculei)

Molecular query methods WarmrL. Dehaspe, H. Toivonen, King, Finding frequent substructures in chemical compounds, 4th International Conference on Knowledge Discovery and Data Mining, AAAI Press., 1998, 30-36. AGMA. Inokuchi, T. Washio, T. Okada, H. Motoda, Applying the Apriori-based Graph Mining Method to Mutagenesis Data Analysis, Journal of Computer Aided Chemistry, 2001;, 2, 87-92.A. Inokuchi, T. Washio, K. Nishimura, H. Motoda, A Fast Algorithm for Mining Frequent Connected Subgraphs, IBM Research, Tokyo Research Laboratory, 2002. PolyFARMA. Clare, R. D. King, Data mining the yeast genome in a lazy functional language, Practical Aspects of Declarative Languages (PADL2003), 2003. FSG MolFea MoFa/MoSST. Meinl, C. Borgelt, M. R. Berthold, Discriminative Closed Fragment Mining and Perfect Extensions in MoFa, Proceedings of the Second Starting AI Researchers Symposium (STAIRS 2004), 2004.T. Meinl, C. Borgelt, M. R. Berthold, M. Philippsen, Mining Fragments with Fuzzy Chains in Molecular Databases, Second International Workshop on Mining Graphs, Trees and Sequences (MGTS2004), 2004. GastonS. Nijssen, J. N. Kok. Frequent Graph Mining and its Application to Molecular Databases, Proceedings of the 2004 IEEE Conference on Systems, Man & Cybernetics (SMC2004), 2004. LAZARC. Helma, Predictive Toxicology, CRC Press, 2005. ParMolM. Wörlein, Extension and parallelization of a graph-mining-algorithm, Friedrich-Alexander-Universität, 2006. PDF (contains MoFa, FFSM, gSpan, and Gaston) optimized gSpanK. Jahn, S. Kramer, Optimizing gSpan for Molecular Datasets, Proceedings of the Third International Workshop on Mining Graphs, Trees and Sequences (MGTS-2005), 2005.X. Yan, J. Han, gSpan: Graph-Based Substructure Pattern Mining, Proceedings of the 2002 IEEE International Conference on Data Mining (ICDM 2002), IEEE Computer Society, 2002, 721-724. SMIREP DMax SAm/AIm/RHC AFGen gRedA. Gago Alonso, J.E. Medina Pagola, J.A. Carrasco-Ochoa and J.F. Martínez-Trinidad Mining Connected Subgraph Mining Reducing the Number of Candidates, Proc. of ECML--PKDD, pp. 365–376, 2008. G-HashXiaohong Wang, Jun Huan, Aaron Smalter, Gerald Lushington, Application of Kernel Functions for Accurate Similarity Search in Large Chemical Databases , BMC Bioinformatics Vol. 11 (Suppl 3):S8 2010.

Methods based on special architectures of neural networks BPZ ChemNet CCS MolNet Graph machines

See also Molecular Query Language Chemical graph theory Chemical space QSAR ADME partition coefficient

References

Further reading Schölkopf, B., K. Tsuda and J. P. Vert: Kernel Methods in Computational Biology, MIT Press, Cambridge, MA, 2004. R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, John Wiley & Sons, 2001. Gusfield, D., Algorithms on Strings, Trees, and Sequences: Computer Science and Computational Biology, Cambridge University Press, 1997. R. Todeschini, V. Consonni, Handbook of Molecular Descriptors, Wiley-VCH, 2000.

External links Small Molecule Subgraph Detector (SMSD) - is a Java-based software library for calculating Maximum Common Subgraph (MCS) between small molecules. 5th International Workshop on Mining and Learning with Graphs, 2007 Overview for 2006 Molecule mining (basic chemical expert systems) ParMol and master thesis documentation - Java - Open source - Distributed mining - Benchmark algorithm library Technical University of Munich (TUM) - Kramer group Molecule mining (advanced chemical expert systems) DMax Chemistry Assistant - commercial software AFGen - Software for generating fragment-based descriptors