graphkit-learn/datasets/MUTAG

=== Introduction ===

This folder contains 6 data sets of undirected labeled graphs in Matlab format for graph 
classification: MUTAG, PTC, NCI1, NCI109, ENZYMES, and D&D.

=== Usage ===

For each data set X, the Matlab command
  load X
loads into the memory a struct array containing graphs, and a column vector lx containing 
a class label for each graph.
X(i).am is the adjacency matrix of the i'th graph, 
X(i).al is the adjacency list of the i'th graph, 
X(i).nl.values is a column vector of node labels for the i'th graph,
X(i).el (not always available) contains edge labels for the i'th graph.

Example: 
typing "load MUTAG" in MATLAB
loads a 188 element array of graph structures, called MUTAG, and a column of 188 numbers, 
each of which indicates the class that the corresponding graph belongs to.

=== Description ===

MUTAG (Debnath et al., 1991) is a data set of 188 mutagenic aromatic and heteroaromatic
nitro compounds labeled according to whether or not they have a mutagenic effect on the
Gram-negative bacterium Salmonella typhimurium. 

PTC (Toivonen et al., 2003) contains 344 chemical compounds tested for carcinogenicity
in mice and rats. The classification task is to predict the carcinogenicity of compounds.

NCI1 and NCI109 represent two balanced subsets of data sets of chemical compounds screened 
for activity against non-small cell lung cancer and ovarian cancer cell lines respectively
(Wale and Karypis (2006) and http://pubchem.ncbi.nlm.nih.gov). 

ENZYMES is a data set of protein tertiary structures obtained from (Borgwardt et al., 
2005) consisting of 600 enzymes from the BRENDA enzyme database (Schomburg et al., 2004). 
In this case the task is to correctly assign each enzyme to one of the 6 EC top-level 
classes. 

D&D is a data set of 1178 protein structures (Dobson and Doig, 2003). Each protein is 
represented by a graph, in which the nodes are amino acids and two nodes are connected 
by an edge if they are less than 6 Angstroms apart. The prediction task is to classify 
the protein structures into enzymes and non-enzymes.

=== References ===

K. M. Borgwardt, C. S. Ong, S. Schoenauer, S. V. N. Vishwanathan, A. J. Smola, and H. P. 
Kriegel. Protein function prediction via graph kernels. Bioinformatics, 21(Suppl 1):i47–i56, 
Jun 2005.

A. K. Debnath, R. L. Lopez de Compadre, G. Debnath, A. J. Shusterman, and C. Hansch. 
Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. 
Correlation with molecular orbital energies and hydrophobicity. J Med Chem, 34: 786–797, 
1991.

P. D. Dobson and A. J. Doig. Distinguishing enzyme structures from non-enzymes without 
alignments. J Mol Biol, 330(4):771–783, Jul 2003.

I. Schomburg, A. Chang, C. Ebeling, M. Gremse, C. Heldt, G. Huhn, and D. Schomburg. Brenda, 
the enzyme database: updates and major new developments. Nucleic Acids Research, 32D:431–433, 
2004.

H. Toivonen, A. Srinivasan, R.D. King, S. Kramer, and C. Helma (2003). Statistical 
evaluation of the predictive toxicology challenge 2000-2001. Bioinformatics, 19(10):1183–1193.

N. Wale and G. Karypis. Comparison of descriptor spaces for chemical compound retrieval and 
classification. In Proc. of ICDM, pages 678–689, Hong Kong, 2006.