Several real-life datasets can be downloaded from this page. All the datasets are available in the format for command-line TreeLiker (download here) and in the form of TreeLiker-GUI project-directories (download here).
The available datasets are the following.
- Predictive Toxicology Challenege datasets (www.predictive-toxicology.org/ptc/) which contain description of small molecules together with the information whether they are toxic for female mice, male mice, female rats and male rats.
- Mutagenesis dataset (H. Lodhi and S. Muggleton. Is mutagenesis still challenging. In International Conference on Inductive Logic Programming, Late-Breaking Papers, 2005.) which contains small molecules marked by their mutagenicity.
- Peptides dataset (Cherkasov, A., Jankovic, B. Application of Inductive QSAR Descriptors for Quantification of Antibacterial Activity of Cationic Polypeptides. Molecules 2004, 9, 1034-1052.) which contains descriptions of spatial structures of antimicrobial peptides divided into classes according to their antimicrobial activity.