Computational structure-activity study directs synthesis of novel antitumor enkephalin analogs - QSAR dataset

2014-12-26T12:43:26Z (GMT) by Fran Supek Matija Gredičak

This dataset accompanies the publication "Computational structure–activity study directs synthesis of novel antitumor enkephalin analogs" by Gredičak, Supek et al. (2010) Amino Acids. doi:10.1007/s00726-009-0329-5

The training data includes 22 chemical compounds (peptides) with measured in vitro biological activity against seven cancer cell lines.
In addition, 8 candidates were chosen based on QSAR modelling, synthesized and tested for activity against a subset of the tumor cell cultures.

In total, this yields 30 compounds with known in vitro antiproliferative activity on human cancer cells.

The unlabeled data is a virtual library of 429 compounds, for which biological activity was predicted using Support Vector Regression.

All compounds are peptides similar to enkephalin or fragements thereof, and often include unnatural, adamantane-containing amino acids.
The 1666 descriptors were computed using the E-Dragon online service.