Non‐supervised Neural Networks: A New Classification Tool to Process Large Databases
Dmitri Kireev, Frédéric Ros, Philippe Bernard, Jacques R. Chrétien, Natalia Rozhkova · 1997
Establishing QSAR in large databases which contain structural and biological information has qualitative differences compared to QSAR studies on compact series of chemical homologues. Indeed, classical QSAR tools often work not so well with databases which count thousands of compounds. The Self-Organising Maps (SOM) suggest a new solution to the problem. A key difference between SOM, also known as Kohonen's neural network, and many other neural networks is that SOM learns without supervision. SOM is a projection technique which reduces the descriptor multidimensional space into a space of any given dimensionality. To adopt the method for QSAR purposes quality estimates for the SOM model evaluation have been developed by the authors. A case study involving SOM is also presented. The processed database contains more titan 2000 organo-phosphorous compounds with various pesticide activities from the STRAC database.