0000000000680941
AUTHOR
María José Castro
Prediction and Discrimination of Pharmacological Activity by Using Artificial Neural Networks
The design of new medical drugs is a very complex process in which combinatorial chemistry techniques are used. For this reason, it is very useful to have tools to predict and to discriminate the pharmacological activity of a given molecular compound so that the laboratory experiments can be directed to those molecule groups in which there is a high probability of finding new compounds with the desired properties. This work presents an application of Artificial Neural Networks to the problem of discriminating and predicting pharmacological characteristics of a molecular compound from its topological properties. A large amount of different configurations are tested, yielding very good perfor…
Improving Pattern Recognition Based Pharmacological Drug Selection Through ROC Analysis
The design of new medical drugs is a very complex process in which combinatorial chemistry techniques are used. The goal consists of discriminating between molecular compounds exhibiting or not certain pharmacological activities. Different machine learning approaches have been recently applied to different drug design problems leading to competitive results in pointing at particular compounds with high probability of exhibiting activity. The present work first deeps into the natural trade-off between accuracy in the much less populated active group and false alarm rate which could lead to too many expensive laboratory tests. Preliminary results show how different classification techniques a…