Prediction of Molecular Properties by Recursive Neural Networks - Application to the glass transition temperature of acrylic polymers

In the past few years, a novel approach in cheminformatics for the Quantitative Structure-Property Relationship (QSPR) analysis of physical, chemical and biological properties of chemical compounds was developed at the University of Pisa. This methodology is based on the direct treatment of molecular structure, without using numerical descriptors, and employs recursive neural networks. In subsequent studies it was successfully used to predict various properties of different classes of compounds. It is a promising tool in the evaluation of existing substances, as well as in the design of new materials. This master thesis focuses on the prediction of the properties of polymers, a problem not easily treatable with traditional methods based on molecular descriptors. The study explores different representational issues and show the accuracy and flexibility of the structure-based QSPR approach.

About the author

Carlo Giuseppe Bertinetto was born on 7-12-1981 in Torino, Italy. In October 2006 he graduated cum laude in chemistry at the University of Pisa. He is currently a PhD student in chemical sciences at the Univesity of Pisa and his main interests are QSAR models and predictive methods in general.

Product details

• Authors: Carlo Giusepp Bertinetto, Carlo Giuseppe Bertinetto, Celi Duce, Celia Duce, Rob Solaro, Roberto Solaro
• Publisher: VDM Verlag Dr. Müller
• Languages: English
• Product format: Paperback / Softback
• Released: 02.02.2010
• EAN: 9783639162097
• ISBN: 978-3-639-16209-7
• No. of pages: 116
• Dimensions: 150 mm x 7 mm x 220 mm
• Weight: 191 g
• Subjects: Natural sciences, medicine, IT, technology > Chemistry; Non-fiction book > Nature, technology > Natural science