CORRELATION BETWEEN STRUCTURE AND NORMAL BOILING POINTS OF HALOALKANES C-1-C-4 USING NEURAL NETWORKS

Authors
BALABAN AT BASAK SC COLBURN T GRUNWALD GD
Citation
At. Balaban et al., CORRELATION BETWEEN STRUCTURE AND NORMAL BOILING POINTS OF HALOALKANES C-1-C-4 USING NEURAL NETWORKS, Journal of chemical information and computer sciences, 34(5), 1994, pp. 1118-1121
Citations number
32
Categorie Soggetti
Information Science & Library Science","Computer Application, Chemistry & Engineering","Computer Science Interdisciplinary Applications",Chemistry,"Computer Science Information Systems
Journal title
Journal of chemical information and computer sciences → ACNP
ISSN journal
00952338
Volume
34
Issue
5
Year of publication
1994
Pages
1118 - 1121
Database
ISI
SICI code
0095-2338(1994)34:5<1118:CBSANB>2.0.ZU;2-5
Abstract
By using neural networks, correlations were established between chemic al structure and boiling points of chlorofluorocarbons with 1, 1-2, or 1-4 carbon atoms (15, 62, and 276 compounds, respectively) as well as of halomethanes with up to four different halogens (48 compounds). Th e molecular descriptors included the number of carbon atoms and of eac h type of halogen atom as well as topological indices. Results were va lidated by the jackknifing procedure. The correlation coefficients wer e r = 0.985-0.995. Predictions were made for the boiling points of sev eral haloethanes.