Ck. Liang et Da. Gallagher, QSPR PREDICTION OF VAPOR-PRESSURE FROM SOLELY THEORETICALLY-DERIVED DESCRIPTORS, Journal of chemical information and computer sciences, 38(2), 1998, pp. 321-324
Citations number
23
Categorie Soggetti
Computer Science Interdisciplinary Applications","Computer Science Information Systems","Computer Science Interdisciplinary Applications",Chemistry,"Computer Science Information Systems
To date, most reported quantitative structure-property relationship (Q
SPR) methods to predict vapor pressure rely on, at least, some empiric
al data, such as boiling points, critical pressures, and critical temp
eratures. This limits their usefulness to available chemicals and incu
rs the time and expense of experimentation. A model to predict vapor p
ressure from only computationally derived molecular descriptors, allow
ing study of hypothetical structures, is described here. Several multi
linear regressions and artificial neural network analyses were tested
with a range of descriptors (e.g., topological and quantum mechanical)
derived solely from computations on molecular structure data. From a
set of 479 compounds, a linear regression with an r(2) of 0.960 was ac
hieved using polarizibility and polar functional group counts as descr
iptors. This new computationally based model also proves to be more ac
curate and works over a wider range of compound classes than most prev
iously reported models.