A Molecular-Based Model for Prediction of Solubility of C60Fullerene in Various Solvents (2008)
- Authors: Farhad Gharagheizi, Reza Fareghi Alamdari
- Journal: Fullerenes, Nanotubes and Carbon Nanostructures
- Article Type: journal-article
- Dataset Type: PhysChem & Functionality Datasets
- Subject: Organic Chemistry,Physical and Theoretical Chemistry,General Materials Science,Atomic and Molecular Physics, and Optics
- Date: 2008-1
- License:
- URL: http://dx.doi.org/10.1080/15363830701779315
- DOI: 10.1080/15363830701779315
Original Study Abstract
In this presented work, a quantitative structure‐property relationship study (QSPR) was done for prediction of solubility of C60 fullerene in various solvents. In this study, genetic algorithm‐based multivariate linear regression (GA‐MLR) was applied to obtain most statistically effective molecular descriptors on solubility of C60 in various solvents. All of these molecular descriptors are only calculated from the chemical structure of solvents. For considering nonlinear behavior of appearing molecular descriptors in GA‐MLR section, a feed forward neural network (FFNN) was constructed and optimized for prediction of solubility of C60 fullerene in solvents. Obtained models considerably showed better accuracy in comparison with the previous models.
Data Sample
| Solvents |
piPC03 |
ATS1m |
Seigp |
More23e |
H1m |
logS Exp. |
| pentane |
1,099 |
1,609 |
0 |
-0,922 |
0,148 |
-6,1 |
| hexane |
1,386 |
1,792 |
0 |
-1,156 |
0,173 |
-5,1 |
| octane |
1,792 |
2,079 |
0 |
-1,656 |
0,208 |
-5,2 |
| iso-octane |
1,792 |
2,079 |
0 |
-1,529 |
0,242 |
-5,2 |
| decane |
2,079 |
2,303 |
0 |
-2,151 |
0,233 |
-4,7 |
Data Summary
| Variable |
Count (unique values) |
| Solvents |
124 |