Solubility of a compound is a crucial feature in drug development and drug enhancement domain. Prediction of a solubility without calculating it experimentally, would provide vital insights into the utility of the compound and details on where and when it can be used. Additionally, it would reduce the manual effort to evaluate solubility using multiple experimentations. In this project, we use details of SMILES data (Simplified Molecular-Input Line-Entry System) which is essentially, the molecular structure in a line format, to calculate descriptors (cLogP:Octanol-water partition coefficient, MW:Molecular weight,RB:Number of rotatable bonds, AP:Aromatic proportion = number of aromatic atoms / total number of heavy atoms) and forecast solubility by training Delaney’s dataset using linear regression technique.
Keerthi-Sreenivas/Solubility-Prediction-Data-Analytics
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|