A random forest model has for the first time enabled the prediction of the crystallisability (crystals vs. no crystals) of organic molecules with ∼70% accuracy. The predictive model is based on calculated molecular descriptors and published experimental crystallisation propensities of a library of substituted acylanilides.
|Number of pages||4|
|Early online date||16 Feb 2015|
|Publication status||Published - 21 Jun 2015|
- molecular descriptors
- Machine Learning