Predicting Polymer Solubility in Solvents Using SMILES Strings
It addresses the need for scalable solubility prediction in applications like green chemistry and materials design, but is incremental as it applies existing deep learning methods to a new dataset.
This work tackled the problem of predicting polymer solubility in solvents by developing a deep learning framework that uses SMILES strings to predict solubility as weight percent, achieving strong agreement with simulated data and high accuracy on 25 unseen experimental combinations.
Understanding and predicting polymer solubility in various solvents is critical for applications ranging from recycling to pharmaceutical formulation. This work presents a deep learning framework that predicts polymer solubility, expressed as weight percent (wt%), directly from SMILES representations of both polymers and solvents. A dataset of 8,049 polymer solvent pairs at 25 deg C was constructed from calibrated molecular dynamics simulations (Zhou et al., 2023), and molecular descriptors and fingerprints were combined into a 2,394 feature representation per sample. A fully connected neural network with six hidden layers was trained using the Adam optimizer and evaluated using mean squared error loss, achieving strong agreement between predicted and actual solubility values. Generalizability was demonstrated using experimentally measured data from the Materials Genome Project, where the model maintained high accuracy on 25 unseen polymer solvent combinations. These findings highlight the viability of SMILES based machine learning models for scalable solubility prediction and high-throughput solvent screening, supporting applications in green chemistry, polymer processing, and materials design.