Predicting Polymer Solubility in Solvents Using SMILES Strings

TL;DR

This paper introduces a deep learning model that predicts polymer solubility directly from SMILES strings, enabling scalable and accurate solvent screening for various industrial and scientific applications.

Contribution

The work presents a novel SMILES-based neural network framework for predicting polymer solubility, validated on simulated and experimental data, advancing high-throughput solvent screening methods.

Findings

Achieved high accuracy in predicting solubility from SMILES data.

Demonstrated model generalizability on unseen polymer-solvent pairs.

Supported applications in green chemistry and materials design.

Abstract

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.