Welcome to the GitHub repository for the paper: https://doi.org/10.26434/chemrxiv-2022-hxvcc
Abstract: One of the biggest obstacles to successful polymer property prediction is an effective representation that accurately captures the sequence of repeat units in a polymer. Motivated by the successes of data augmentation in computer vision and natural language processing, we explore augmenting polymer data by iteratively rearranging the molecular representation while preserving the correct connectivity, revealing additional substructural information that is not present in a single representation. We evaluate the effects of this technique on the performance of machine learning models trained on three polymer datasets and compare them to common molecular representations. Data augmentation does not yield significant improvements in machine learning property prediction performance compared to equivalent (non-augmented) representations. In datasets where the target property is primarily influenced by the polymer sequence rather than experimental parameters, this data augmentation technique provides the molecular embedding with more information to improve property prediction accuracy.
Keywords: data augmentation, machine learning, polymers, molecular representation
- Fork, Clone, or Download this repository.
- Create a conda environment.
- In this directory,
pip install -e . - Access raw data ->
da_for_polymers/data/raw/Dataset - Access data augmentation tool ->
da_for_polymers/data/input_representation/Dataset/manual_frag/augment_manual_frag.py - Access processed data ->
da_for_polymers/data/input_representation/Dataset - Access prediction results ->
da_for_polymers/training - Run the shell files in
da_for_polymers/ML_models/pytorch/Datasetorda_for_polymers/ML_models/sklearn/Datasetto run models on your setup. To run specific models or molecular representations, uncomment or comment specific lines. Recommened to understand how to use argument parsers for these scripts. <<<<<<< HEAD - To view or re-create figures, go to ->
da_for_polymers/visualization. Each figure in the paper can be recreated with therecreate_all_plots.shfile (read comments). (Supplementary Figures are found inda_for_polymers/data/exploration)g ======= - To view or re-create figures, go to ->
da_for_polymers/visualization. Each figure in the paper can be recreated with therecreate_all_plots.shfile (read comments). (Supplementary Figures are found inda_for_polymers/data/exploration)
3518320fe8131a4d5c99874c5d2194ecbf421006