@article{10.1021/acs.jcim.5c03121,
    author = {Brzakala, Cole and Moultos, Othonas A. and van der Hoek, Jan Peter and Taormina, Riccardo},
    title = {Evaluating Molecular
Representations for Predicting
Cyclodextrin-PFAS Binding Energy with Machine Learning: Domain Transfer
and Data Limitations},
    journal = {Journal of Chemical Information and Modeling},
    volume = {66},
    number = {13},
    pages = {7360-7376},
    year = {2026},
    month = {07},
    abstract = {Per- and polyfluoroalkyl substances (PFAS) persist in
water systems
and resist conventional removal methods such as activated carbon,
which shows reduced efficiency with short-chain PFAS and in the presence
of dissolved organic matter. Cyclodextrin-based polymers (CDPs) have
emerged as sustainable alternatives, with competitive and selective
PFAS adsorption capabilities. These polymers consist of glucose-based
cyclodextrin (CD) units that can form host–guest inclusion
complexes with PFAS pollutants. However, these binding interactions
are not fully understood or quantified. We conducted an evaluation
of machine learning approaches to model these host–guest interactions,
providing insights into predictive capabilities for later CDP design.
This study systematically compares molecular representations (Mordred,
ECFP, ChemBERTa, UniMol2, etc.) across several machine learning architectures
to predict CD-PFAS binding energies. First, we generated molecular
embeddings of 3459 experimental host–guest pairs in the OpenCycloDB
data set and 63 external CD-PFAS pairs. We then compared these embeddings
via AlignedUMAP visualizations and nearest neighbor analyses. Next,
we trained and evaluated predictive models using these embeddings
on the OpenCycloDB data set, exploring the effectiveness of transfer
learning and finetuning techniques. We finally tested model generalizability
on two external experimental CD-PFAS binding data sets. All embeddings
captured relevant chemical features, where UniMol2 differed most from
other methods in embedding space analysis. Predictive models performed
variably based on embedding choice and architecture, with the best-performing
combination achieving moderate accuracy on the OpenCycloDB data set.
Embeddings pretrained on large molecular data sets and finetuning
the ChemBERTa embeddings both showed predictive improvements. However,
external validation revealed limited generalizability to CD-PFAS complexes,
highlighting domain shift challenges. Notably, leave-one-out cross-validation
on the external PFAS-specific data indicated that training on in-domain
data improved predictive performance at the cost of generalizability.
This work demonstrates that molecular representation choice is critical
for small-data host–guest binding prediction. However, domain
shift between general CD data and specialized CD–PFAS applications
remains a fundamental challenge, for which transfer learning and finetuning
may offer potential solutions for future data-driven pipelines for
CDP design and sustainable PFAS removal.},
    issn = {1549-9596},
    doi = {10.1021/acs.jcim.5c03121},
    url = {https://doi.org/10.1021/acs.jcim.5c03121},
    eprint = {https://pubs.acs.org/jcisd8/article-pdf/66/13/7360/65250369/acs.jcim.5c03121.pdf},
}