Christopher L. Porterfield
Christopher L. Porterfield has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Sebastian Hauser
Department of Drug Design and Pharmacology University of Copenhagen Copenhagen Denmark
1 shared publication - Jakob Sture Madsen
Department of Drug Design and Pharmacology
1 shared publication - Sara Angelucci
Department of Drug Design and Pharmacology
1 shared publication - Xiaoting Liu
Department of Drug Design and Pharmacology
1 shared publication
Latest Publications
- Open Access
- 19 June 2026
- Published by American Chemical Society (ACS) in ChemRxiv
ModernMolBERT: A Compact SELFIES Encoder for Molecular Representation Learning
We introduce ModernMolBERT, an encoder-only transformer model for small-molecule representation learning. ModernMolBERT adapts the ModernBERT architecture to molecular language modelling and pairs it with a SELFIES-aware Atom Pair Encoding (APE) tokeniser. Both released variants (small and base) are pre-trained with masked language modelling on approximately 2.4M unique SELFIES strings from ChEMBL 36 and evaluated as frozen molecular embedders on 25 binary classification benchmarks. ModernMolBERT-base attains a mean ROC-AUC of 77.9 (reported on a 0 to 100 scale), competitive with a strong fingerprint baseline and improving on comparable pre-trained string encoders by roughly five points. ModernMolBERT provides a compact, reproducible, open-source foundation for SELFIES-based molecular representation learning; we release the model weights, the APE tokeniser, and training code.
- 19 June 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessModernMolBERT: A Compact SELFIES Encoder for Molecular Representation Learning
We introduce ModernMolBERT, an encoder-only transformer model for small-molecule representation learning. ModernMolBERT adapts the ModernBERT architecture to molecular language modelling and pairs it with a SELFIES-aware Atom Pair Encoding (APE) tokeniser. Both released variants (small and base) are pre-trained with masked language modelling on approximately 2.4M unique SELFIES strings from ChEMBL 36 and evaluated as frozen molecular embedders on 25 binary classification benchmarks. ModernMolBERT-base attains a mean ROC-AUC of 77.9 (reported on a 0 to 100 scale), competitive with a strong fingerprint baseline and improving on comparable pre-trained string encoders by roughly five points. ModernMolBERT provides a compact, reproducible, open-source foundation for SELFIES-based molecular representation learning; we release the model weights, the APE tokeniser, and training code.