Related Experiment Video
Updated: Jun 19, 2025

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
Published on: April 13, 2022
BartSmiles: Generative Masked Language Models for Molecular Representations
Gayane Chilingaryan1, Hovhannes Tamoyan1, Ani Tevosyan1,2
1YerevaNN, Charents str. 20, 0025 Yerevan, Armenia.
Abstract:
We discover a robust self-supervised strategy tailored toward molecular representations for generative masked language models through a series of tailored, in-depth ablations. Using this pretraining strategy, we train BARTSmiles, a BART-like model with an order of magnitude more compute than previous self-supervised molecular representations. In-depth evaluations show that BARTSmiles consistently outperforms other self-supervised representations across classification, regression, and generation tasks, setting a new state-of-the-art on eight tasks. We then show that when applied to the molecular domain, the BART objective learns representations that implicitly encode our downstream tasks of interest. For example, by selecting seven neurons from a frozen BARTSmiles, we can obtain a model having performance within two percentage points of the full fine-tuned model on task Clintox. Lastly, we show that standard attribution interpretability methods, when applied to BARTSmiles, highlight certain substructures that chemists use to explain specific properties of molecules. The code and pretrained model are publicly available.
Related Concept Videos
Molecular Models
Predicting Molecular Geometry
Newman Projections
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
Fischer Projections
Molecular Orbital Theory II
Molecular Orbital Theory I

