# Thin Bridges for Drug Text Alignment: Lightweight Contrastive Learning for Target Specific Drug Retrieval

arXiv: https://arxiv.org/abs/2510.03309 · HTML: https://mlsanity.com/paper/2510.03309/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction](https://mlsanity.com/paper/2010.09885/) (2020)
- [Decoding speech perception from non-invasive brain recordings](https://mlsanity.com/paper/2208.12266/) (2022)
- [Brain decoding: toward real-time reconstruction of visual perception](https://mlsanity.com/paper/2310.19812/) (2023)
- [Advancing Drug Discovery with Enhanced Chemical Understanding via Asymmetric Contrastive Multimodal Learning](https://mlsanity.com/paper/2311.06456/) (2023)
- [Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge Graphs](https://mlsanity.com/paper/2501.01644/) (2025)
- [OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities](https://mlsanity.com/paper/2409.11059/) (2024)

## Abstract (arXiv)

Multimodal foundation models hold promise for drug discovery and biomedical applications, but most existing approaches rely on heavy pretraining or large scale multimodal corpora. We investigate whether thin contrastive bridges, lightweight projection heads over frozen unimodal encoders can align chemical and textual representations without training a full multimodal model. Using paired mechanisms from ChEMBL, we align ECFP4 molecular fingerprints with biomedical sentence embeddings through dual linear projections trained with a contrastive objective. To better handle drugs sharing the same therapeutic target, we incorporate hard negative weighting and a margin loss. Evaluation under scaffold based splits, which require generalization across disjoint chemical cores, demonstrates that our approach achieves non-trivial cross modal alignment and substantially improves within target discrimination compared to frozen baselines. These results suggest that thin bridges offer a compute efficient alternative to large scale multimodal pretraining, enabling scaffold aware drug text alignment and target specific retrieval in precision medicine.