# Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery

arXiv: https://arxiv.org/abs/2509.14788 · HTML: https://mlsanity.com/paper/2509.14788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [DeepDTA: Deep Drug-Target Binding Affinity Prediction](https://mlsanity.com/paper/1801.10193/) (2018)
- [ChemBERTa-2: Towards Chemical Foundation Models](https://mlsanity.com/paper/2209.01712/) (2022)
- [SELFIES and the future of molecular string representations](https://mlsanity.com/paper/2204.00056/) (2022)
- [MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction](https://mlsanity.com/paper/2004.11424/) (2020)
- [DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences](https://mlsanity.com/paper/1811.02114/) (2018)
- [SELFormer: Molecular Representation Learning via SELFIES Language Models](https://mlsanity.com/paper/2304.04662/) (2023)
- [Interpretable bilinear attention network with domain adaptation improves drug-target prediction](https://mlsanity.com/paper/2208.02194/) (2022)
- [Augmenting Convolutional networks with attention-based aggregation](https://mlsanity.com/paper/2112.13692/) (2021)
- [DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening](https://mlsanity.com/paper/2310.06367/) (2023)
- [A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction](https://mlsanity.com/paper/2405.14545/) (2024)

## Abstract (arXiv)

Accurate identification of drug-target interactions (DTI) remains a central challenge in computational pharmacology, where sequence-based methods offer scalability. This work introduces a sequence-based drug-target interaction framework that integrates structural priors into protein representations while maintaining high-throughput screening capability. Evaluated across multiple benchmarks, the model achieves state-of-the-art performance on Human and BioSNAP datasets and remains competitive on BindingDB. In virtual screening tasks, it surpasses prior methods on LIT-PCBA, yielding substantial gains in AUROC and BEDROC. Ablation studies confirm the critical role of learned aggregation, bilinear attention, and contrastive alignment in enhancing predictive robustness. Embedding visualizations reveal improved spatial correspondence with known binding pockets and highlight interpretable attention patterns over ligand-residue contacts. These results validate the framework's utility for scalable and structure-aware DTI prediction.