Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP
- 1University College London
Abstract
Virtual screening has become central to early-stage drug discovery, and structure-based approaches have recently been reframed as a retrieval problem through contrastive learning methods such as DrugCLIP, which project protein pockets and ligands into a shared embedding space. However, what these abstract representations exactly encode, and how they relate to conventional notions of structural and chemical similarity, remains unclear. Here we present a systematic dissection of DrugCLIP's latent space. We show that its pocket embeddings, despite not being explicitly trained for the task, set a new state of the art in pocket similarity search while running over 100 times faster than existing structural descriptors, and that this embedding space is structurally coherent and robust to conformational variation. Ligand embeddings, by contrast, encode a pocket-aware notion of chemical similarity that only partially mirrors fingerprint-based measures. Using a rigorous de-leakage benchmark, we further show that DrugCLIP generalises to unseen proteins and chemistries rather than memorising training data, recovering the correct bound ligand within the top 1% of 50,000 candidates for 55-75% of novel targets. Performance nonetheless declines under increasingly realistic screening conditions, a drop attributable to sidechain reorientation across apo, holo and AlphaFold-derived structures, and to residue mismatch when using predicted pockets. These findings clarify the practical boundaries of DrugCLIP's applicability, identify pocket prediction accuracy as a key factor for improving performance, and offer a transferable framework for interpreting the latent spaces of related contrastive pocket-ligand encoders. Together, these results support the improvement of existing methods and the development of a new generation of contrastive screening approaches.
Related
- Pocket contrastive learning and conformation fusion for robust structure-conditioned 3D molecular generation under receptor conformational variation.
- ContrasTED: contrastive domain embeddings for scalable remote homology classification
- Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role
- A Unified Structure-Based Deep-Learning Framework for High-Throughput Screening of Protein-Binding RNAs
- Predicting miRNA–Disease Associations Based on Contrastive Learning of Linear and Nonlinear Features
BibTeX
@misc{utges2026interrogating,
title = {{Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP}},
author = {J. Sanchez Utges and D. T. Jones and C. Orengo},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.752029},
url = {https://www.biorxiv.org/content/10.64898/2026.09.16.752029v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP
AU - J. Sanchez Utges
AU - D. T. Jones
AU - C. Orengo
PY - 2026
DA - 2026/09/16
PB - bioRxiv
DO - 10.64898/2026.09.16.752029
UR - https://www.biorxiv.org/content/10.64898/2026.09.16.752029v1
AB - Virtual screening has become central to early-stage drug discovery, and structure-based approaches have recently been reframed as a retrieval problem through contrastive learning methods such as DrugCLIP, which project protein pockets and ligands into a shared embedding space. However, what these abstract representations exactly encode, and how they relate to conventional notions of structural and chemical similarity, remains unclear. Here we present a systematic dissection of DrugCLIP's latent space. We show that its pocket embeddings, despite not being explicitly trained for the task, set a new state of the art in pocket similarity search while running over 100 times faster than existing structural descriptors, and that this embedding space is structurally coherent and robust to conformational variation. Ligand embeddings, by contrast, encode a pocket-aware notion of chemical similarity that only partially mirrors fingerprint-based measures. Using a rigorous de-leakage benchmark, we further show that DrugCLIP generalises to unseen proteins and chemistries rather than memorising training data, recovering the correct bound ligand within the top 1% of 50,000 candidates for 55-75% of novel targets. Performance nonetheless declines under increasingly realistic screening conditions, a drop attributable to sidechain reorientation across apo, holo and AlphaFold-derived structures, and to residue mismatch when using predicted pockets. These findings clarify the practical boundaries of DrugCLIP's applicability, identify pocket prediction accuracy as a key factor for improving performance, and offer a transferable framework for interpreting the latent spaces of related contrastive pocket-ligand encoders. Together, these results support the improvement of existing methods and the development of a new generation of contrastive screening approaches.
ER -