# Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design

arXiv: https://arxiv.org/abs/2601.09693 · HTML: https://mlsanity.com/paper/2601.09693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 98 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [DeepDTA: Deep Drug-Target Binding Affinity Prediction](https://mlsanity.com/paper/1801.10193/) (2018)
- [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://mlsanity.com/paper/2202.05146/) (2022)
- [CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP](https://mlsanity.com/paper/2110.11316/) (2021)
- [Development and evaluation of a deep learning model for protein-ligand binding affinity prediction](https://mlsanity.com/paper/1712.07042/) (2017)
- [Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language](https://mlsanity.com/paper/2303.03363/) (2023)
- [DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening](https://mlsanity.com/paper/2310.06367/) (2023)
- [Context-enriched molecule representations improve few-shot drug discovery](https://mlsanity.com/paper/2305.09481/) (2023)
- [Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning](https://mlsanity.com/paper/2508.06199/) (2025)
- [Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models](https://mlsanity.com/paper/2310.13913/) (2023)
- [A large dataset curation and benchmark for drug target interaction](https://mlsanity.com/paper/2401.17174/) (2024)
- [Hashing based Contrastive Learning for Virtual Screening](https://mlsanity.com/paper/2407.19790/) (2024)
- [Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT](https://mlsanity.com/paper/2411.15418/) (2024)
- [Learning Protein-Ligand Binding in Hyperbolic Space](https://mlsanity.com/paper/2508.15480/) (2025)
- [S2Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening](https://mlsanity.com/paper/2511.07006/) (2025)
- [Tensor-DTI: Enhancing Biomolecular Interaction Prediction with Contrastive Embedding Learning](https://mlsanity.com/paper/2601.05792/) (2026)

## Abstract (arXiv)

Structure-based and ligand-based computational drug design have traditionally relied on disjoint data sources and modeling assumptions, limiting their joint use at scale. In this work, we introduce Contrastive Geometric Learning for Unified Computational Drug Design (ConGLUDe), a single contrastive geometric model that unifies structure- and ligand-based training. ConGLUDe couples a geometric protein encoder that produces whole-protein representations and implicit embeddings of predicted binding sites with a fast ligand encoder, removing the need for predefined pockets. By aligning ligands with both global protein representations and multiple candidate binding sites through contrastive learning, ConGLUDe supports ligand-conditioned pocket prediction in addition to virtual screening and target fishing, while being trained jointly on protein-ligand complexes and large-scale bioactivity data. Across diverse benchmarks, ConGLUDe achieves competitive zero-shot virtual screening performance, substantially outperforms existing methods on a challenging target fishing task, and demonstrates state-of-the-art ligand-conditioned pocket selection. These results highlight the advantages of unified structure-ligand training and position ConGLUDe as a step toward general-purpose foundation models for drug discovery.