Optimizing Quantum Data Embeddings for Ligand-Based Virtual Screening
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918254609432576 |
|---|---|
| author | Choi, Junggu Hur, Tak Jeong, Seokhoon Jung, Kyle L. Park, Jun Bae Lee, Junho Jung, Jae U. Park, Daniel K. |
| author_facet | Choi, Junggu Hur, Tak Jeong, Seokhoon Jung, Kyle L. Park, Jun Bae Lee, Junho Jung, Jae U. Park, Daniel K. |
| contents | Effective molecular representations are essential for ligand-based virtual screening. We investigate how quantum data embedding strategies can improve this task by developing and evaluating a family of quantum-classical hybrid embedding approaches. These approaches combine classical neural networks with parameterized quantum circuits in different ways to generate expressive molecular representations and are assessed across two benchmark datasets of different sizes: the LIT-PCBA and COVID-19 collections. Across multiple biological targets and class-imbalance settings, several quantum and hybrid embedding variants consistently outperform classical baselines, especially in limited-data regimes. These results highlight the potential of optimized quantum data embeddings as data-efficient tools for ligand-based virtual screening. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16177 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Quantum Data Embeddings for Ligand-Based Virtual Screening Choi, Junggu Hur, Tak Jeong, Seokhoon Jung, Kyle L. Park, Jun Bae Lee, Junho Jung, Jae U. Park, Daniel K. Quantum Physics Effective molecular representations are essential for ligand-based virtual screening. We investigate how quantum data embedding strategies can improve this task by developing and evaluating a family of quantum-classical hybrid embedding approaches. These approaches combine classical neural networks with parameterized quantum circuits in different ways to generate expressive molecular representations and are assessed across two benchmark datasets of different sizes: the LIT-PCBA and COVID-19 collections. Across multiple biological targets and class-imbalance settings, several quantum and hybrid embedding variants consistently outperform classical baselines, especially in limited-data regimes. These results highlight the potential of optimized quantum data embeddings as data-efficient tools for ligand-based virtual screening. |
| title | Optimizing Quantum Data Embeddings for Ligand-Based Virtual Screening |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2512.16177 |