HiCP2GAN: a plug and play foundation model-based GAN for Hi-C enhancement.
- 1Department of Computer Science, University of Colorado at Colorado Springs, 1420 Austin Bluffs Pkwy, Colorado Springs, CO 80918, United States.
- 2Department of Computer Science and Engineering, University of North Texas, 1155 Union Circle, Denton, TX 76203, United States.
Abstract
The 3D organization of chromatin shapes gene regulation and cellular function, and Hi-C has become the primary technique for mapping chromatin interactions genome-wide. However, high-resolution data remain costly and scarce, leaving many studies with sparse contact maps that limit downstream analysis. Deep learning methods, especially generative adversarial networks (GANs), have shown promise for enhancing low-resolution Hi-C data, but most existing GAN-based approaches rely on custom discriminators trained from scratch, which can yield unstable training and limited generalization. Hi-C foundation models pretrained on large-scale data capture rich, transferable representations of chromatin structure, yet their use as discriminators within adversarial enhancement frameworks had not been explored. We introduce HiCP2GAN, a plug-and-play GAN that employs a pretrained Vision Transformer-based Hi-C foundation model as its discriminator. The discriminator was pretrained on 118 million Hi-C patches across diverse species and cell types, providing biologically meaningful gradients for adversarial supervision. The framework is generator-agnostic: any compatible Hi-C resolution enhancement architecture can serve as the generator, enabling fair comparison across methods. The encoder phase of the foundation model was adapted as a discriminator backbone, finetuning the first few layers from the input while freezing the deeper transformer layers to preserve pretrained knowledge while allowing task-specific adaptation. Experiments across various cell lines show that HiCP2GAN outperforms traditional GAN-based methods in most settings and improves the reconstruction quality and biological reproducibility of existing Hi-C enhancement models in most evaluated cases. HiCP2GAN is publicly available at https://github.com/OluwadareLab/HiCP2GAN.
Related
- Plug-and-Play or Plug-and-Pray? Impact of random versus targeted integration on the linearity and orthogonality of synthetic gene circuits in CHO cells.
- Plug-and-play assembly of biodegradable ionizable lipids for potent mRNA delivery and gene editing in vivo
- Constructing safe and highly potent antiviral neutralising nanodevices using a ferritin-based plug-and-play molecular assembly platform
- Phospholipids that Plug the Pores of Cholesteryl Ester Transfer Protein Control Its Triglyceride Transfer
- Maternal ranging strategies facilitate offspring social play at energetic cost in the most solitary ape.
BibTeX
@article{olowofila2026hicp2gan,
title = {{HiCP2GAN: a plug and play foundation model-based GAN for Hi-C enhancement.}},
author = {Samuel Olowofila and Oluwatosin Oluwadare},
journal = {Briefings in bioinformatics},
year = {2026},
month = nov,
doi = {10.1093/bib/bbag610},
url = {https://europepmc.org/article/MED/42969856},
note = {CC BY},
}
RIS
TY - JOUR
TI - HiCP2GAN: a plug and play foundation model-based GAN for Hi-C enhancement.
AU - Samuel Olowofila
AU - Oluwatosin Oluwadare
PY - 2026
DA - 2026/11/01
JO - Briefings in bioinformatics
DO - 10.1093/bib/bbag610
UR - https://europepmc.org/article/MED/42969856
AB - The 3D organization of chromatin shapes gene regulation and cellular function, and Hi-C has become the primary technique for mapping chromatin interactions genome-wide. However, high-resolution data remain costly and scarce, leaving many studies with sparse contact maps that limit downstream analysis. Deep learning methods, especially generative adversarial networks (GANs), have shown promise for enhancing low-resolution Hi-C data, but most existing GAN-based approaches rely on custom discriminators trained from scratch, which can yield unstable training and limited generalization. Hi-C foundation models pretrained on large-scale data capture rich, transferable representations of chromatin structure, yet their use as discriminators within adversarial enhancement frameworks had not been explored. We introduce HiCP2GAN, a plug-and-play GAN that employs a pretrained Vision Transformer-based Hi-C foundation model as its discriminator. The discriminator was pretrained on 118 million Hi-C patches across diverse species and cell types, providing biologically meaningful gradients for adversarial supervision. The framework is generator-agnostic: any compatible Hi-C resolution enhancement architecture can serve as the generator, enabling fair comparison across methods. The encoder phase of the foundation model was adapted as a discriminator backbone, finetuning the first few layers from the input while freezing the deeper transformer layers to preserve pretrained knowledge while allowing task-specific adaptation. Experiments across various cell lines show that HiCP2GAN outperforms traditional GAN-based methods in most settings and improves the reconstruction quality and biological reproducibility of existing Hi-C enhancement models in most evaluated cases. HiCP2GAN is publicly available at https://github.com/OluwadareLab/HiCP2GAN.
SN - 1467-5463
SN - 1477-4054
ER -