Multimodal 3D Genome Pre-training
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917046699163648 |
|---|---|
| author | Yang, Minghao Li, Pengteng Liang, Yan Cai, Qianyi Zheng, Zhihang Zhang, Shichen Zhang, Pengfei Huang, Zhi-An Xiong, Hui |
| author_facet | Yang, Minghao Li, Pengteng Liang, Yan Cai, Qianyi Zheng, Zhihang Zhang, Shichen Zhang, Pengfei Huang, Zhi-An Xiong, Hui |
| contents | Deep learning techniques have driven significant progress in various analytical tasks within 3D genomics in computational biology. However, a holistic understanding of 3D genomics knowledge remains underexplored. Here, we propose MIX-HIC, the first multimodal foundation model of 3D genome that integrates both 3D genome structure and epigenomic tracks, which obtains unified and comprehensive semantics. For accurate heterogeneous semantic fusion, we design the cross-modal interaction and mapping blocks for robust unified representation, yielding the accurate aggregation of 3D genome knowledge. Besides, we introduce the first large-scale dataset comprising over 1 million pairwise samples of Hi-C contact maps and epigenomic tracks for high-quality pre-training, enabling the exploration of functional implications in 3D genomics. Extensive experiments show that MIX-HIC can significantly surpass existing state-of-the-art methods in diverse downstream tasks. This work provides a valuable resource for advancing 3D genomics research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09060 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multimodal 3D Genome Pre-training Yang, Minghao Li, Pengteng Liang, Yan Cai, Qianyi Zheng, Zhihang Zhang, Shichen Zhang, Pengfei Huang, Zhi-An Xiong, Hui Machine Learning Artificial Intelligence Genomics Deep learning techniques have driven significant progress in various analytical tasks within 3D genomics in computational biology. However, a holistic understanding of 3D genomics knowledge remains underexplored. Here, we propose MIX-HIC, the first multimodal foundation model of 3D genome that integrates both 3D genome structure and epigenomic tracks, which obtains unified and comprehensive semantics. For accurate heterogeneous semantic fusion, we design the cross-modal interaction and mapping blocks for robust unified representation, yielding the accurate aggregation of 3D genome knowledge. Besides, we introduce the first large-scale dataset comprising over 1 million pairwise samples of Hi-C contact maps and epigenomic tracks for high-quality pre-training, enabling the exploration of functional implications in 3D genomics. Extensive experiments show that MIX-HIC can significantly surpass existing state-of-the-art methods in diverse downstream tasks. This work provides a valuable resource for advancing 3D genomics research. |
| title | Multimodal 3D Genome Pre-training |
| topic | Machine Learning Artificial Intelligence Genomics |
| url | https://arxiv.org/abs/2504.09060 |