ProtFAD: Introducing function-aware domains as implicit modality towards protein function prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929609874866176 |
|---|---|
| author | Wang, Mingqing Nie, Zhiwei He, Yonghong Vasilakos, Athanasios V. Ren, Zhixiang |
| author_facet | Wang, Mingqing Nie, Zhiwei He, Yonghong Vasilakos, Athanasios V. Ren, Zhixiang |
| contents | Protein function prediction is currently achieved by encoding its sequence or structure, where the sequence-to-function transcendence and high-quality structural data scarcity lead to obvious performance bottlenecks. Protein domains are "building blocks" of proteins that are functionally independent, and their combinations determine the diverse biological functions. However, most existing studies have yet to thoroughly explore the intricate functional information contained in the protein domains. To fill this gap, we propose a synergistic integration approach for a function-aware domain representation, and a domain-joint contrastive learning strategy to distinguish different protein functions while aligning the modalities. Specifically, we align the domain semantics with GO terms and text description to pre-train domain embeddings. Furthermore, we partition proteins into multiple sub-views based on continuous joint domains for contrastive training under the supervision of a novel triplet InfoNCE loss. Our approach significantly and comprehensively outperforms the state-of-the-art methods on various benchmarks, and clearly differentiates proteins carrying distinct functions compared to the competitor. Our implementation is available at https://github.com/AI-HPC-Research-Team/ProtFAD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_15158 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ProtFAD: Introducing function-aware domains as implicit modality towards protein function prediction Wang, Mingqing Nie, Zhiwei He, Yonghong Vasilakos, Athanasios V. Ren, Zhixiang Biomolecules Machine Learning Protein function prediction is currently achieved by encoding its sequence or structure, where the sequence-to-function transcendence and high-quality structural data scarcity lead to obvious performance bottlenecks. Protein domains are "building blocks" of proteins that are functionally independent, and their combinations determine the diverse biological functions. However, most existing studies have yet to thoroughly explore the intricate functional information contained in the protein domains. To fill this gap, we propose a synergistic integration approach for a function-aware domain representation, and a domain-joint contrastive learning strategy to distinguish different protein functions while aligning the modalities. Specifically, we align the domain semantics with GO terms and text description to pre-train domain embeddings. Furthermore, we partition proteins into multiple sub-views based on continuous joint domains for contrastive training under the supervision of a novel triplet InfoNCE loss. Our approach significantly and comprehensively outperforms the state-of-the-art methods on various benchmarks, and clearly differentiates proteins carrying distinct functions compared to the competitor. Our implementation is available at https://github.com/AI-HPC-Research-Team/ProtFAD. |
| title | ProtFAD: Introducing function-aware domains as implicit modality towards protein function prediction |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2405.15158 |