KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality
Motivation: Synthetic lethality (SL) is a promising strategy for anticancer therapy, as inhibiting SL partners of genes with cancer-specific mutations can selectively kill the cancer cells without harming the normal cells. Wet-lab techniques for SL screening have issues like high cost and off-target...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/174266 |
| _version_ | 1826112549110677504 |
|---|---|
| author | Zhang, Ke Wu, Min Liu, Yong Feng, Yimiao Zheng, Jie |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Zhang, Ke Wu, Min Liu, Yong Feng, Yimiao Zheng, Jie |
| author_sort | Zhang, Ke |
| collection | NTU |
| description | Motivation: Synthetic lethality (SL) is a promising strategy for anticancer therapy, as inhibiting SL partners of genes with cancer-specific mutations can selectively kill the cancer cells without harming the normal cells. Wet-lab techniques for SL screening have issues like high cost and off-target effects. Computational methods can help address these issues. Previous machine learning methods leverage known SL pairs, and the use of knowledge graphs (KGs) can significantly enhance the prediction performance. However, the subgraph structures of KG have not been fully explored. Besides, most machine learning methods lack interpretability, which is an obstacle for wide applications of machine learning to SL identification. Results: We present a model named KR4SL to predict SL partners for a given primary gene. It captures the structural semantics of a KG by efficiently constructing and learning from relational digraphs in the KG. To encode the semantic information of the relational digraphs, we fuse textual semantics of entities into propagated messages and enhance the sequential semantics of paths using a recurrent neural network. Moreover, we design an attentive aggregator to identify critical subgraph structures that contribute the most to the SL prediction as explanations. Extensive experiments under different settings show that KR4SL significantly outperforms all the baselines. The explanatory subgraphs for the predicted gene pairs can unveil prediction process and mechanisms underlying synthetic lethality. The improved predictive power and interpretability indicate that deep learning is practically useful for SL-based cancer drug target discovery. |
| first_indexed | 2024-10-01T03:08:52Z |
| format | Journal Article |
| id | ntu-10356/174266 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:08:52Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1742662024-03-29T15:36:09Z KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality Zhang, Ke Wu, Min Liu, Yong Feng, Yimiao Zheng, Jie School of Computer Science and Engineering Computer and Information Science Automated pattern recognition Drug delivery system Motivation: Synthetic lethality (SL) is a promising strategy for anticancer therapy, as inhibiting SL partners of genes with cancer-specific mutations can selectively kill the cancer cells without harming the normal cells. Wet-lab techniques for SL screening have issues like high cost and off-target effects. Computational methods can help address these issues. Previous machine learning methods leverage known SL pairs, and the use of knowledge graphs (KGs) can significantly enhance the prediction performance. However, the subgraph structures of KG have not been fully explored. Besides, most machine learning methods lack interpretability, which is an obstacle for wide applications of machine learning to SL identification. Results: We present a model named KR4SL to predict SL partners for a given primary gene. It captures the structural semantics of a KG by efficiently constructing and learning from relational digraphs in the KG. To encode the semantic information of the relational digraphs, we fuse textual semantics of entities into propagated messages and enhance the sequential semantics of paths using a recurrent neural network. Moreover, we design an attentive aggregator to identify critical subgraph structures that contribute the most to the SL prediction as explanations. Extensive experiments under different settings show that KR4SL significantly outperforms all the baselines. The explanatory subgraphs for the predicted gene pairs can unveil prediction process and mechanisms underlying synthetic lethality. The improved predictive power and interpretability indicate that deep learning is practically useful for SL-based cancer drug target discovery. Published version 2024-03-25T02:59:43Z 2024-03-25T02:59:43Z 2023 Journal Article Zhang, K., Wu, M., Liu, Y., Feng, Y. & Zheng, J. (2023). KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality. Bioinformatics, 39(39 Suppl 1), i158-i167. https://dx.doi.org/10.1093/bioinformatics/btad261 1367-4811 https://hdl.handle.net/10356/174266 10.1093/bioinformatics/btad261 37387166 2-s2.0-85164229758 39 Suppl 1 39 i158 i167 en Bioinformatics © The Author(s) 2023. Published by Oxford University Press. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. application/pdf |
| spellingShingle | Computer and Information Science Automated pattern recognition Drug delivery system Zhang, Ke Wu, Min Liu, Yong Feng, Yimiao Zheng, Jie KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality |
| title | KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality |
| title_full | KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality |
| title_fullStr | KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality |
| title_full_unstemmed | KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality |
| title_short | KR4SL: knowledge graph reasoning for explainable prediction of synthetic lethality |
| title_sort | kr4sl knowledge graph reasoning for explainable prediction of synthetic lethality |
| topic | Computer and Information Science Automated pattern recognition Drug delivery system |
| url | https://hdl.handle.net/10356/174266 |
| work_keys_str_mv | AT zhangke kr4slknowledgegraphreasoningforexplainablepredictionofsyntheticlethality AT wumin kr4slknowledgegraphreasoningforexplainablepredictionofsyntheticlethality AT liuyong kr4slknowledgegraphreasoningforexplainablepredictionofsyntheticlethality AT fengyimiao kr4slknowledgegraphreasoningforexplainablepredictionofsyntheticlethality AT zhengjie kr4slknowledgegraphreasoningforexplainablepredictionofsyntheticlethality |