ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction.
Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adapt...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1012748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206782776049664 |
|---|---|
| author | Yunyun Dong Yuanrong Zhang Yuhua Qian Yiming Zhao Ziting Yang Xiufang Feng |
| author_facet | Yunyun Dong Yuanrong Zhang Yuhua Qian Yiming Zhao Ziting Yang Xiufang Feng |
| author_sort | Yunyun Dong |
| collection | DOAJ |
| description | Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy. |
| format | Article |
| id | doaj-art-493131e08969484bb4be66aedae44be5 |
| institution | Kabale University |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-493131e08969484bb4be66aedae44be52025-02-07T05:30:26ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-01-01211e101274810.1371/journal.pcbi.1012748ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction.Yunyun DongYuanrong ZhangYuhua QianYiming ZhaoZiting YangXiufang FengPersonalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy.https://doi.org/10.1371/journal.pcbi.1012748 |
| spellingShingle | Yunyun Dong Yuanrong Zhang Yuhua Qian Yiming Zhao Ziting Yang Xiufang Feng ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. PLoS Computational Biology |
| title | ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. |
| title_full | ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. |
| title_fullStr | ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. |
| title_full_unstemmed | ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. |
| title_short | ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. |
| title_sort | asgcl adaptive sparse mapping based graph contrastive learning network for cancer drug response prediction |
| url | https://doi.org/10.1371/journal.pcbi.1012748 |
| work_keys_str_mv | AT yunyundong asgcladaptivesparsemappingbasedgraphcontrastivelearningnetworkforcancerdrugresponseprediction AT yuanrongzhang asgcladaptivesparsemappingbasedgraphcontrastivelearningnetworkforcancerdrugresponseprediction AT yuhuaqian asgcladaptivesparsemappingbasedgraphcontrastivelearningnetworkforcancerdrugresponseprediction AT yimingzhao asgcladaptivesparsemappingbasedgraphcontrastivelearningnetworkforcancerdrugresponseprediction AT zitingyang asgcladaptivesparsemappingbasedgraphcontrastivelearningnetworkforcancerdrugresponseprediction AT xiufangfeng asgcladaptivesparsemappingbasedgraphcontrastivelearningnetworkforcancerdrugresponseprediction |