A hybrid deep forest-based method for predicting synergistic drug combinations
Summary: Combination therapy is a promising approach in treating multiple complex diseases. However, the large search space of available drug combinations exacerbates challenge for experimental screening. To predict synergistic drug combinations in different cancer cell lines, we propose an improved...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | Cell Reports: Methods |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266723752300022X |
| _version_ | 1828001719008624640 |
|---|---|
| author | Lianlian Wu Jie Gao Yixin Zhang Binsheng Sui Yuqi Wen Qingqiang Wu Kunhong Liu Song He Xiaochen Bo |
| author_facet | Lianlian Wu Jie Gao Yixin Zhang Binsheng Sui Yuqi Wen Qingqiang Wu Kunhong Liu Song He Xiaochen Bo |
| author_sort | Lianlian Wu |
| collection | DOAJ |
| description | Summary: Combination therapy is a promising approach in treating multiple complex diseases. However, the large search space of available drug combinations exacerbates challenge for experimental screening. To predict synergistic drug combinations in different cancer cell lines, we propose an improved deep forest-based method, ForSyn, and design two forest types embedded in ForSyn. ForSyn handles imbalanced and high-dimensional data in medium-/small-scale datasets, which are inherent characteristics of drug combination datasets. Compared with 12 state-of-the-art methods, ForSyn ranks first on four metrics for eight datasets with different feature combinations. We conduct a systematic analysis to identify the most appropriate configuration parameters. We validate the predictive value of ForSyn with cell-based experiments on several previously unexplored drug combinations. Finally, a systematic analysis of feature importance is performed on the top contributing features extracted by ForSyn. The resulting key genes may play key roles on corresponding cancers. Motivation: Combination therapy has shown promise as a treatment for complex diseases such as cancer. Synergistic drug combinations can offer increased therapeutic efficacy and reduce toxicity compared with single drugs. However, class imbalances in datasets have complicated the use of computational tools, such as deep learning, for synergistic drug prediction. We propose an improved deep forest-based model, ForSyn, to address the above problem on imbalanced, medium- or small-scale datasets with high dimensionality. |
| first_indexed | 2024-04-10T06:33:18Z |
| format | Article |
| id | doaj.art-bcd9723f17eb48d8af1c0781be93fc28 |
| institution | Directory Open Access Journal |
| issn | 2667-2375 |
| language | English |
| last_indexed | 2024-04-10T06:33:18Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Cell Reports: Methods |
| spelling | doaj.art-bcd9723f17eb48d8af1c0781be93fc282023-03-01T04:33:24ZengElsevierCell Reports: Methods2667-23752023-02-0132100411A hybrid deep forest-based method for predicting synergistic drug combinationsLianlian Wu0Jie Gao1Yixin Zhang2Binsheng Sui3Yuqi Wen4Qingqiang Wu5Kunhong Liu6Song He7Xiaochen Bo8Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China; Department of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing 100850, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Fujian Medical University, Fuzhou 350122, ChinaDepartment of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing 100850, ChinaSchool of Film, Xiamen University, Xiamen 361005, ChinaDepartment of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing 100850, ChinaSchool of Film, Xiamen University, Xiamen 361005, ChinaSchool of Film, Xiamen University, Xiamen 361005, China; Corresponding authorDepartment of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing 100850, China; Corresponding authorAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China; Department of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing 100850, China; Corresponding authorSummary: Combination therapy is a promising approach in treating multiple complex diseases. However, the large search space of available drug combinations exacerbates challenge for experimental screening. To predict synergistic drug combinations in different cancer cell lines, we propose an improved deep forest-based method, ForSyn, and design two forest types embedded in ForSyn. ForSyn handles imbalanced and high-dimensional data in medium-/small-scale datasets, which are inherent characteristics of drug combination datasets. Compared with 12 state-of-the-art methods, ForSyn ranks first on four metrics for eight datasets with different feature combinations. We conduct a systematic analysis to identify the most appropriate configuration parameters. We validate the predictive value of ForSyn with cell-based experiments on several previously unexplored drug combinations. Finally, a systematic analysis of feature importance is performed on the top contributing features extracted by ForSyn. The resulting key genes may play key roles on corresponding cancers. Motivation: Combination therapy has shown promise as a treatment for complex diseases such as cancer. Synergistic drug combinations can offer increased therapeutic efficacy and reduce toxicity compared with single drugs. However, class imbalances in datasets have complicated the use of computational tools, such as deep learning, for synergistic drug prediction. We propose an improved deep forest-based model, ForSyn, to address the above problem on imbalanced, medium- or small-scale datasets with high dimensionality.http://www.sciencedirect.com/science/article/pii/S266723752300022XCP: Systems biology |
| spellingShingle | Lianlian Wu Jie Gao Yixin Zhang Binsheng Sui Yuqi Wen Qingqiang Wu Kunhong Liu Song He Xiaochen Bo A hybrid deep forest-based method for predicting synergistic drug combinations Cell Reports: Methods CP: Systems biology |
| title | A hybrid deep forest-based method for predicting synergistic drug combinations |
| title_full | A hybrid deep forest-based method for predicting synergistic drug combinations |
| title_fullStr | A hybrid deep forest-based method for predicting synergistic drug combinations |
| title_full_unstemmed | A hybrid deep forest-based method for predicting synergistic drug combinations |
| title_short | A hybrid deep forest-based method for predicting synergistic drug combinations |
| title_sort | hybrid deep forest based method for predicting synergistic drug combinations |
| topic | CP: Systems biology |
| url | http://www.sciencedirect.com/science/article/pii/S266723752300022X |
| work_keys_str_mv | AT lianlianwu ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT jiegao ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT yixinzhang ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT binshengsui ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT yuqiwen ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT qingqiangwu ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT kunhongliu ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT songhe ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT xiaochenbo ahybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT lianlianwu hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT jiegao hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT yixinzhang hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT binshengsui hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT yuqiwen hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT qingqiangwu hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT kunhongliu hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT songhe hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations AT xiaochenbo hybriddeepforestbasedmethodforpredictingsynergisticdrugcombinations |