iBT-Net: an incremental broad transformer network for cancer drug response prediction
Yongkang Zhan1, Jifeng Guo1, C L Philip Chen1,2
1School of Computer Science & Engineering,South China University of Technology, 510006, China.
Abstract:
In modern precision medicine, it is an important research topic to predict cancer drug response. Due to incomplete chemical structures and complex gene features, however, it is an ongoing work to design efficient data-driven methods for predicting drug response. Moreover, since the clinical data cannot be easily obtained all at once, the data-driven methods may require relearning when new data are available, resulting in increased time consumption and cost. To address these issues, an incremental broad Transformer network (iBT-Net) is proposed for cancer drug response prediction. Different from the gene expression features learning from cancer cell lines, structural features are further extracted from drugs by Transformer. Broad learning system is then designed to integrate the learned gene features and structural features of drugs to predict the response. With the capability of incremental learning, the proposed method can further use new data to improve its prediction performance without retraining totally. Experiments and comparison studies demonstrate the effectiveness and superiority of iBT-Net under different experimental configurations and continuous data learning.
Insights
This study introduces an incremental broad Transformer network (iBT-Net) for predicting cancer drug response. The iBT-Net efficiently integrates drug structure and gene features, enabling continuous learning without full retraining.
Area of Science:
- Oncology
- Bioinformatics
- Computational Biology
Background:
- Predicting cancer drug response is crucial for precision medicine.
- Challenges include incomplete chemical structures, complex gene features, and difficulty in acquiring large clinical datasets.
- Existing data-driven methods often require costly and time-consuming retraining with new data.
Purpose of the Study:
- To develop an efficient, data-driven method for cancer drug response prediction.
- To address the limitations of retraining models with new clinical data.
- To propose a novel network architecture capable of incremental learning.
Main Methods:
- An incremental broad Transformer network (iBT-Net) was developed.
- Transformer models extracted structural features from drugs.
- A broad learning system integrated gene expression features and drug structural features.
- The network was designed for incremental learning, allowing updates without complete retraining.
Main Results:
- The iBT-Net demonstrated effectiveness in predicting cancer drug response.
- Experimental results showed superiority compared to other methods.
- The incremental learning capability allowed for performance improvement with continuous data acquisition.
Conclusions:
- The proposed iBT-Net offers an efficient and superior approach to cancer drug response prediction.
- Its incremental learning feature addresses the challenge of updating models with new clinical data.
- iBT-Net holds promise for advancing precision medicine through improved drug response prediction.
More Related Videos
Related Concept Videos
02:50Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
01:21Cancer Survival Analysis