DrugBERT: a BERT-based approach integrating LDA topic embedding and efficacy-aware mechanism for predicting
Weiwei Zhu1,2, Xiaodong Jiang3, Lei Zhang4
1University of Science and Technology of China, Hefei, Anhui, 230026, China.
Background:
Due to the complexity of tumor genetic heterogeneity, personalized medicine has progressively emerged as the central focus of cancer research. However, how to accurately predict the drug response of patients before receiving treatment is the critical challenge to the development of this field.
Methods:
This paper proposes DrugBERT, a BERT-based framework integrated with LDA topic embedding and a drug efficacy-aware mechanism for predicting the efficacy of antitumor drugs. The method incorporates LDA-generated topic embedding as a semantic enhancement module into the BERT language model and introduces a drug efficacy-aware attention mechanism to prioritize drug efficacy-related semantic features. The model is via LSTM to capture long-range dependencies in clinical text data. In addition, the SMOTE algorithm is used to synthesize samples of the minority class to solve the problem of data imbalance.
Results:
The proposed method DrugBERT demonstrated remarkable performance on a dataset of 958 patients with non-small cell cancer treated with antitumor drugs. Furthermore, when validated on an independent dataset of 266 bowel cancer patients, the model achieved a 3% improvement in AUC over previous methods, signifying its robust generalization capability.
Conclusions:
DrugBERT can help predict the efficacy of antitumor drugs based on clinical text while exhibiting strong generalization capability. These findings highlight its potential for optimizing personalized therapeutic strategies through language model.
Insights
DrugBERT, a novel framework, accurately predicts antitumor drug efficacy from clinical text. This advance aids personalized cancer medicine by improving treatment strategy optimization.
Area of Science:
- Computational biology
- Natural language processing in oncology
Background:
- Tumor genetic heterogeneity complicates personalized cancer medicine.
- Accurate prediction of patient drug response remains a significant challenge.
Purpose of the Study:
- To develop DrugBERT, a BERT-based framework for predicting antitumor drug efficacy.
- To enhance prediction accuracy by integrating topic modeling and drug efficacy-aware mechanisms.
Main Methods:
- DrugBERT utilizes Latent Dirichlet Allocation (LDA) topic embedding and a drug efficacy-aware attention mechanism.
- Long-range dependencies in clinical text are captured using Long Short-Term Memory (LSTM).
- The SMOTE algorithm addresses data imbalance issues.
Main Results:
- DrugBERT showed strong performance on a non-small cell lung cancer dataset (958 patients).
- The model achieved a 3% AUC improvement on an independent bowel cancer dataset (266 patients), demonstrating robust generalization.
Conclusions:
- DrugBERT accurately predicts antitumor drug efficacy using clinical text.
- The model's strong generalization capability supports its potential in optimizing personalized cancer therapy.
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...
01:28Structure-Activity Relationships and Drug Design
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
02:57Targeted Cancer Therapies
There are several types of targeted therapies against...