BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction
This work addresses the need for interpretable and model-agnostic data augmentation in biomedical research, particularly for drug combination discovery, though it is incremental as it builds on existing language model and data synthesis techniques.
The paper tackles the problem of limited interpretability and data leakage in using language models for drug combination prediction by proposing BLIAM, a literature-based data synthesis method that directly generates interpretable training data, and it substantially outperforms non-augmented and manual prompting approaches in a rigorous dataset setting.
Language models pre-trained on scientific literature corpora have substantially advanced scientific discovery by offering high-quality feature representations for downstream applications. However, these features are often not interpretable, and thus can reveal limited insights to domain experts. Instead of obtaining features from language models, we propose BLIAM, a literature-based data synthesis approach to directly generate training data points that are interpretable and model-agnostic to downstream applications. The key idea of BLIAM is to create prompts using existing training data and then use these prompts to synthesize new data points. BLIAM performs these two steps iteratively as new data points will define more informative prompts and new prompts will in turn synthesize more accurate data points. Notably, literature-based data augmentation might introduce data leakage since labels of test data points in downstream applications might have already been mentioned in the language model corpus. To prevent such leakage, we introduce GDSC-combo, a large-scale drug combination discovery dataset that was published after the biomedical language model was trained. We found that BLIAM substantially outperforms a non-augmented approach and manual prompting in this rigorous data split setting. BLIAM can be further used to synthesize data points for novel drugs and cell lines that were not even measured in biomedical experiments. In addition to the promising prediction performance, the data points synthesized by BLIAM are interpretable and model-agnostic, enabling in silico augmentation for in vitro experiments.