DRIVE: Machine Learning to Identify Drivers of Cancer with High-Dimensional Genomic Data & Imputed Labels
This addresses a key challenge in precision oncology for identifying rare driver mutations, though it appears incremental as it combines existing approaches.
The paper tackles the problem of identifying cancer driver mutations, particularly rare low-frequency ones, by proposing a novel combination method that integrates statistical modeling with functional-impact approaches. The method outperforms state-of-the-art methods in precision and achieves comparable AU-ROC performance.
Identifying the mutations that drive cancer growth is key in clinical decision making and precision oncology. As driver mutations confer selective advantage and thus have an increased likelihood of occurrence, frequency-based statistical models are currently favoured. These methods are not suited to rare, low frequency, driver mutations. The alternative approach to address this is through functional-impact scores, however methods using this approach are highly prone to false positives. In this paper, we propose a novel combination method for driver mutation identification, which uses the power of both statistical modelling and functional-impact based methods. Initial results show this approach outperforms the state-of-the-art methods in terms of precision, and provides comparable performance in terms of area under receiver operating characteristic curves (AU-ROC). We believe that data-driven systems based on machine learning, such as these, will become an integral part of precision oncology in the near future.