MOTIVATION: Whole-genome sequencing has revolutionized biosciences by providing tools for constructing complete DNA sequences of individuals. With entire genomes at hand, scientists can pinpoint DNA fragments responsible for oncogenesis and predict patient responses to cancer treatments. Machine learning plays a paramount role in this process. However, the sheer volume of whole-genome data makes it difficult to encode the characteristics of genomic variants as features for learning algorithms. RESULTS: In this article, we propose three feature extraction methods that facilitate classifier learning from sets of genomic variants. The core contributions of this work include: (i) strategies for determining features using variant length binning, clustering and density estimation; (ii) a programing library for automating distribution-based feature extraction in machine learning pipelines. The proposed methods have been validated on five real-world datasets using four different classification algorithms and a clustering approach. Experiments on genomes of 219 ovarian, 61 lung and 929 breast cancer patients show that the proposed approaches automatically identify genomic biomarkers associated with cancer subtypes and clinical response to oncological treatment. Finally, we show that the extracted features can be used alongside unsupervised learning methods to analyze genomic samples. AVAILABILITY AND IMPLEMENTATION: The source code of the presented algorithms and reproducible experimental scripts are available on Github at https://github.com/MNMdiagnostics/dbfe. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This paper aims to explore popular CNN architectures for the generation of patient-specific dose distributions for Volumetric Modulated Arc Therapy (VMAT) radiotherapy satisfying clinical dose-volume constraints. Only organs at risk (OARs) and planning target volume (PTV) segmentations are required as input. The outcome of the research is selecting the optimal network architecture and assessing training parameters. The U-net,$\mathbf{ResNet}+\mathbf{U-net},\mathbf{ResNet}+\mathbf{PSPNet}$networks are analyzed. The$\mathbf{Resnet}+\mathbf{U-net}$model was chosen as the most suited to the task. The similarity measures such as mIoU and mDice coefficient as well as the dose-volume constraints in PTV and selected OARs are evaluated. The results confirm that the$\mathbf{Reset}+\boldsymbol{U}$-net network is capable of generating patient-specific dose distribution and can be used as a valuable assistance during clinical radiotherapy planning procedures.