Machine learning and data mining frameworks for predicting drug response in cancer: An overview and a novel in silico screening process based on association rule mining.

A major challenge in cancer treatment is predicting the clinical response to anti-cancer drugs on a personalized basis. The success of such a task largely depends on the ability to develop computational resources that integrate big "omic" data into effective drug-response models. Machine learning is both an expanding and an evolving computational field that holds promise to cover such needs. Here we provide a focused overview of: 1) the various supervised and unsupervised algorithms used specifically in drug response prediction applications, 2) the strategies employed to develop these algorithms into applicable models, 3) data resources that are fed into these frameworks and 4) pitfalls and challenges to maximize model performance. In this context we also describe a novel in silico screening process, based on Association Rule Mining, for identifying genes as candidate drivers of drug response and compare it with relevant data mining frameworks, for which we generated a web application freely available at: https://compbio.nyumc.org/drugs/. This pipeline explores with high efficiency large sample-spaces, while is able to detect low frequency events and evaluate statistical significance even in the multidimensional space, presenting the results in the form of easily interpretable rules. We conclude with future prospects and challenges of applying machine learning based drug response prediction in precision medicine.

Localized Synchrotron Irradiation of Mouse Skin Induces Persistent Systemic Genotoxic and Immune Responses.

The importance of nontargeted (systemic) effects of ionizing radiation is attracting increasing attention. Exploiting synchrotron radiation generated by the Imaging and Medical Beamline at the Australian Synchrotron, we studied radiation-induced nontargeted effects in C57BL/6 mice. Mice were locally irradiated with a synchrotron X-ray broad beam and a multiplanar microbeam radiotherapy beam. To assess the influence of the beam configurations and variations in peak dose and irradiated area in the response of normal tissues outside the irradiated field at 1 and 4 days after irradiation, we monitored oxidatively induced clustered DNA lesions (OCDL), DNA double-strand breaks (DSB), apoptosis, and the local and systemic immune responses. All radiation settings induced pronounced persistent systemic effects in mice, which resulted from even short exposures of a small irradiated area. OCDLs were elevated in a wide variety of unirradiated normal tissues. In out-of-field duodenum, there was a trend for elevated apoptotic cell death under most irradiation conditions; however, DSBs were elevated only after exposure to lower doses. These genotoxic events were accompanied by changes in plasma concentrations of macrophage-derived cytokine, eotaxin, IL10, TIMP1, VEGF, TGFß1, and TGFß2, along with changes in tissues in frequencies of macrophages, neutrophils, and T lymphocytes. Overall, our findings have implications for the planning of therapeutic and diagnostic radiation treatments to reduce the risk of radiation-related adverse systemic effects. Cancer Res; 77(22); 6389-99. ©2017 AACR.