high-performance computing


Precision medicine takes centre stage


Robert Roe reports from the SC16 conference, held in Salt Lake City, Utah, where he discovered that the use of


machine learning and HPC technology is driving advances in precision medicine


T


his year the plenary session of SC16, held in Salt Lake City, Utah, focused on the convergence of technologies that are enabling new initiatives around


precision medicine. Tis shiſt in the treatment of patients holds


the potential to open up new avenues in the fight against complex diseases such as cancer, where a single blanket treatment is not sufficient to treat the variety of mutations observed. Precision medicine aims to use a combination


of traditional clinical methods with genomic and proteomic data, as well as external data sources – such as from environmental and pollution records – to better prescribe drugs and treatments based on individual patient requirements. While the concept of precision medicine


has been around in some form for a number of years, it is now widespread due to the availability and falling cost of obtaining genomic data, a convergence of rapidly maturing technologies such as machine learning and big data analytics – all combined using HPC hardware.


www.scientific-computing.com l


The war on cancer Te session opened with a video featuring Dr Ernest Moniz, US secretary of energy, who stressed the importance of precision medicine in tackling hugely complex diseases such as cancer. ‘We have had a war on cancer going back many decades but we cannot say that we have cracked the problem,’ said Moniz. ‘Cancer Moonshot is using new tools, using a new level of activity and collaboration to hopefully get that solution that has been so elusive over the last half century.’ Te first speaker, Mitchell Cohen, director


of surgery at Denver Health Medical Center and University of Colorado School of Medicine professor, explained that current medical treatment and patient outcome are tied to the experience of a given physician and the capabilities and expertise of the supporting staff and facilities. In a perfect world, all patients would have


access to the same quality of care but, in reality, as Cohen stressed, it can be the experience of one ‘grizzled old clinician’ that ultimately leads to the best outcome for a patient.


@scwmagazine


‘Can we use computational modelling and


high performance computing and what we know about biology, physiology and the clinical trajectory of our patients to model that astute old clinician?’ Cohen explained that successful precision


medicine initiatives will lead to an improvement in patient care because computational modelling will be available to help inform clinicians – supplementing their knowledge and expertise. Te largest of these initiatives, the ‘Cancer


Moonshot’ project is the largest precision medicine initiative to date – funded by the US government to achieve a decade’s progress in cancer research in just five years.


SUCCESSFUL


PRECISION MEDICINE INITIATIVES WILL LEAD TO AN IMPROVEMENT IN PATIENT CARE


At the forefront of this research is the


collection of thousands of patient’s genetic data, which is incredibly important to exploring how the myriad of cancer mutations can affect patients. In the past cancer research has concentrated


on the most common mutations, as this provides treatment to the largest percentage of patients. However, this probability-based approach of


DECEMBER 2016/JANUARY 2017 19 ➤


photo.ua/Shutterstock.com


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32