photo: istockphoto

According to the World Health Organization, 11 million people are diagnosed with cancer every year. Nearly 8 million die. It’s estimated that, by 2020, the annual number of cancer diagnoses will exceed 16 million. Chances are, you will know cancer up close.

SAP HANA, SAP AG’s implementation of in-memory database technology, marked its first birthday last week. The company hopes it is the first of many such celebrations, both because SAP HANA is key to its strategy and because, like the American Cancer Society, which dubs itself the official sponsor of birthdays,  SAP HANA is helping doctors develop effective treatments against the disease.

Cancer is a generic description of more than 100 conditions related to the uncontrolled growth of cells in the body. Whether inherited or induced by environmental factors, growth of these atypical cells is associated with multiple and specific changes in DNA – changes that are not completely understood. In other words, we don’t know exactly what causes cancer. But, to save lives, we may not need to.

A method known as Translational Cancer Research (TCR) uses information gathered in laboratory investigations, clinical trials, and population studies to develop clinical applications that reduce cancer incidence, morbidity, and mortality – independent of our knowledge of the disease’s natural history. In TCR, researchers analyze data generated from DNA gene sequencing (imaging and “interrogating” human genomes to extract meaningful patterns) and proteomics (the study of the structures and function of proteins). These findings are integrated with clinical data generated when cancer patients undergo diagnostic and therapeutic procedures like imaging studies, blood work, and biopsies. Researches use the amalgamated data to better understand the underlying mechanisms of cancer, and to guide development of preventions and interventions optimized for each patient’s genetic and clinical profile – true, personalized medicine.The enormity of this research is staggering. Consider the amount of raw data collected: Each individual’s genome has 3 billion base pairs. In full gene sequencing, this translates into an average of 1.5 gigabytes of data per person. On average, scientists fully sequence the genome of 167 individuals per week, generating 250 gigabytes of images. Identifying patterns can expand the data by a factor of 20. To put that in perspective, every two weeks researchers gather the same amount of data (10 terabytes) that contains the entire Unites States Library of Congress archive – 130 million items occupying 530 miles of bookshelves. Add to that the massive amount of information generated every day by clinicians performing diagnostic and therapeutic procedures on millions of patients. This vast store of data must be coded, parsed, and analyzed to find meaningful patterns and, ultimately, more effective cancer treatments.

SAP HANA’s in-memory technology makes this kind of analysis possible. By storing and processing enormous datasets in main memory rather than on a hard disk, researchers can process and analyze huge amounts of data extremely quickly. “It took 15 years and $3 billion to complete the first genome,” says George Church, professor of genetics at Harvard Medical School and director of the Center for Computational Genetics, “It now takes one computer only a few weeks and costs $5,000. This drop in cost is mainly due to radically new technologies.”

SAP HANA Oncolyzer, a mobile data analysis application powered by the SAP in-memory backend, makes use of these advances, enabling researchers to quickly access vast amounts of structured and unstructured data, wherever they happen to be. What one took “supercomputers” hours or days to evaluate can now be processed in a few seconds, on an iPad.“What would previously take an oncologist three to four days to analyze can now be done in two to three seconds, saving critical time and allowing researchers to move forward with therapies, rather than waiting days for the results,” explains Dr. Alexander Zeier of the Hasso Plattner Institute, where the HANA Oncolyzer was developed in conjunction with the SAP Innovation Center in Potsdam, Germany. “In the clinical setting, physicians can (use the application) to select  various criteria such as cancer type, stage of cancer, treatment, and age and sex of the patient, and create and analyze what-if scenarios. This helps clinicians gain a better understanding of their patients, resulting in more targeted therapy and earlier diagnosis.”

Improving cancer outcomes is just one of many early successes for SAP HANA. Just a year since it became generally available, SAP HANA powers 33 solutions serving more than 350 customers, including Colgate, Medtronic, T-Mobile, Groupon, and Lenovo, and serves 64,000 end users.  According to SAP Executive Board Member Vishal Sikka, it also represents the company’s intellectual renewal. “In January, SAP HANA became the fastest growing technology in SAP history,” he says, “Not only is SAP HANA revolutionizing our industry, it has also shown the power of technology to transform lives. Customers have been calling me from all over the world talking about the power of SAP HANA. This anniversary of SAP HANA is about celebrating innovation and the result of SAP HANA renewing how we think and how we work.”

According to Sikka, the next wave of SAP HANA innovation will further transform healthcare with new applications in the areas of genome analysis. The banking and utilities industries will also be touched with applications addressing energy management and the “unbanked,” a term used by the US Federal Deposit Insurance Corporation (FDIC) to describe the growing population of people without an account at a bank or other financial institution.

“I am incredibly excited for the next year and for the future innovations SAP HANA will bring,” says Sikka.