Biotech companies can differentiate already through the ability to process large amounts of data from different sources, i.e. to gather it, consolidate it, represent it in a comprehensible way and to deliver it safely. Some biotech companies already offer this as core service. Those ones who can validate the quality of data and extract the relevant information have a competitive advantage. In-memory technology even opens up more opportunities as different data formats including unstructured texts can be consolidated easily and quickly from various data sources.
Another way to positively stand out in the market is the ability to analyze raw data that biotech companies can get by collaborating with hospitals using smart
algorithms. To do this, a biotech company can pursue two possible strategies:
- Providing an added value by processing Big Data very rapidly through a comparably simple algorithm or
- Offering insights from relatively few data from various sources by using a highly complex algorithm.
Both approaches can be pushed by technology. Big Data solutions offer the necessary IT-capacities to process huge data masses in extremely short time periods as well as the capability to run data mining in an intelligent and quick way.
Examples indicating the future direction
There are many success stories to tell already how Big Data technology helped advance personalized medicine:
The National Center for Tumor Diseases (NCT) has gained new insights to fight cancer. The project “Medical Research Insights” which is based on the in-memory platform SAP HANA helps develop new personalized therapies. Employees can now capture enormous amounts of data per patient and analyze in real time. No matter if we are looking at medical reports, MRT results, genetic analysis and cancer registry data, all information come together in one central place. It can be found out very quickly which therapy has the greatest probability to work best at which patient.
„ProteomicsDB“, a database focusing on the human proteome that was jointly developed by one of Munich’s universities, Technische Universität München (TUM), and SAP supports scientists to explore the human proteome and conduct fundamental research. When building up this database, the human proteome was captured in an unprecedented degree of completeness, assessed in a structured way and pooled. Extremely high data volumes and various scattered data sources were coped with.
Alacris Theranostics has come up with an innovative Virtual Patient Platform that allows to accurately analyze the exact type of cancer of a specific patient and to find the best therapy. In the background molecular data of the patient and algorithms are used to derive the behavior of the tumor and to simulate the efficacy of different therapies. The complex mathematical model contains thousands of variables like genes, proteins and tests for every drug and every dose. With SAP HANA these simulations could be reduced to only a few minutes.
Stanford School of Medicine has provided a database of genetic predispositions that was combined with thousands of genomes from the 1,000 genomes project in SAP HANA to allow analyzing the data interactively. Some analyses could be accelerated by a factor of 17-600 and others were not even thinkable with traditional setups. Through this database many new opportunities arise, e.g. finding personalized therapies for chronic diseases like diabetes.
Mitsui Knowledge Industry (MKI) leveraged SAP HANA to not only extremely accelerate DNA sequencing, but also lower cost for DNA extraction and analysis from 1m USD to less than 1,000 USD. DNA analysis became affordable for many more patients through this.
Summing up, new architectures of databases and new IT infrastructures enable to overcome hurdles like complexities as well as high amounts of data and/or data sources and find answers to questions that were not possible to solve before. Further, saving time and computing capacity can enable pharma companies to make sound decision in earlier R&D stages than before, which means saving cost and time to market. Big Data technology also allows understanding illnesses that were not much investigated through clinical studies much better than before. For example, many clinical trials geographically concentrate on Europe which means other regions are currently underrepresented. Big Data solutions can help fill the gap by identifying suitable participants worldwide and process the data. They can also help shift focus of R&D from investigating how to deal with symptoms towards the root causes of a chronic disease and to further advance personalized medicine quicker.
This blog was written jointly by Emanuel Ziegler and me. I would like to express to thank Emanuel for all his great insights and support! The content of this blog was first published in a shorter version in German in goingpublic.de