Informatics
Unlocking clinical trial data to uncover new therapeutic opportunities key considerations and best practices
This article discusses opportunities, challenges and best practices in leveraging infrastructure excellence and AI to unlock the value of early or inconclusive clinical trial data. The goal... driving stronger biomarker-based insights and decisions and helping to advance new cures and treatment approaches.
A
s we all know, data is increasingly king in our information-driven world and organi- sations that learn how to turn mega infor-
mation into informed strategies are creating true sea changes in their industries. The opportunity to harness the power of data in new and exciting ways is also moving increasingly into life sciences. In drug discovery, for example, AI can now be
employed to mine the mountains of siloed and under-utilised data from early or inconclusive clin- ical trials. Having this capability helps feed the increasing demand for genotypic and phenotypic data, leads to deeper and faster bio-marker informed insights and helps support the develop- ment of new approaches and cures. Achieving this can seem a herculean task, but there
are growing examples of success and best practices around data management, organisational rigour and combining the best of science and technology domain expertise to meet the key challenges posed.
New data insights propel new thinking The higher volume and variety of data being gen- erated in our labs certainly brings more data man- agement complexity, but it also brings greater potential for improving the success of clinical trials by better leveraging biomarker-driven science. For example, routinely-collected biomarker or
Drug Discovery World Fall 2019
assay data is now being used to pre-define patient trial subsets around shared, common disease aeti- ology or molecular profiles. This approach is yield- ing results and appears to be compelling regulatory authorities, such as the US FDA, to encourage the use of technologies such as advanced analytics for next-generation sequencing and high throughput screening to identify those patients that could ben- efit most from emerging therapies. The highly-effective Herceptin® drug, which tar-
gets 15-30% of breast cancer patients whose molecular profile indicates higher quantities of the HER2 protein1, and Merck’s Keytruda® drug, are both excellent illustrations of the value of mining clinical trial data to make new advances. The Keytruda® offering was originally investi-
gated to control the immune response in patients with autoimmune disease. In 2009, Merck’s Keytruda® (pembrolizumab) compound was shelved, but promising results from a competitive later-stage compound prompted Merck to take another look at the Keytruda® compound for lung cancer. Stringent selection of patient cohorts using the biomarker-based analytics that resulted, allowed Merck to speed up the drug’s approval2. The Keytruda® offering is indeed a compelling
illustration of the therapeutic value and commercial opportunity that can come from ‘decoding’ failed
9
By David Wang, Masha Hoffey and Dr Simone Sharma
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 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
