Informatics


Patients receive Targeted


Therapies


Translational Research Biomarkers


Basic Research Clinical Research Phase I Phase II Phase IIIII Failed Clinical Trials


Biomarkers help identify the right trial subjects


Source: PerkinElmer, Inc


90% of clinical trials fail. Applying biomarkers to failed trial data helps identify the hidden treasure of promising drug candidates


more effective for them


Pha hase IV


or inconclusive clinical trial data. The ability to per- form retrospective analysis on compound data that has been demoted in priority or placed on an out- license list not only in this case delivered the ‘President’s Drug’, but also led to approval for use in other cancers where treatment is based on a com- mon biomarker versus the anatomical location of a tumour’s origin2,3.


Top challenges in addressing an ailing pipeline with technology Current technological advances – whether infras- tructure-oriented like data storage or around Artificial Intelligence systems – are indeed giving us an unprecedented opportunity to release scientific insights from siloed resources and accelerate the path towards more successful clinical trials. While there is a consensus in the industry on the


benefits of doing this, the challenges can seem daunting. These include: 1) Dealing with high volume, disparate data in cor- porate data landfills in a scalable, supportable way. 2) Harmonising extracted, relevant data to then perform effective cross-study analysis. 3) Ensuring effective interactive collaboration across teams (within a company and between com- panies/academic collaborators etc). 4) Staying in lock-step with scientists’ needs by iden- tifying what is important in their analysis and then providing ways to intuitively visualise key data. Even before we think about these issues, howev-


er, it is essential to identify and detail the right problem(s) we want to solve before any specific technologies are considered, as biology is complex and insightful analysis can be challenging. Generally, sponsors appreciate that the key to harnessing therapeutic value in an avalanche of


10


data requires them to be strategic about implement- ing a system that will address infrastructure and analysis needs so that scientific insights are easily understood and actionable by key decision makers. Thanks to the pioneering work that has been


carried out in other industries by consumer giants such as Amazon and Google, we are now equipped with some solid advances to deal with these chal- lenges in the pharma discovery space. Best practices are now being established to facili-


tate data aggregation for cross-study analysis, be it via staging or federated data; creating robust yet flex- ible models to harmonise datasets; deploying strate- gies to ensure data is secure by design versus by com- pliance; or, creating purpose-built workflow solu- tions that enable analytics for specific end-users without overtaxing highly-specialised data scientists. Conventional statistical tests work by fitting data


into a mathematic model for statistical inference and this can be problematic for complex, high- dimensional data, and especially with historical datasets with many underlying assumptions. Generalised algorithms reliant on a minimal set of assumptions can be much more useful in finding patterns in complex high-dimensional data4. Such applications, known as Machine Learning (ML), can help us better leverage and make sense of these data without compromising on the scientific value5.


Discovering the hidden potential of data with Machine Learning (ML) High throughput platforms like high content screening (HCS) and next-generation sequencing (NGS) provide data types with millions of features, in which only a small proportion have established clinical significance. With Artificial Intelligence (AI) systems going


Drug Discovery World Fall 2019


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