Cancer biomarker research has become a data-intensive discipline requiring innovative approaches for data analysis that can combine traditional and data-driven methods. Significant leveraging can be done transferring methodologies and capabilities across scientific disciplines, such as planetary science and astronomy, each of which are grappling with and developing similar solutions for the analysis of massive scientific data.
Planetary science has unique challenges for data collected from instruments in space. These diverse data are processed through data-generation pipelines and delivered to international archives for analysis by the scientific community. To support the analysis, heterogeneous archives are rapidly adopting data science services to improve data access, use, and discovery worldwide  Modern artificial intelligence (AI)/machine learning (ML) capabilities are being applied to discover features in images—for example, in detecting dust storms on Mars—as well as other science phenomena through combining data across missions, instruments, and data types.
