Abstract

The automation of important aspects of scientific data analysis would significantly accelerate the pace of science and innovation. Although there has been a lot of work done towards that automation, the hypothesize-test-evaluate discovery cycle is still largely carried out by hand by researchers. This introduces a significant human bottleneck, which leads to inefficiencies, potential errors, and incomplete explorations of the hypothesis and data analysis space. We introduce a novel approach to automate the hypothesize-test-evaluate discovery cycle with an intelligent system that a scientist can task to test hypotheses of interest against a data repository. Our approach captures three types of data analytics knowledge: 1) common data analytic methods represented as semantic workflows; 2) meta-analysis methods that aggregate those results, represented as meta-workflows; and 3) data analysis strategies that specify for a type of hypothesis what data and methods to use, represented as lines of inquiry. Given a hypothesis specified by a scientist, appropriate lines of inquiry are triggered, which lead to retrieving relevant datasets, running relevant workflows on that data, and finally running meta-workflows on workflow results. The scientist is then presented with a level of confidence on the initial hypothesis, a revised hypothesis, and possibly with new hypotheses. We have implemented this approach in the DISK system, and applied it to multi-omics data analysis.

Metadata

publication

Proceedings of the Fourth Annual Conference on Advances in Cognitive Systems …, 2016

year

2016

publication date

2016/6

authors

Yolanda Gil, Daniel Garijo, Varun Ratnakar, Rajiv Mayani, Ravali Adusumilli, Hunter Boyce, Parag Mallick

link

https://dgarijo.com/papers/acs2016.pdf

resource_link

https://dgarijo.com/papers/acs2016.pdf

journal

Proceedings of the Fourth Annual Conference on Advances in Cognitive Systems (ACS)

volume

2

pages

4