Conceptual Modeling of Human Genome: Integration Challenges

Abstract. Multidimensional data is systematically analysed at multiple granularities by applying aggregate and disaggregate operators (e.g., by the use of OLAP tools). For instance, in a supermarket we may want to predict sales of tomatoes for next week, but we may also be interested in predicting sales for all vegetables (higher up in the product hierarchy) for next Friday (lower down in the time dimension). While the domain and data are the same, the operating context is different. We explore several approaches for multidimensional data when predictions have to be made at different levels (or contexts) of aggregation. One method relies on the same resolution, another approach aggregates predictions bottom-up, a third approach disaggregates predictions top-down and a final technique corrects predictions using the relation between levels. We show how these strategies behave when the resolution context changes, using several machine learning techniques in four application domains.

show abstract

“…structured in 20 (numerical and nominal) attributes [20]. Data goes from years 1970 to 2012 and the output variable is the number of variations.…”

Section: Experimental Setting and Resultsmentioning

confidence: 99%

Multidimensional Prediction Models When the Resolution Context Changes

Martínez-Usó

Hernández-Orallo

2015

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

show abstract

“…To achieve what we refer to as the "Smart Data" perspective presented in this article, we need a conceptual structure in which to store each piece of genomic data in the right place, regardless of the data's origin. To accomplish this goal, we propose the use of the Conceptual Schema of the Human Genome (CSHG) [17], [18].…”

Section: The Conceptual Schema Of the Human Genomementioning

confidence: 99%

Smart Data for Genomic Information Systems: the SILE Method

Palacio

López

2018

CSIMQ

View full text Add to dashboard Cite

During the last two decades, data generated by Next Generation Sequencing Technologies have revolutionized our understanding of human biology and improved the study on how changes (variations) in the DNA are involved in the risk of suffering a certain disease. A huge amount of genomic data is publicly available and frequently used by the research community in order to extract meaningful and reliable gene-disease relationships. However, the management of this exponential growth of data has become a challenge for biologists. Under such a Big Data problem perspective, they are forced to delve into a lake of complex data, spread in over one thousand heterogeneous repositories, represented in multiple formats and with different levels of quality; but when data are used to solve a concrete problem only, a small part of that "data lake" is really significant; this is what we call the "smart" data perspective. By using conceptual models and the principles of data quality management, adapted to the genomic domain, we propose a systematic approach called the SILE method to move from a Big Data to a Smart Data perspective. The aim of this approach is to populate an Information System with genomic data which are sufficiently accessible, informative and actionable to extract valuable knowledge.

show abstract