Data Model

Metadata Structure

The DCIC, with input from different 4DN Network Working groups, has defined a metadata structure to describe:

• biological samples
• experimental methods
• data files
• analysis steps
• and other pertinent data.

The framework for the the metadata structure is based on the work of ENCODE DCC.

The metadata is organized as objects that are related with each other. An overview of the major objects is provided in the following slides.

Implementation

Our model defines a schema for discrete objects by type (e.g. experiment or file) and provides a set of fields to describe them (e.g. biosample or file size). Objects can be linked to each other and to the underlying data files. In addition to the fields and relations input by users, additional information is generated (e.g. accession) or calculated (a useful description based on entered fields), and appended to each item. This approach allows the creation of a rich and logical representation of the experiments performed by 4DN investigators.

In our database:

• The objects are stored in the JavaScript Object Notation format.
• The schemas for the different object types are described in JSON-LD format.
• The json schemas can be found here.

On our web pages:

• The descriptions of all the properties (stored and calculated) of any object can be seen on the profile page for that object.
• A profile page can be accessed using a url formatted as: https://data.4dnucleome.org/profiles/ eg. https://data.4dnucleome.org/profiles/experiment_hi_c.json