Artificial 23andMe Data for Software Development

In this post, we are going deeper into the Dynamic Data project, looking at the 23andMe dynamic data (library available here on GitHub and at NPM). Opening the library, you’ll see there are one type of data files: RawDataObject
Learn more about dynamic data generators and the benefits of artificial data in software development.

About the data source

23andMe is a biotechnology company that provides an Ancestry, Health and Traits service that requires the customer to send their DNA for analysis. 23andMe also provides a paid-for membership which grants ongoing access to enhanced premium features and reports. 
Ancestry Service:

• Automatic Family Tree
• Connect with DNA relatives
• Ancestry Composition - where user's DNA comes from
• A detailed granular view of ancestry over the world 
• Neanderthal Ancestry

Health Service: 

• Health Predisposition Reports
• Carrier Status Reports
• Wellness Reports
• ​Family Health History Tree

Traits Service:

• Disposition to Male Bald Spot
• Whether the user prefers sweet or salty
• Disposition to Widow’s Peak Hairline 
• Likelihood for fear of public speaking
• etc

Approach used

23andMe provides a data exporting services that allows the user to download their raw genotype data. A subset of such data was converted into JSON format to create a mockup file. A simple data model of these objects can be seen below. This mockup file makes up the 23andme-data package.

The 23andme-mockup package imports the aforementioned file and goes through each attribute of them generating artificial (new) data using proprietary functions, such as those found in the utils package.

For example, with the RawDataObject object:

Static RawDataObject Object

Artificial RawDataObject Object

Use Case Ideas

• Health/Diet Apps
• Avatar Visualization
• etc

Explore entirely new use cases

• Biomarkers of concern, through database lookup or machine learning efforts, to encourage a professional medical diagnosis
• Using your genetic data, construct an avatar with realistic similarities to the user
• Ancestry Journey - shows your ancestry through a timeline with a stylised person through the earliest recorded time to now. 
• Recommend food that works best with genetic profile
• Educational App which helps to reduce the complexity of the data and make it accessible to the user

Ideas to combine with some other data sources

Combine with similar Raw Genetic Data exports, like from Ancestry, to gain a greater scope at genetic data. Look at any discrepancies for further analysis. 

Combine with photo applications to generate a life-like model of the user, for instance genetic data can help provide data about hair (texture, baldness, etc) but cannot tell your hairstyle

Open-source data library

We welcome contributions and forks to this data set, and look forward to seeing what developers build in our Liberty. Equality. Data. Slack channel.

Considerations for next version/improvements

• Ensure that the rsid attribute only generates valid Reference SNP cluster ID (RSID) values that 23andMe works with
• Ensure that the position attribute generates valid values
• Ensure that the chromosome attribute generates valid values

Join our Slack community; Liberty. Equality. Data. - to ideate and collaborate with other app developers, designers, and our team.