Uniform set of tag SNPs for distributed learning.

[mikeDTI]

Please make sure that this is a feature request.

System information

• GenoML version (you are using): > 1.03
• Are you willing to contribute it (Yes/No): yes

Describe the feature and the current behavior/state.
Mike will make a uniform set of easily imputable tag SNPs to help with feature selection in distributed learning environments across data silos.

Will this change the current api? How?
Additional download / filter.

Who will benefit with this feature?
Anyone running distributed learning with common SNPs.

Any Other info.
Pending as part of new "neuroGlobo" array project.
Based on TopMed and implemented with TagIt, but will also include N370S and G2019S because Parkinson's disease PoC.
Wojcik-ImputationAwareTagSNPSelection.pdf

[mikeDTI]

Thinking we just make this into NBA/GDA SNPs that tag > 2 population ancestries well?

[m-makarious]

We could consider an additional directory with useful files such as this and perhaps PRS betas, GWAS summary stats in the correct format, among others?