Welcome to the 1000 Genomes Project ancestry prediction competition.

Geneticists identified locations in the human genome that can assess an individual's ancestry, called ancestry-informative single nucleotide polymorphisms (AISNPs). These locations, denoted by rsid numbers, display ancestry-specific variation. For example, at location [rs3737576](https://www.ncbi.nlm.nih.gov/snp/rs3737576), 32% of individuals from the 1000 Genomes Project who were assigned American ancestry have a C allele, while the study-wide frequency of the C allele was only 8%.

There are many locations like this across the human genome. AISNPs from two peer-reviewed publications are available in this competition. [Kidd et al.](https://pubmed.ncbi.nlm.nih.gov/24508742/) identified 55 AISNPs, and [Seldin et al.](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3073397/) identified 128 AISNPs with varying degrees of discriminatory power. You can learn more about original ancestry classifications from the 1000 Genomes Project [here](https://www.internationalgenome.org/category/population/) and [here](https://www.internationalgenome.org/data-portal/population).

The dataset in this competition contains alleles from the 1000 Genomes Project for 2,504 individuals across 183 AISNPs.

**Goal:** This competition aims to use AISNPs from the 1000 Genomes Project to predict individuals' ancestry. 
Collaborating with the winner to incorporate the winning model into the [ezancestry](https://github.com/arvkevi/ezancestry) Python library would be fun.

The term "ancestry" can be confusing, especially in genetics. I encourage you to read more about the term [here](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7082057/).

This competition is not affiliated with the 1000 Genomes Project.