Related Experiment Video
Updated: Jul 2, 2025

Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations
Published on: December 7, 2021
Computationally efficient demographic history inference from allele frequencies with supervised machine learning.
Linh N Tran1,2, Connie K Sun2, Travis J Struck2
1Genetics Graduate Interdisciplinary Program, University of Arizona, Tucson, AZ, USA.
We developed donni, a new neural network method for inferring population demographic history from genomic data. Donni offers faster and computationally efficient demographic inference with accuracy comparable to existing methods.
Area of Science:
- Population genetics
- Genomic data analysis
- Computational biology
Background:
- Inferring population demographic history from genomic data is crucial across scientific fields.
- The dadi method, based on allele frequency spectrum (AFS) and maximum composite likelihood optimization, is widely used but computationally intensive.
- There is a need for more efficient demographic inference methods.
Conclusions:
- Donni offers a more efficient alternative for demographic history inference.
- Supervised machine learning presents a promising approach for developing sustainable and computationally efficient demographic inference tools.
- This advancement facilitates broader application of genomic data in understanding population dynamics.
Related Concept Videos
Hardy-Weinberg Principle
What is Population Genetics?
Mutation, Gene Flow, and Genetic Drift
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Genetic Drift
Evolutionary Relationships through Genome Comparisons

