Pui, C.S.; Fumagalli, M.; Mathieson, S.
Python code for building and training a generative adversarial network for demographic inferences from genomic data
Cite this model code as:
Pui, C.S.; Fumagalli, M.; Mathieson, S. (2023). Python code for building and training a generative adversarial network for demographic inferences from genomic data. NERC EDS Environmental Information Data Centre. https://doi.org/10.5285/3ae572f6-4862-47ae-b4a0-4b9c496b5b54
Download/Access
PLEASE NOTE: By accessing or using this model code, you agree to the terms of the relevant licence agreement(s). You will ensure that this model code is cited in any publication that describes research in which the data have been used.
Publication of this model code by the EIDC does not signify any endorsement or approval. By accessing and using the resource, you acknowledge that it is entirely at your own risk and you are solely responsible for any loss or liability that may arise
Publication of this model code by the EIDC does not signify any endorsement or approval. By accessing and using the resource, you acknowledge that it is entirely at your own risk and you are solely responsible for any loss or liability that may arise
This model code is available under the terms of the Open Government Licence
https://doi.org/10.5285/3ae572f6-4862-47ae-b4a0-4b9c496b5b54
A collection of python and bash scripts to implement, train and deploy a generative adversarial network for population genetic inferences.
The networks have been tuned to be deployed to genomic data from Anopheles mosquitoes. However, the general framework can be applied to other species.
It requires the input data to be in Variant Call Format (VCF) format and the simulations need to be in msprime format.
The networks have been tuned to be deployed to genomic data from Anopheles mosquitoes. However, the general framework can be applied to other species.
It requires the input data to be in Variant Call Format (VCF) format and the simulations need to be in msprime format.
Publication date: 2023-12-08
View numbers valid from 08 December 2023 Download numbers valid from 20 June 2024 (information prior to this was not collected)
Formats
Python scripts, Bash scripts, R script
Provenance & quality
The methodology can be applied to up to two populations at the same time. The code uses the keras python package and the scripts have been tested via simulations. Inferences were tested using simulations with known output, and the power to infer the ground truth was recovered. Simulations can be performed using msprime or SLiM.
Licensing and constraints
This model code is available under the terms of the Open Government Licence
Cite this model code as:
Pui, C.S.; Fumagalli, M.; Mathieson, S. (2023). Python code for building and training a generative adversarial network for demographic inferences from genomic data. NERC EDS Environmental Information Data Centre. https://doi.org/10.5285/3ae572f6-4862-47ae-b4a0-4b9c496b5b54
Correspondence/contact details
Authors
Other contacts
Rights holder
Queen Mary University of London
Custodian
NERC EDS Environmental Information Data Centre
info@eidc.ac.uk
Publisher
NERC EDS Environmental Information Data Centre
info@eidc.ac.uk
Additional metadata
Keywords
demographic inference , generative adversarial network , population genetics
Funding
Natural Environment Research Council Award: NE/X009637/1
Last updated
06 January 2025 09:24