End-to-End Deep Learning Approach for Demographic History Inference

Théophile Sanchez 1 Guillaume Charpiat 1 Flora Jay 2
1 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
2 BioInfo - LRI - Bioinformatique (LRI)
LRI - Laboratoire de Recherche en Informatique
Abstract : Recent methods for demographic history inference have achieved good results, circumventing the complexity of raw genomic data by summarizing them into handcrafted features called summary statistics [1, 3]. We developed a new approach based on deep learning that takes as input the variant sites found within a sample of individuals from the same population, and infers demographic descriptor values without relying on these predefined summary statistics. By letting our model choose how to handle raw data and learn its own way to embed them, we were able to outperform a method frequently used in population genetics for the inference of three out of seven demographic descriptor values of a scenario with a bottleneck and two expansions. This is still preliminary work and we are hopeful that future developments would allow us to tackle a broader range of demographic scenarios and outperform previous methods by developing more flexible artificial neural network architectures.
Document type :
Poster communications
Liste complète des métadonnées

https://hal.inria.fr/hal-01823543
Contributor : Flora Jay <>
Submitted on : Tuesday, June 26, 2018 - 10:40:44 AM
Last modification on : Tuesday, January 8, 2019 - 8:36:01 AM

Identifiers

  • HAL Id : hal-01823543, version 1

Citation

Théophile Sanchez, Guillaume Charpiat, Flora Jay. End-to-End Deep Learning Approach for Demographic History Inference. Human Evolution: Fossils, Ancient and Modern Genomes 2017, Nov 2017, Hinxton, Cambridge, United Kingdom. 〈hal-01823543〉

Share

Metrics

Record views

71