Skip to Main content Skip to Navigation
Conference papers

SPI-DNA: End-to-end Deep Learning Approach for Demographic History Inference

Théophile Sanchez 1 Guillaume Charpiat 1 Flora Jay 2, 3, 1
1 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, Inria Saclay - Ile de France
2 BioInfo - LRI - Bioinformatique (LRI)
LRI - Laboratoire de Recherche en Informatique
Abstract : Recent methods for demographic history inference have achieved good results, avoiding the complexity of raw genomic data by summarizing them into handcrafted features called expert statistics. Here we introduce a new approach 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 expert 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 by geneticists for the inference of two demographic descriptor values while using less data.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01679385
Contributor : Flora Jay <>
Submitted on : Tuesday, January 9, 2018 - 7:19:21 PM
Last modification on : Tuesday, April 21, 2020 - 1:08:35 AM

Identifiers

  • HAL Id : hal-01679385, version 1

Citation

Théophile Sanchez, Guillaume Charpiat, Flora Jay. SPI-DNA: End-to-end Deep Learning Approach for Demographic History Inference. Paris-Saclay Junior Conference on Data Science and Engineering, Sep 2017, Orsay, France. ⟨hal-01679385⟩

Share

Metrics

Record views

319