Back to Africa with Deep Learning and Whole Genomes

[Angela]

See:
https://www.biorxiv.org/content/10.1101/2020.12.10.419069v1

"[h=1]Revisiting the Out of Africa event with a novel Deep Learning approach[/h][FONT=hwicons !important] View ORCID ProfileFrancesco Montinaro, Vasili Pankratov, [FONT=hwicons !important] View ORCID ProfileBurak Yelmen, [FONT=hwicons !important][/FONT] View ORCID ProfileLuca Pagani, [FONT=hwicons !important][/FONT] View ORCID ProfileMayukh Mondal"

"[/FONT][FONT=&quot]Anatomically modern humans evolved around 300 thousand years ago in Africa. Modern humans started to appear in the fossil record outside of Africa about 100 thousand years ago though other hominins existed throughout Eurasia much earlier. Recently, several researchers argued in favour of a single out of Africa event for modern humans based on whole-genome sequences analyses. However, the single out of Africa model is in contrast with some of the findings from fossil records, which supports two out of Africa, and uniparental data, which proposes back to Africa movement. Here, we used a novel deep learning approach coupled with Approximate Bayesian Computation and Sequential Monte Carlo to revisit these hypotheses from the whole genome sequence perspective. Our results support the back to Africa model over other alternatives. We estimated that there are two successive splits between Africa and out of African populations happening around 60-80 thousand years ago and separated by 12-13 thousand years. One of the populations resulting from the more recent split has to a large extent replaced the older West African population while the other one has founded the out of Africa populations."


Razib Khan's take:
[/FONT]https://www.gnxp.com/WordPress/2020/12/12/back-to-africa-migration-deep-learning/?utm_source=dlvr.it&utm_medium=twitter&utm_campaign=back-to-africa-migration-deep-learning

[h=1]Back To Africa Migration & Deep Learning[/h]POSTED ON DECEMBER 12, 2020 BY RAZIB KHAN

Revisiting the Out of Africa event with a novel Deep Learning approach:

Anatomically modern humans evolved around 300 thousand years ago in Africa. Modern humans started to appear in the fossil record outside of Africa about 100 thousand years ago though other hominins existed throughout Eurasia much earlier. Recently, several researchers argued in favour of a single out of Africa event for modern humans based on whole-genome sequences analyses. However, the single out of Africa model is in contrast with some of the findings from fossil records, which supports two out of Africa, and uniparental data, which proposes back to Africa movement. Here, we used a novel deep learning approach coupled with Approximate Bayesian Computation and Sequential Monte Carlo to revisit these hypotheses from the whole genome sequence perspective. Our results support the back to Africa model over other alternatives. We estimated that there are two successive splits between Africa and out of African populations happening around 60-80 thousand years ago and separated by 12-13 thousand years. One of the populations resulting from the more recent split has to a large extent replaced the older West African population while the other one has founded the out of Africa populations.
​

"This is basically Dienekes Pontikos’ old Afrasian/Paleo-African Hypothesis. These models are not crazy. We have so much data there is room for them. The problem with “Deep Learning” is that we’re not too familiar with these methods, and who knows how to get a sense whether the results are just crazy artifacts? Even the authors say “it is still challenging to measure the significance of a prediction performed by NN, given that it is a black-box approach.”"

Petty response.

[/FONT]