iiinova — where your digital self keeps evolving

Reposted by Luc Blassel

Laurent Jacob @laurentjacob.bsky.social · 03/06/2026

The video recordings of the legend 2025 conference held last December on machine learning for evolutionary genomics are now online ! Feel free to have a look if you missed the conference. www.canal-u.tv/chaines/lisn...

1107

Luc Blassel @lblassel.bsky.social · 16/10/2025

We’re very excited to finally share our latest work: Phyloformer 2, a deep end-to-end phylogenetic reconstruction method: arxiv.org/abs/2510.12976 Using neural posterior estimation, it outperforms Phyloformer 1 and maximum-likelihood methods under simple and complex evolutionary models. 🧵1/17

A three panel figure describing the Phyloformer 2 (PF2) method. The top panel describes the architecture of the PF2 neural network. The bottom right panel describes how PF2 estimates the posterior probability of a tree given a sequence emebdding at train time. The bottom left panel describes how PF2 samples trees from the learned posterior at inference time.

182

Reposted by Luc Blassel

mariemorel.bsky.social @mariemorel.bsky.social · 28/05/2025

La vidéo sur notre projet de recherche est en ligne ! Merci encore à toute l'équipe d'animal pensant pour leur incroyable travail ! D’où viennent les fleurs ? lejournal.cnrs.fr/videos/dou-v...

lejournal.cnrs.fr

D’où viennent les fleurs ?

Les fleurs dominent le monde végétal, mais leur origine reste un mystère. Dans cette vidéo en partenariat avec Le Monde, des chercheurs du CNRS tentent de remonter à l’ancêtre commun de toutes les pla...

051

Reposted by Luc Blassel

Laurent Jacob @laurentjacob.bsky.social · 24/06/2024

All this work was done by Luca Nesterenko and @lblassel.bsky.social , assisted by P. Veber, Bastien Boussau and myself. The code and data are available at github.com/lucanest/Phy... Please share if you find this interesting, and we welcome your feedback :)

A sketch summarizing the entire Phyloformer process.

011

Reposted by Luc Blassel

Laurent Jacob @laurentjacob.bsky.social · 24/06/2024

We just released a preprint for Phyloformer, a likelihood-free inference method for phylogenetic reconstruction: biorxiv.org/content/10.1... Faster than distance methods like neighbor joining, it outperforms maximum likelihood methods under complex models of sequence evolution. 🧵

132