About

Evolutionary genomics and population genetics investigate patterns of genetic diversity between species or between populations within a species and play a fundamental role in many aspects, from theoretical facets of evolution to practical ones, such as conservation genetics and biomedical sciences.

Methodologies have always been a strong interest of the community, from the development of mathematical models to the design of statistical inference tools, leading to numerous biological discoveries. These developments helped to adapt very quickly to the continuous influx of data, which has not only dramatically increased in quantity but also keeps changing in terms of quality and type.

Among the methodological frameworks, machine learning has emerged as a promising way of analysing large and complex datasets. The application of AI, and particularly deep learning, to evolutionary genomics is still in its infancy while showing promising initial results. It is currently applied to a variety of tasks, such as the inference of demographic history, ancestry, natural selection, phylogeny, species delimitation and diversification.

However, machine learning methods in evolutionary genomics and population genetics face unique challenges, including identifying appropriate assumptions about the evolutionary process and how to simulate it, and identifying the best ways to handle sequences, sequence alignments, phylogenetic trees, or additional information, such as geographical maps, temporal labels and environmental covariates. Overcoming these challenges requires a collaborative effort. The goal of this conference is to foster this effort by allowing interested researchers to meet and share their work.

We held a previous edition of LEGEND in Heraklion in 2024.

 

 

Keynote speakers

anneFlorence_300.jpg 

Anne-Florence Bitbol, EPFL

Anne-Florence Bitbol studied physics at ENS Lyon and Université Paris-Diderot in France, and obtained her PhD in 2012, advised by Jean-Baptiste Fournier. As an HFSP postdoctoral fellow, she then joined the Biophysics Theory group at Princeton University (USA), led by William Bialek, Curtis Callan and Ned Wingreen. In 2016, she became an independent CNRS researcher at Sorbonne Université in Paris, before joining EPFL as a tenure-track assistant professor in early 2020. She is broadly interested in understanding biological phenomena through physical concepts and mathematical and computational tools, and she investigates the impacts of optimization and historical contingency in biological systems, from the molecular to the population scale. In particular, she is interested in coevolution-based inference from protein sequence data, using methods based on statistical physics, information theory, and protein language models. 

Tentative title: Coevolution-aware language models
claudia_300.jpg 

Claudia Solís-Lemus, University of Wisconsin-Madison

Claudia Solís-Lemus is an assistant professor at the Wisconsin Institute for Discovery and the Department of Plant Pathology at the University of Wisconsin-Madison. Originally from Mexico City, she did her Undergraduate degrees in Actuarial Sciences and Applied Mathematics at ITAM. Then, she did a MA in Mathematics and a PhD in Statistics at the University of Wisconsin-Madison.
 

Tentative title: The good, the bad and the ugly of deep learning in phylogenetic inference
burak_300.jpeg  Burak Yelmen, University of Tartu
 
Burak Yelmen is a research fellow at the Institute of Genomics, University of Tartu. His research focuses on modelling human genomes with generative neural networks. He is also interested in interpretable deep learning methodologies for complex trait genetics.
 
Tentative title: A perspective on generative neural networks in genomics with applications in synthetic data generation

 

 

Key dates

Registration opens: May 20th 2025

Abstract submission opens (oral presentations and posters): August 25th 2025

Abstract submission deadline for oral presentations: September 22nd 2025 AoE

Abstract submission deadline for posters: October 1st 2025 AoE

(if your oral presentation is rejected we will automatically consider your submission for a poster, no need for a separate submission)

Decision : October 6th 2025

Registration Deadline: October 17th 2025 AoE (or upon reaching 80 registrations)

Conference: December 8th - 12th

Even if the conference is booked before the registration deadline, we will be saving one registration slot for speakers of accepted oral presentations.

If you are planning to attend whether or not you are selected for a presentation, we invite you to register as soon as possible. 

Practical information

The registration fees will be around 600€ (exact rate TBD). They cover:

  • Housing and all meals from the evening of December 8th until the morning of December 12th (4 nights),
  • Transportation by bus between Aussois and Lyon airport (LYS) or train station (Part Dieu),
  • An accessible hike in the Alps and an alternative more quiet social event (TBD),
  • Participation to the conference.

The conference itself will start in the morning of December 9th, and close on the evening of December 11th.

We offer a limited number of free registrations to help include authors of accepted oral presentations and posters who could not attend otherwise. If you would like to apply, please send an email to legend2025@scienceconf.org.

 

 

Organizers

 

 

Code of conduct

(freely adapted from NeurIPS and ICML)

The LEGEND conference aims at gathering the international community in machine learning for evolutionary genomics, in order to foster an exchange of ideas and a respectful scientific debate.

Our objective is that anyone interested by these events can attend them comfortably and in particular without experiencing any form of harassement or discrimination (racist, sexist, homophobic, transphobic or ableist).

Any witness or victim of such incidents or any other non-professional behavior can get in touch with the organizers. All complaints will be handled as confidentially as possible.

 

 

Sponsors
Online user: 2 Privacy | Accessibility
Loading...