BioAI-rgUpcoming Talks
Find details about the next talks and what’s coming up.
(There are past talks below this section)
Genome modeling and design across all domains of life
Brian Hie
Stanford University
Brian is an Assistant Professor of Chemical Engineering at Stanford University, the Dieter Schwarz Foundation Stanford Data Science Faculty Fellow, and an Innovation Investigator at Arc Institute, where his group conducts research at the intersection of biology and machine learning.
Abstract: All of life encodes information with DNA. While tools for sequencing, synthesis, and editing of genomic code have transformed biological research, intelligently composing new biological systems would also require a deep understanding of the immense complexity encoded by genomes. We introduce Evo 2, a biological foundation model trained on 9.3 trillion DNA base pairs from a highly curated genomic atlas spanning all domains of life. We train Evo 2 with 7B and 40B parameters to have an unprecedented 1 million token con- text window with single-nucleotide resolution. Evo 2 learns from DNA sequence alone to accurately predict the functional impacts of genetic variation—from noncoding pathogenic mutations to clinically significant BRCA1 variants—without task-specific finetuning. Applying mechanistic interpretability analyses, we reveal that Evo 2 autonomously learns a breadth of biological features, including exon–intron boundaries, transcrip- tion factor binding sites, protein structural elements, and prophage genomic regions. Beyond its predictive capabilities, Evo 2 generates mitochondrial, prokaryotic, and eukaryotic sequences at genome scale with greater naturalness and coherence than previous methods. Guiding Evo 2 via inference-time search enables controllable generation of epigenomic structure, for which we demonstrate the first inference-time scaling results in biology. We make Evo 2 fully open, including model parameters, training code, inference code, and the OpenGenome2 dataset, to accelerate the exploration and design of biological complexity.
Talk details coming soon!
June 19, 2025
11:00 (Montreal Time)
Clare Bycroft
Deepmind
We’ll share more about Clare Bycroft’s talk soon—stay tuned!
Past Talks
Look back at previous talks and speakers, thanks again to all of you !
Alphafold 2 and 3 - Methodological Overview and Drug Discovery Applications
April 24, 2025
James Kirkpatrick
Isomorphic Labs
The real roadblocks in drug development is more than just chemistry
March 20, 2025
Nardin Nakhla
Simmunome Inc
ML-based phenotyping for genomic discovery
March 6, 2025
Cory McLean
Google Research
ML-powered 'lab-in-the-loop' approach for therapeutic antibody discovery and optimization
February 27, 2025
Vladimir Gligorijevic
Genentech - Member of the Roche Group
Artificial Intelligence for Life in Space
February 14, 2025
Lauren Sanders
NASA
A Mila BioAI-rg X Multi-omics-rg talk: Foundation model research across biological data modalities like DNA, RNA and protein
January 31, 2025
Thomas Pierrot
InstaDeep
Speaking the Structure: Generative Models in Molecular Science
December 6, 2024
Yunhui Jang
POSTECH, South Korea
From Health AI to Table Foundation Models; and back?
December 5, 2024
Gaël Varoquaux
Inria (French computer science national research)
AI in the RNA Era: Bridging Fundamental Biology and Therapeutic Discovery
September 26, 2024
Giulia Cantini
Helmholtz Munich
Geometric and Topological Machine Learning for Drug Discovery and Pattern Formation
August 8, 2024
Dhananjay Bhaskar
Yale School of Medicine
Reinforcement Learning for Tissue-Specific Synthetic Promoter Generation
June 27, 2024
Luca Scimeca
Mila
Biologically Explainable Dynamical Systems Underlying Gene Regulation in Cancer
April 4, 2024
Intekhab Hossain
Harvard University
Applications of Machine Learning for Gene Networks
March 18, 2024
Victoria Mochulska
McGill University
Efficiently Detecting Interactions and Matching Across Modalities in High Dimensional 'Omics Data
February 21, 2024
Jason Hartford
Valence Labs at Recursion Pharmaceutical
ProteinShake: Building Datasets and Benchmarks for Deep Learning on Protein Structures
February 14, 2024
Carlos Oliver
Max Planck Institute of Biochemistry, Germany
Phantom oscillations in principal component analysis
January 25, 2024
Matthew Scicluna
Université de Montréal
Learning from prepandemic data to forecast viral escape
November 30, 2023
David Hamelin
Université de Montréal
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
November 16, 2023
Joseph Viviano
Mila
HyenaDNA
November 2, 2023
Alexis Nolin Lapalme
Université de Montréal
Causal Experimental Design
June 22, 2023
Stefan Bauer
Technical University of Munich
Monitoring Cancer Patients Using Liquid Biopsy and High-Multiplex qPCR
May 31, 2023
Zeev Russak
Infiniplex
Machine Learning enabled Pooled Optical Screening in Human Lung Cancer Cells
December 14, 2022
Srinivasan Sivanandan
Insitro
Causal inference with instrumental variables
November 16, 2022
Jason Hartford
Mila
Fast and Accurate Bayesian Polygenic Risk Modeling with Variational Inference
November 2, 2022
Shadi Zabad
McGill University
T cell atlas: receptor sharing vs age, sex and disease
June 29, 2022
Assya Trofimov
University of Washington
The HLA-dependent impact of emerging sars-cov-2 lineages on cellular immunity and antigenic drift
June 15, 2022
David Hamelin
Université de Montréal
Guided Generative Protein Design using Regularized Transformers
June 1, 2022
Egbert Castro
Yale University
Single-cell simulation and cell state control
May 18, 2022
Ionelia Buzatu
Mila
Opening up the brain: An overview of an end-to-end open science neuroimaging research project
April 6, 2022
Colleen Gillon
University of Toronto
The Liver Microenvironment in Health and Disease
March 9, 2022
Tallulah Andrews
University of Western Ontario
Cellular Phenotyping using Deep Learning
February 23, 2022
Oren Krauss
Recursion Pharmaceuticals
Neighbour Embeddings of scRNA-seq Data
January 26, 2022
Dmitry Kobak
University of Tübingen
Morphogenesis as Collective Intelligence: from basal cognition to general AI
January 12, 2022
Michael Levin
Tufts University
Density estimation and comparison on single-cell graphs
November 11, 2021
Alex Tong
Mila
What challenges do we face when designing recommendation systems to guide laboratory experiments?
October 27, 2021
Paul Bertin
Mila
LSTM based context-dependent model of sequence evolution
September 29, 2021
Dongjoon Lim
McGill University
TorchDrug
September 16, 2021
Zhaocheng Zhu, Chence Shi and Zuobai Zhang
Mila
Transport problems in biology: theoretical and applied insights
June 16, 2021
Adit Radhakrishnan, Louis Cammarata
Broad Institute
Saliency is a Possible Red Herring When Diagnosing Poor Generalization
June 2, 2021
Joseph Viviano
Mila
Geometry-based data exploration
April 21, 2021
Guy Wolf
Mila
CRISPR genome editing tutorial
April 7, 2021
Natasha Dudek
Mila
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks
November 26, 2020
Cen Wan
Birkbeck, University of London
A machine learning Automated Recommendation Tool for synthetic biology
November 12, 2020
Hector Garcia Martin
Lawrence Berkeley National Lab
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
October 29, 2020
Alexander Rives
Facebook
Gene2vec: distributed representation of genes based on co-expression
October 15, 2020
Degui Zhi
University of Texas, Houston
UDSMProt: universal deep sequence models for protein classification
October 1, 2020
Nils Strodthoff
Heinrich Hertz Institute
Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations
September 17, 2020
John San Soucie
MIT-WHOI
Supervised learning on phylogenetically distributed data
August 18, 2020
Elliot Layne
McGill
Generative models for graph-based protein design
August 4, 2020
Zichao Yan
McGill
Genomic Language Models
July 21, 2020
Matthew Scicluna
Université de Montréal
Predicting reservoir hosts and arthropod vectors from evolutionary signatures in RNA virus genomes
July 7, 2020
Natasha Dudek
McGill