EPFL BioE Talks SERIES "Generative Modelling to Understand Health and Disease Across Cells, Tissues and Perturbations"


Event details

Date 13.11.2023
Hour 16:0017:00
Speaker Prof. Mohammad Lotfollahi, Wellcome Sanger Institute, Cambridge (UK)
Location Online
Category Conferences - Seminars
Event Language English

The advancements in single-cell technologies have enabled the generation of datasets comprising information from millions of cells. These datasets called 'atlases,' include data from different conditions and individuals across multiple modalities, offering insights into cellular processes and states in various scenarios. I will demonstrate generative approaches to model cellular heterogeneity and how cells interact in tissues and respond to perturbations. Finally, I will discuss how linking patient metadata and single-cell genomics can enable the construction of population-level atlases across thousands of samples and the challenges in such scenarios when dissecting noise from biologically meaningful signals.

I have recently completed my PhD in Computational Biology at the Technical University of Munich (TUM) and Helmholtz Munich under the supervision of Fabian Theis. I am also a member of ELLIS. I am the director of machine learning research at Relation Therapeutics and also a scientist at Helmholtz Munich and also incoming faculty at Wellcome Sanger Institute.

My research focuses on developing AI/ML algorithms for biomedical data, with a specific emphasis on single-cell technologies for diagnostics, therapeutics, and drug discovery. I have received multiple awards for my research (see example) and have been featured in press/journals (see research). Additionally, I have been awarded multiple fellowships, grants, and scholarships, including those from Joachim Hertz, EMBL, and Meta.

I have been offered a faculty position directly after my PhD (rare in Biology) at the Wellcome Sanger Institute, a leading program contributing to the Human Cell Atlas project. As part of this role, I will be hiring PhD students from the University of Cambridge.

In addition to my academic activities, I have industry experience as a researcher, consultant, and advisor in both biotechnology and ML/AI companies, including:

    Meta AI
    Relation Therapeutics

Zoom link (with one-time registration for the whole series) for attending remotely: https://go.epfl.ch/EPFLBioETalks

Instructions for 1st-year Ph.D. students who are under EDBB’s mandatory seminar attendance rule:
IF you are not attending in-person in the room, please make sure to
  1. send D. Reinhard a note before noon on seminar day, informing that you plan to attend the talk online, and
  2. be signed in on Zoom with a recognizable user name (not a pseudonym making it difficult or impossible to be identified).
Students attending the seminar in-person should collect a confirmation signature after the talk - please print your own signature sheet beforehand (71 kB pdf available for download here).

Practical information

  • Informed public
  • Registration required