Interpretable Machine Learning to Model Drug Perturbations in Single Cell Genomics


Modeling a cell's state e.g. during differentiation or in response to perturbations is a central goal of computational biology. Single-cell technologies now give us easy and large-scale access to state observations on the transcriptomic and more recently also epigenomic level. In particular, they allow resolving potential heterogeneities due to asynchronicity of differentiating or responding cells, and profiles across multiple conditions such as time points, space and replicates are being generated. This makes this an ideal application area for machine learning method development to understand cellular variation, contribution of particular transcripts as well as impact of perturbations.

In this talk, I will shortly review approaches from deep representation learning we and others have been using to identify the manifold of cellular state (=gene expression manifold). I will then introduce our recent perturbation model 'compositional perturbation autoencoder' (CPA), a deep autoencoder we developed to describe the impact of perturbations such as drug or genetic modification on this manifold. With CPA we can learn an interpretable model of perturbations and predict novel and/or optimal perturbations. I show examples of CPA predicting dosage-specific drug effects as well as combinatorial genetic interactions, and how CPA allows in-silico generation of putative interaction effects.


Fabian Theis is director of the Institute of Computational Biology at the Helmholtz Center Munich and scientific director of the Helmholtz Artificial Intelligence Cooperation Unit (HelmholtzAI) which was launched in 2019. He is a full professor at the Technical University of Munich, holding the chair ‘Mathematical Modelling of Biological Systems’, associate faculty at the Wellcome Trust Sanger Institute as well as adjunct faculty at the Northwestern University. Fabian Theis holds a Master’s degree in Mathematics and Physics and Ph.D. Degrees in Physics and Computer Science. After different research stays. He worked as visiting researcher at the Department of Architecture and Computer Technology (University of Granada, Spain), at the RIKEN Brain Science Institute (Wako, Japan), at FAMU-FSU (Florida State University, USA), and TUAT’s Laboratory for Signal and Image Processing (Tokyo, Japan), and headed the ‘signal processing & information theory’ group at the Institute of Biophysics (Regensburg, Germany). In 2006, he started working as a Bernstein fellow leading a junior research group at the Bernstein Center for Computational Neuroscience, located at the Max Planck Institute for Dynamics and Self-Organisation at Göttingen. In summer 2007, Fabian Theis became working group head of CMB at the Institute of Bioinformatics at the Helmholtz Center Munich. In spring 2009, he became associate Professor for Mathematics in Systems Biology at the Math Department of the TU Munich. 2009-2014 he was a member of the ‘Young Academy’ (founded by the Berlin-Brandenburg Academy of Sciences and Humanities and the German Academy of Natural Scientists Leopoldina) and was awarded an ERC starting grant in 2010. In 2017 he was awarded the Erwin Schrödinger prize together within an interdisciplinary team at the ETH Zürich. Fabian Theis is part of and also coordinates various consortia (i.e. sparse2big involving 8 Helmholtz Centers) and founded the network SingleCellOmics Germany (SCOG). Furthermore, he coordinates 2019 launched Munich School for Data Science (MUDS) and is co-directing the ELLIS Munich Unit, the local hub of the European Machine Learning network ELLIS. Since 2020, he holds the position of co-chair of the Bavarian AI Council of the Bavarian Ministry for Science and Art and supports the TUM with his expertise as start-up Ambassador.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google