Biology subjects

Hutter, J.-C.

Publications and source records attributed to Hutter, J.-C..

3 recordsLinked to original sources

bioRxiv2024

A Supervised Contrastive Framework for Learning Disentangled Representations of Cell Perturbation Data

CRISPR technology, combined with single-cell RNA-Seq, has opened the way to large scale pooled perturbation screens, allowing more systematic interrogations of gene functions in cells at scale. However, such Perturb-seq data poses many analysis challenges, due to its high-dimensionality, high level of technical noise, and variable Cas9 efficiency. The single-cell nature of the data also poses its own challenges, as we observe the heterogeneity of phenotypes in the unperturbed cells, along with the effect of the perturbations. All in all, these characteristics make it difficult to discern subtler effects. Existing tools, like mixscape and ContrastiveVI, provide partial solutions, but may oversimplify biological dynamics, or have low power to characterize perturbations with a smaller effect size. Here, we address these limitations by introducing the Supervised Contrastive Variational Autoencoder (SC-VAE). SC-VAE integrates guide RNA identity with gene expression data, ensuring a more discriminative analysis, and adopts the Hilbert-Schmidt Independence Criterion as a way to achieve disentangled representations, separating the heterogeneity in the control population from the effect of the perturbations. Evaluation on large-scale data sets highlights SC-VAEs superior sensitivity in identifying perturbation effects compared to ContrastiveVI, scVI and PCA. The perturbation embeddings better reflect known protein complexes (evaluated on CORUM), while its classifier offers promise in identifying assignment errors and cells escaping the perturbation phenotype. SC-VAE is readily applicable across diverse perturbation data sets.

bioinformatics↗

bioRxiv2023

Sequential Optimal Experimental Design of Perturbation Screens Guided by Multi-modal Priors

Understanding a cells expression response to genetic perturbations helps to address important challenges in biology and medicine, including the function of gene circuits, discovery of therapeutic targets and cell reprogramming and engineering. In recent years, Perturb-seq, pooled genetic screens with single cell RNA-seq (scRNA-seq) readouts, has emerged as a common method to collect such data. However, irrespective of technological advances, because combinations of gene perturbations can have unpredictable, non-additive effects, the number of experimental configurations far exceeds experimental capacity, and for certain cases, the number of available cells. While recent machine learning models, trained on existing Perturb-seq data sets, can predict perturbation outcomes with some degree of accuracy, they are currently limited by sub-optimal training set selection and the small number of cell contexts of training data, leading to poor predictions for unexplored parts of perturbation space. As biologists deploy Perturb-seq across diverse biological systems, there is an enormous need for algorithms to guide iterative experiments while exploring the large space of possible perturbations and their combinations. Here, we propose a sequential approach for designing Perturb-seq experiments that uses the model to strategically select the most informative perturbations at each step for subsequent experiments. This enables a significantly more efficient exploration of the perturbation space, while predicting the effect of the rest of the unseen perturbations with high-fidelity. Analysis of a previous large-scale Perturb-seq experiment reveals that our setting is severely restricted by the number of examples and rounds, falling into a non-conventional active learning regime called "active learning on a budget". Motivated by this insight, we develop IO_SCPLOWTERC_SCPLOWPO_SCPLOWERTC_SCPLOW, a novel active learning method that exploits rich and multi-modal prior knowledge in order to efficiently guide the selection of subsequent perturbations. Using prior knowledge for this task is novel, and crucial for successful active learning on a budget. We validate IO_SCPLOWTERC_SCPLOWPO_SCPLOWERTC_SCPLOW using insilico benchmarking of active learning, constructed from a large-scale CRISPRi Perturb-seq data set. We find that IO_SCPLOWTERC_SCPLOWPO_SCPLOWERTC_SCPLOW outperforms other active learning strategies by reaching comparable accuracy at only a third of the number of perturbations profiled as the next best method. Overall, our results demonstrate the potential of sequentially designing perturbation screens through IO_SCPLOWTERC_SCPLOWPO_SCPLOWERTC_SCPLOW.

bioinformatics↗

bioRxiv2022

Disentangling shared and group-specific variations in single-cell transcriptomics data with multiGroupVI

Single-cell RNA sequencing (scRNA-seq) technologies have enabled a greater understanding of previously unexplored biological diversity. Based on the design of such experiments, individual cells from scRNA-seq datasets can often be attributed to non-overlapping "groups". For example, these group labels may denote the cells tissue or cell line of origin. In this setting, one important problem consists in discerning patterns in the data that are shared across groups versus those that are group-specific. However, existing methods for this type of analysis are mainly limited to (generalized) linear latent variable models. Here we introduce multiGroupVI, a deep generative model for analyzing grouped scRNA-seq datasets that decomposes the data into shared and group-specific factors of variation. We first validate our approach on a simulated dataset, on which we significantly outperform state-of-the-art methods. We then apply it to explore regional differences in an scRNA-seq dataset sampled from multiple regions of the mouse small intestine. We implemented multiGroupVI using the scvi-tools library [1], and released it as open-source software at https://github.com/Genentech/multiGroupVI.

bioinformatics↗