GEARS: Predicting transcriptional outcomes of novel multi-gene perturbations

Cellular response to genetic perturbation is central to numerous biomedical applications from identifying genetic interactions involved in cancer to methods for regenerative medicine. However, the combinatorial explosion in the number of possible multi-gene perturbations severely limits experimental interrogation. Here, we present GEARS, a method that can predict transcriptional response to both single and multi-gene perturbations using single-cell RNA-sequencing data from perturbational screens. GEARS is uniquely able to predict outcomes of perturbing combinations consisting of novel genes that were never experimentally perturbed by leveraging geometric deep learning and a knowledge graph of gene-gene relationships. GEARS has higher precision than existing approaches in predicting five distinct genetic interaction subtypes and can identify the strongest interactions more than twice as well as prior approaches. Overall, GEARS can discover novel phenotypic outcomes to multi-gene perturbations and can thus guide the design of perturbational experiments.

[1]  Chun Jimmie Ye,et al.  CRISPR activation and interference screens decode stimulation responses in primary human T cells , 2022, Science.

[2]  Thomas M. Norman,et al.  Mapping information-rich genotype-phenotype landscapes with genome-scale Perturb-seq , 2021, Cell.

[3]  The Tabula Sapiens: a multiple organ single cell transcriptomic atlas of humans , 2021, bioRxiv.

[4]  Yongjin P. Park.  Faculty Opinions recommendation of SCENIC: single-cell regulatory network inference and clustering. , 2021, Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature.

[5]  M. Maitland,et al.  CRISPR-Cas9 In Vivo Gene Editing for Transthyretin Amyloidosis. , 2021, The New England journal of medicine.

[6]  Fabian J Theis,et al.  Learning interpretable cellular responses to complex perturbations in high-throughput screens , 2021, bioRxiv.

[7]  E. Ruppin,et al.  Synthetic lethality-mediated precision oncology via the tumor transcriptome , 2021, Cell.

[8]  A. Regev,et al.  Multimodal pooled Perturb-CITE-seq screens in patient models define mechanisms of cancer immune evasion , 2021, Nature Genetics.

[9]  Yuchen Yang,et al.  Direct cell reprogramming: approaches, mechanisms and progress , 2021, Nature Reviews Molecular Cell Biology.

[10]  Antonia A. Dominguez,et al.  CRISPR technologies for precise epigenome editing , 2021, Nature Cell Biology.

[11]  H. Clevers,et al.  CRISPR-Cas Tools and Their Application in Genetic Engineering of Human Stem Cells and Organoids. , 2020, Cell stem cell.

[12]  John G. Doench,et al.  Design and analysis of CRISPR–Cas experiments , 2020, Nature Biotechnology.

[13]  T. K. Nguyen,et al.  CRISPR technologies for stem cell engineering and regenerative medicine. , 2019, Biotechnology advances.

[14]  Thomas M. Norman,et al.  Exploring genetic interaction manifolds constructed from rich single-cell phenotypes , 2019, Science.

[15]  Mohammad Lotfollahi,et al.  scGen predicts single-cell perturbation responses , 2019, Nature Methods.

[16]  T. M. Murali,et al.  Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data , 2019, Nature Methods.

[17]  J. Moffat,et al.  Global Genetic Networks and the Genotype-to-Phenotype Relationship , 2019, Cell.

[18]  Kilian Q. Weinberger,et al.  Simplifying Graph Convolutional Networks , 2019, ICML.

[19]  Damian Szklarczyk,et al.  STRING v11: protein–protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets , 2018, Nucleic Acids Res..

[20]  Neal K. Bennett,et al.  Mapping the Genetic Landscape of Human Cells , 2018, Cell.

[21]  K. Davis,et al.  Tisagenlecleucel in Children and Young Adults with B‐Cell Lymphoblastic Leukemia , 2018, The New England journal of medicine.

[22]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[23]  Henning Hermjakob,et al.  The Reactome pathway knowledgebase , 2013, Nucleic Acids Res..

[24]  寛 大岩.  早期関節リウマチ：brief overview , 2018 .

[25]  P. Hieter,et al.  Synthetic lethality and cancer , 2017, Nature Reviews Genetics.

[26]  J. Aerts,et al.  SCENIC: Single-cell regulatory network inference and clustering , 2017, Nature Methods.

[27]  Yuhao Wang,et al.  Permutation-based Causal Inference Algorithms with Interventions , 2017, NIPS.

[28]  Aaron N. Chang,et al.  Combinatorial CRISPR-Cas9 screens for de novo mapping of genetic interactions , 2017, Nature Methods.

[29]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[30]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[31]  Thomas M. Norman,et al.  A Multiplexed Single-Cell CRISPR Screening Platform Enables Systematic Dissection of the Unfolded Protein Response , 2016, Cell.

[32]  Thomas M. Norman,et al.  Perturb-Seq: Dissecting Molecular Circuits with Scalable Single-Cell RNA Profiling of Pooled Genetic Screens , 2016, Cell.

[33]  Mulin Jun Li,et al.  Nature Genetics Advance Online Publication a N a Ly S I S the Support of Human Genetic Evidence for Approved Drug Indications , 2022 .

[34]  Yoshihiro Yamanishi,et al.  KEGG for linking genomes to life and the environment , 2007, Nucleic Acids Res..

[35]  K. Sachs,et al.  Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data , 2005, Science.

[36]  B Marshall,et al.  Gene Ontology Consortium: The Gene Ontology (GO) database and informatics resource , 2004, Nucleic Acids Res..

[37]  H. Kitano.  Systems Biology: A Brief Overview , 2002, Science.

[38]  D. Lauffenburger,et al.  Receptors: Models for Binding, Trafficking, and Signaling , 1993 .