Fatemeh Behjati Ardakani1,2,3,4, Kathrin Kattler5, Tobias Heinen2,3, Florian Schmidt1,2,3,4, David Feuerborn6, Gilles Gasparoni5, Konstantin Lepikhov5, Patrick Nell6, Jan Hengstler6, Jörn Walter5, Marcel H Schulz1,2,3. 1. Institute for Cardiovascular Regeneration, Goethe University, 60590 Frankfurt am Main, Germany; Theodor-Stern-Kai 7. 2. Cluster of Excellence MMCI, Saarland University, Campus E1 7, Saarland Informatics Campus, 66123 Saarbrücken, Germany. 3. Max Planck Institute for Informatics, Campus E1 4, Saarland Informatics Campus, 66123 Saarbrücken, Germany. 4. Graduate School of Computer Science, Saarland University, Campus E1 3, Saarbrücken, Germany. 5. Department of Genetics, Saarland University, Campus A2 4, 66123 Saarbrücken, Germany. 6. Leibniz Research Centre for Working Environment and Human Factors (IfADo), Ardeystraße 67, 44139 Dortmund, Germany.
Abstract
BACKGROUND: Single-cell RNA sequencing is a powerful technology to discover new cell types and study biological processes in complex biological samples. A current challenge is to predict transcription factor (TF) regulation from single-cell RNA data. RESULTS: Here, we propose a novel approach for predicting gene expression at the single-cell level using cis-regulatory motifs, as well as epigenetic features. We designed a tree-guided multi-task learning framework that considers each cell as a task. Through this framework we were able to explain the single-cell gene expression values using either TF binding affinities or TF ChIP-seq data measured at specific genomic regions. TFs identified using these models could be validated by the literature. CONCLUSION: Our proposed method allows us to identify distinct TFs that show cell type-specific regulation. This approach is not limited to TFs but can use any type of data that can potentially be used in explaining gene expression at the single-cell level to study factors that drive differentiation or show abnormal regulation in disease. The implementation of our workflow can be accessed under an MIT license via https://github.com/SchulzLab/Triangulate.
BACKGROUND: Single-cell RNA sequencing is a powerful technology to discover new cell types and study biological processes in complex biological samples. A current challenge is to predict transcription factor (TF) regulation from single-cell RNA data. RESULTS: Here, we propose a novel approach for predicting gene expression at the single-cell level using cis-regulatory motifs, as well as epigenetic features. We designed a tree-guided multi-task learning framework that considers each cell as a task. Through this framework we were able to explain the single-cell gene expression values using either TF binding affinities or TF ChIP-seq data measured at specific genomic regions. TFs identified using these models could be validated by the literature. CONCLUSION: Our proposed method allows us to identify distinct TFs that show cell type-specific regulation. This approach is not limited to TFs but can use any type of data that can potentially be used in explaining gene expression at the single-cell level to study factors that drive differentiation or show abnormal regulation in disease. The implementation of our workflow can be accessed under an MIT license via https://github.com/SchulzLab/Triangulate.
Authors: James C Liao; Riccardo Boscolo; Young-Lyeol Yang; Linh My Tran; Chiara Sabatti; Vwani P Roychowdhury Journal: Proc Natl Acad Sci U S A Date: 2003-12-12 Impact factor: 11.205
Authors: Jun Ding; Bruce J Aronow; Naftali Kaminski; Joseph Kitzmiller; Jeffrey A Whitsett; Ziv Bar-Joseph Journal: Genome Res Date: 2018-01-09 Impact factor: 9.043
Authors: Stephen J Clark; Ricard Argelaguet; Chantriolnt-Andreas Kapourani; Thomas M Stubbs; Heather J Lee; Celia Alda-Catalinas; Felix Krueger; Guido Sanguinetti; Gavin Kelsey; John C Marioni; Oliver Stegle; Wolf Reik Journal: Nat Commun Date: 2018-02-22 Impact factor: 14.919
Authors: Elisabeth Drucker; Kerstin Holzer; Stefan Pusch; Juliane Winkler; Diego F Calvisi; Eva Eiteneuer; Esther Herpel; Benjamin Goeppert; Stephanie Roessler; Alessandro Ori; Peter Schirmacher; Kai Breuhahn; Stephan Singer Journal: Cell Commun Signal Date: 2019-11-29 Impact factor: 5.712
Authors: Sara Aibar; Carmen Bravo González-Blas; Thomas Moerman; Vân Anh Huynh-Thu; Hana Imrichova; Gert Hulselmans; Florian Rambow; Jean-Christophe Marine; Pierre Geurts; Jan Aerts; Joost van den Oord; Zeynep Kalender Atak; Jasper Wouters; Stein Aerts Journal: Nat Methods Date: 2017-10-09 Impact factor: 28.547