MARS: discovering novel cell types across heterogeneous single-cell experiments

Brbić, Maria; Žitnik, Marinka; Wang, Sheng; Pisco, Angela Oliveira; Altman, Russ B.; Darmanis, Spyros; Leskovec, Jure

doi:10.1038/s41592-020-00979-3

Cited by 113 publications

(148 citation statements)

References 41 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…Following this observation, we decided to use differentially expressed genes between 24h PN clusters for PN-type identification for all stages. We applied meta-learned representations for single cell data (MARS) for identifying and annotating cell types (Brbic et al, 2020). MARS learns to project cells using deep neural networks in the latent low-dimensional space in which cells group according to their cell types.…”

Section: Identifying Pn Types At All Developmental Stagesmentioning

confidence: 99%

See 1 more Smart Citation

Temporal evolution of single-cell transcriptomes of Drosophila olfactory projection neurons

Xie

Brbić

Horns

et al. 2021

eLife

Self Cite

View full text Add to dashboard Cite

Neurons undergo substantial morphological and functional changes during development to form precise synaptic connections and acquire specific physiological properties. What are the underlying transcriptomic bases? Here, we obtained the single-cell transcriptomes of Drosophila olfactory projection neurons (PNs) at four developmental stages. We decoded the identity of 21 transcriptomic clusters corresponding to 20 PN types and developed methods to match transcriptomic clusters representing the same PN type across development. We discovered that PN transcriptomes reflect unique biological processes unfolding at each stage—neurite growth and pruning during metamorphosis at an early pupal stage; peaked transcriptomic diversity during olfactory circuit assembly at mid-pupal stages; and neuronal signaling in adults. At early developmental stages, PN types with adjacent birth order share similar transcriptomes. Together, our work reveals principles of cellular diversity during brain development and provides a resource for future studies of neural development in PNs and other neuronal types.

show abstract

Section: Identifying Pn Types At All Developmental Stagesmentioning

confidence: 99%

“…Unless otherwise specified, all data analysis was performed in Python using Scanpy (Wolf et al, 2018), Numpy, Scipy, Pandas, scikit-learn, and custom single-cell RNA-seq modules (Li et al, 2017;Brbic et al, 2020). Gene Ontology analysis were performed using Flymine (Lyne et al, 2007).…”

Section: Quantification and Statistical Analysismentioning

confidence: 99%

Temporal evolution of single-cell transcriptomes of Drosophila olfactory projection neurons

Xie

Brbić

Horns

et al. 2021

eLife

Self Cite

View full text Add to dashboard Cite

show abstract

“…The classifier achieves 79.8% accuracy in MP cell type prediction, demonstrating the capability of automatically annotating query scRNA-seq datasets using the pretrained scETM model on the reference scRNA-seq data. We expect that these results can be improved by further tuning of the model on the unannotated query data, or by the use of a compatible transfer learning framework such as MARS [25].…”

Section: Transfer Learning Across Single-cell Datasetsmentioning

confidence: 99%

Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data

Zhao

Cai

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

The advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, integrative analysis of scRNA-seq data remains a challenge largely due to batch effects. We present single-cell Embedded Topic Model (scETM), an unsupervised deep generative model that recapitulates known cell types by inferring the latent cell topic mixtures via a variational autoencoder. scETM is scalable to over 106 cells and enables effective knowledge transfer across datasets. scETM also offers high inter-pretability and allows the incorporation of prior pathway knowledge into the gene embeddings. The scETM-inferred topics show enrichment in cell-type-specific and disease-related pathways.

show abstract

“…In comparison to other current tools, such as cscGAN [24], MARS [25], FiRE [26], and ELSA [27], sc-SynO uses synthetic oversampling of previously, manually curated cell populations to identify such rare cells in novel data. In addition, sc-SynO is easily applicable and only requires a single, well-curated dataset, including only a few cells of interest, to be able to achieve already a high predictive accuracy.…”

Section: Discussionmentioning

confidence: 99%

Automated annotation of rare-cell types from single-cell RNA-sequencing data through synthetic oversampling

Bej

Galow

Dávid

et al. 2021

Preprint

View full text Add to dashboard Cite

The research landscape of single-cell and single-nuclei RNA sequencing is evolving rapidly, and one area that is enabled by this technology, is the detection of rare cells. An automated, unbiased and accurate annotation of rare subpopulations is challenging. Once rare cells are identified in one dataset, it will usually be necessary to generate other datasets to enrich the analysis (e.g., with samples from other tissues). From a machine learning perspective, the challenge arises from the fact that rare cell subpopulations constitute an imbalanced classification problem.We here introduce a Machine Learning (ML)-based oversampling method that uses gene expression counts of already identified rare cells as an input to generate synthetic cells to then identify similar (rare) cells in other publicly available experiments. We utilize single-cell synthetic oversampling (sc-SynO), which is based on the Localized Random Affine Shadowsampling (LoRAS) algorithm. The algorithm corrects for the overall imbalance ratio of the minority and majority class.We demonstrate the effectiveness of the method for two independent use cases, each consisting of two published datasets. The first use case identifies cardiac glial cells in snRNA-Seq data (17 nuclei out of 8,635). This use case was designed to take a larger imbalance ratio (∼1 to 500) into account and only uses single-nuclei data. The second use case was designed to jointly use snRNA-Seq data and scRNA-Seq on a lower imbalance ratio (∼1 to 26) for the training step to likewise investigate the potential of the algorithm to consider both single cell capture procedures and the impact of “less” rare-cell types. For validation purposes, all datasets have also been analyzed in a traditional manner using common data analysis approaches, such as the Seurat3 workflow.Our algorithm identifies rare-cell populations with a high accuracy and low false positive detection rate. A striking benefit of our algorithm is that it can be readily implemented in other and existing workflows. The code basis is publicly available at FairdomHub (https://fairdomhub.org/assays/1368) and can easily be transferred to train other customized approaches.

show abstract

MARS: discovering novel cell types across heterogeneous single-cell experiments

Cited by 113 publications

References 41 publications

Temporal evolution of single-cell transcriptomes of Drosophila olfactory projection neurons

Temporal evolution of single-cell transcriptomes of Drosophila olfactory projection neurons

Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data

Automated annotation of rare-cell types from single-cell RNA-sequencing data through synthetic oversampling

Contact Info

Product

Resources

About