Classification of tumor and normal cells in the tumor microenvironment from scRNA-seq data is an ongoing challenge in human cancer study.
Copy number karyotyping of aneuploid tumors (***copyKAT***) (Gao, Ruli, et al., 2021) is a method proposed for identifying copy number variations in single-cell transcriptomics data. It is used to predict aneuploid tumor cells and delineate the clonal substructure of different subpopulations that coexist within the tumor mass.
In this notebook, we will illustrate a basic workflow of CopyKAT based on the tutorial provided on CopyKAT's repository. We will use a dataset of triple negative cancer tumors sequenced by 10X Chromium 3'-scRNAseq (GSM4476486) as an example. The dataset contains 20,990 features across 1,097 cells. We have modified the notebook to demonstrate how the tool works on BioTuring's platform.
Single-cell RNA sequencing methods can profile the transcriptomes of single cells but cannot preserve spatial information. Conversely, spatial transcriptomics assays can profile spatial regions in tissue sections but do not have single-cell resolution.
Here, Runmin Wei (Siyuan He, Shanshan Bai, Emi Sei, Min Hu, Alastair Thompson, Ken Chen, Savitri Krishnamurthy & Nicholas E. Navin) developed a computational method called CellTrek that combines these two datasets to achieve single-cell spatial mapping through coembedding and metric learning approaches. They benchmarked CellTrek using simulation and in situ hybridization datasets, which demonstrated its accuracy and robustness.
They then applied CellTrek to existing mouse brain and kidney datasets and showed that CellTrek can detect topological patterns of different cell types and cell states. They performed single-cell RNA sequencing and spatial transcriptomics experiments on two ductal carcinoma in situ tissues and applied CellTrek to identify tumor subclones that were restricted to different ducts, and specific T-cell states adjacent to the tumor areas.
Geneformer is a foundation transformer model pretrained on a large-scale corpus of ~30 million single cell transcriptomes to enable context-aware predictions in settings with limited data in network biology. Here, we will demonstrate a basic workflow to work with ***Geneformer*** models.
These notebooks include the instruction to:
1. Prepare input datasets
2. Finetune Geneformer model to perform specific task
3. Using finetuning models for cell classification and gene classification application
Single-cell RNA data allows cell-cell communications (***CCC***) methods to infer CCC at either the individual cell or cell cluster/cell type level, but physical distances between cells are not preserved Almet, Axel A., et al., (2021). On the other hand, spatial data provides spatial distances between cells, but single-cell or gene resolution is potentially lost. Therefore, integrating two types of data in a proper manner can complement their strengths and limitations, from that improve CCC analysis.
In this pipeline, we analyze CCC on Visium data with single-cell data as a reference. The pipeline includes 4 sub-notebooks as following
01-deconvolution: This step involves deconvolution and cell type annotation for Visium data, with cell type information obtained from a relevant single-cell dataset. The deconvolution method is SpatialDWLS which is integrated in Giotto package.
02-giotto: performs spatial based CCC and expression based CCC on Visium data using Giotto method.
03-nichenet: performs spatial based CCC and expression based CCC on Visium data using NicheNet method.
04-visualization: visualizes CCC results obtained from Giotto and NicheNet.
Perturbation effects on gene programs are commonly investigated in single-cell experiments. Existing models measure perturbation responses independently across time series, disregarding the temporal consistency of specific gene programs. We introduce CellDrift, a generalized linear model based functional data analysis approach to investigate temporal gene patterns in response to perturbations.
CellDrift is a python package for the evaluation of temporal perturbation effects using single-cell RNA-seq data. It includes functions below:
1. Disentangle common and cell type specific perturbation effects across time;
2. Identify patterns of genes that have similar temporal perturbation responses;
3. Prioritize genes with distinct temporal perturbation responses between perturbations or cell types;
4. Infer differential genes of perturbational states in the pseudo-time trajectories.
Reconstructing cell type compositions and their gene expression from bulk RNA sequencing (RNA-seq) datasets is an ongoing challenge in cancer research. BayesPrism (Chu, T., Wang, Z., Pe’er, D. et al., 2022) is a Bayesian method used to predict cellular composition and gene expression in individual cell types from bulk RNA-seq datasets, with scRNA-seq as references.
This notebook illustrates an example workflow for bulk RNA-seq deconvolution using BayesPrism. The notebook content is inspired by BayesPrism's vignette and modified to demonstrate how the tool works on BioTuring's platform.
Droplet-based single-cell RNA sequence analyses assume that all acquired RNAs are endogenous to cells. However, there is a certain amount of cell-free mRNAs floating in the input solution (referred to as 'the soup'), created from cells in the input solution being lysed. These background mRNAs are then distributed into the droplets with cells and sequenced alongside them, resulting in background contamination that confounds the biological interpretation of single-cell transcriptomic data.
SoupX (Young and Behjati, 2020) is one of the methods proposed for ambient mRNA removal. In this notebook, we will illustrate a workflow example that applies SoupX to correct the ambient RNA in a dataset of 10k PBMC cells. The output of SoupX is a modified counts matrix, which can be used for any downstream analysis tool.
This tool provides a user-friendly and automated way to analyze large-scale single-cell RNA-seq datasets stored in RDS (Seurat) format. It allows users to run various analysis tools on their data in one command, streamlining the analysis workflow and saving time.
Note that this notebook is only for the demonstration of the tool. Users can run the tool directly through the command line.
Currently, we support:
- CellChat - Inference and analysis of cell-cell communication using CellChat
The recent development of single-cell RNA-sequencing (scRNA-seq) technology has enabled us to infer cell-type-specific co-expression networks, enhancing our understanding of cell-type-specific biological functions. However, existing methods proposed for this task still face challenges due to unique characteristics in scRNA-seq data, such as high sequencing depth variations across cells and measurement errors.
CS-CORE (Su, C., Xu, Z., Shan, X. et al., 2023), an R package for cell-type-specific co-expression inference, explicitly models sequencing depth variations and measurement errors in scRNA-seq data.
In this notebook, we will illustrate an example workflow of CS-CORE using a dataset of Peripheral Blood Mononuclear Cells (PBMC) from COVID patients and healthy controls (Wilk et al., 2020). The notebook content is inspired by CS-CORE's vignette and modified to demonstrate how the tool works on BioTuring's platform.
The simultaneous measurement of multiple modalities represents an exciting frontier for single-cell genomics and necessitates computational methods that can define cellular states based on multimodal data.
Here, we introduce "weighted-nearest neighbor" analysis, an unsupervised framework to learn the relative utility of each data type in each cell, enabling an integrative analysis of multiple modalities. We apply our procedure to a CITE-seq dataset of 211,000 human peripheral blood mononuclear cells (PBMCs) with panels extending to 228 antibodies to construct a multimodal reference atlas of the circulating immune system. Multimodal analysis substantially improves our ability to resolve cell states, allowing us to identify and validate previously unreported lymphoid subpopulations.
Moreover, we demonstrate how to leverage this reference to rapidly map new datasets and to interpret immune responses to vaccination and coronavirus disease 2019 (COVID-19). Our approach represents a broadly applicable strategy to analyze single-cell multimodal datasets and to look beyond the transcriptome toward a unified and multimodal definition of cellular identity.
Importantly 'informative' is decided based on how well a gene's variation agrees with some cell metric - some similarity mapping between cells.
Genes which are informative are those whose expression varies in similar way among cells which are nearby in the given metric.
The choice of metric allows you to evaluate different types of gene modules:
- Spatial: For spatial single-cell datasets, you can define cell similarity by proximity in physical, 2D/3D space. When set up this way, Hotspot can be used to identify spatially-varying genes.
- Lineage: For single-cell datasets with a lineage tracing system, you can infer a cell developmental lineage and use that as the cell metric. Then Hotspot can be used to identify heritable patterns of gene expression.
- Transcriptional: The result of a dimensionality reduction procedure can be used create the similarity metric. With this configuration, Hotspot identifies gene modules with local correlation. This can be particularly useful for interpreting axes of variation in non-linear dimensionality reduction procedures where the mapping between components and genes is not straightforward to evaluate.
SpatialData (Marconato, Luca, et al., 2023) is a framework for processing spatial omics data, including
- spatialdata-io: load data from common spatial omics technologies into spatialdata.
- spatialdata-plot: static plotting library for spatialdata.
- napari-spatialdata: napari plugin for interactive exploration and annotation of spatial data.
In this notebook, we will illustrate the visualization functions implemented in SpatialData for Visium data. For datasets from other spatial technologies, please check this document. Also, we will use spatial queries to retrieve all the spatial elements and instances that are within a given rectangular window or polygonal shape from an example Visium brain dataset.
The notebook content is inspired from SpatialData's vignette and modified to demonstrate how the tool works on BioTuring's platform.
Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Deepcell shows that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types. The authors share their experience in designing and optimizing deep convolutional neural networks for this task and propose some design rules to achieve stable performance. The authors conclude that deep convolutional neural networks are an accurate, time-saving, applicable method for many types of cells, from bacteria to animal cells, and expand the capabilities of live-cell imaging to include multi-cell systems.
Deepcell library allows users to apply pre-existing models to imaging data as well as to develop new deep learning models for single-cell analysis. This library specializes in models for cell segmentation (whole-cell and nuclear) in 2D and 3D images as well as cell tracking in 2D time-lapse datasets. These models are applicable to data ranging from multiplexed images of tissues to dynamic live-cell imaging movies.
deepcell-tf which is written in Python using TensorFlow, is a deep learning library for single-cell analysis of biological images. It is one of several resources created by the Van Valen lab to facilitate the development and application of new deep learning methods to biology.
This notebook illustrates how to convert data from a Seurat object into a Scanpy annotation data and a Scanpy annotation data into a Seurat object using the BioStudio data transformation library (currently under development). It facilitates continued research using libraries that interact with Scanpy in Python and Seurat in R.
seurat.to.adata function can retain information about reductions (such as PCA, t-SNE, UMAP and Seurat Clusters) and spatial information.
scVI-tools (single-cell variational inference tools) is a package for end-to-end analysis of single-cell omics data primarily developed and maintained by the Yosef Lab at UC Berkeley. scvi-tools has two components
- Interface for easy use of a range of probabilistic models for single-cell omics (e.g., scVI, scANVI, totalVI).
- Tools to build new probabilistic models, which are powered by PyTorch, PyTorch Lightning, and Pyro.
Single-cell RNA sequencing (scRNA-seq) protocols often face challenges in measuring the expression of all genes within a cell due to various factors, such as technical noise, the sensitivity of scRNA-seq techniques, or sample quality. This limitation gives rise to a need for the prediction of unmeasured gene expression values (also known as dropout imputation) from scRNA-seq data.
ADImpute (Leote A, 2023) is an R package combining several dropout imputation methods, including two existing methods (DrImpute, SAVER), two novel implementations: Network, a gene regulatory network-based approach using gene-gene relationships learned from external data, and Baseline, a method corresponding to a sample-wide average..
This notebook is to illustrate an example workflow of ADImpute on sample datasets loaded from the package. The notebook content is inspired from ADImpute's vignette and modified to demonstrate how the tool works on BioTuring's platform.
Recent spatial transcriptomics (ST) technologies have allowed us to capture cellular heterogeneity while retaining spatial information. However, ST datasets may lose single-cell resolution, limiting the discovery of cell-type-specific spatial patterns of localization and expression.
spacexr (Spatial-eXpression-R) is an R package providing two methods, i.e., Robust Cell Type Decomposition (RCTD) (Cable, Dylan M., et al., 2022) and Cell type-Specific Inference of Differential Expression (C-SIDE) (Cable, Dylan M., et al., 2022) for ST data. RCTD is proposed for cell type deconvolution, while leveraging references from another annotated single-cell RNA-seq data. C-SIDE identifies cell type-specific differential expression, accounting for localization of other cell types.
We will illustrate an example workflow in two notebooks, RCTD and C-SIDE, on a hippocampus Visium dataset provided by the authors. The notebooks are inspired from spacexr's vignettes and modified to demonstrate how the tool works on BioTuring's platform.
Understanding global communications among cells requires accurate representation of cell-cell signaling links and effective systems-level analyses of those links.
We construct a database of interactions among ligands, receptors and their cofactors that accurately represent known heteromeric molecular complexes. We then develop **CellChat**, a tool that is able to quantitatively infer and analyze intercellular communication networks from single-cell RNA-sequencing (scRNA-seq) data.
CellChat predicts major signaling inputs and outputs for cells and how those cells and signals coordinate for functions using network analysis and pattern recognition approaches. Through manifold learning and quantitative contrasts, CellChat classifies signaling pathways and delineates conserved and context-specific pathways across different datasets.
Applying **CellChat** to mouse and human skin datasets shows its ability to extract complex signaling patterns.