Notebooks
Categories
Cells
Premium
BioTuring
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
BioTuring
Doublets are a characteristic error source in droplet-based single-cell sequencing data where two cells are encapsulated in the same oil emulsion and are tagged with the same cell barcode. Across type doublets manifest as fictitious phenotypes that can be incorrectly interpreted as novel cell types. DoubletDetection present a novel, fast, unsupervised classifier to detect across-type doublets in single-cell RNA-sequencing data that operates on a count matrix and imposes no experimental constraints.
This classifier leverages the creation of in silico synthetic doublets to determine which cells in the
input count matrix have gene expression that is best explained by the combination of distinct cell
types in the matrix.
In this notebook, we will illustrate an example workflow for detecting doublets in single-cell RNA-seq count matrices.
BioTuring
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.
BioTuring
In this notebook, we present COMMOT (COMMunication analysis by Optimal Transport) to infer cell-cell communication (CCC) in spatial transcriptomic, a package that infers CCC by simultaneously considering numerous ligand–receptor pairs for either spatial transcriptomic data or spatially annotated scRNA-seq data equipped with spatial distances between cells estimated from paired spatial imaging data.
A collective optimal transport method is developed to handle complex molecular interactions and spatial constraints. Furthermore, we introduce downstream analysis tools to infer spatial signaling directionality and genes regulated by signaling using machine learning models.
Trends
BioTuring
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.