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
In the realm of transcriptional dynamics, understanding the intricate interplay of regulatory proteins is crucial for deciphering processes ranging from normal development to disease progression. However, traditional RNA velocity methods often overlook the underlying regulatory drivers of gene expression changes over time. This gap in knowledge hinders our ability to unravel the mechanistic intricacies of these dynamic processes.
scKINETICs (Key regulatory Interaction NETwork for Inferring Cell Speed) (Burdziak et al, 2023) offers a dynamic model for gene expression changes that simultaneously learns per-cell transcriptional velocities and a governing gene regulatory network. By employing an expectation-maximization approach, scKINETICS quantifies the impact of each regulatory element on its target genes, incorporating insights from epigenetic data, gene-gene coexpression patterns and constraints dictated by the phenotypic manifold.
In the realm of cancer research, grasping the intricacies of intratumor heterogeneity and its interplay with the immune system is paramount for deciphering treatment resistance and tumor progression. While single-cell RNA sequencing unveils diverse transcriptional programs, the challenge persists in automatically discerning malignant cells from non-malignant ones within complex datasets featuring varying coverage depths. Thus, there arises a compelling need for an automated solution to this classification conundrum.
SCEVAN (De Falco et al., 2023), a variational algorithm, is designed to autonomously identify the clonal copy number substructure of tumors using single-cell data. It automatically separates malignant cells from non-malignant ones, and subsequently, groups of malignant cells are examined through an optimization-driven joint segmentation process.
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.
Single-cell sequencing is an increasingly used technology and has promising applications in basic research and clinical translations. However, genotyping methods developed for bulk sequencing data have not been well adapted for single-cell data. In this notebook, we introduce cellSNP-lite for genotyping in single-cell sequencing data for both droplet and well-based platforms.
Cellsnp-lite is a C/C++ tool for efficient genotyping bi-allelic SNPs on single cells. You can use cellsnp-lite after read alignment to obtain the snp x cell pileup UMI or read count matrices for each alleles of given or detected SNPs.
cellSNP-lite aims to pileup the expressed alleles in single-cell or bulk RNA-seq data, which can be directly used for donor deconvolution in multiplexed single-cell RNA-seq data, particularly with vireo, which assigns cells to donors and detects doublets, even without genotyping reference.
Cellsnp-lite has following features:
- Wide applicability: cellsnp-lite can take data from various omics as input, including RNA-seq, DNA-seq, ATAC-seq, either in bulk or single cells.
- Simplified user interface that supports parallel computing, cell barcode and UMI tags.
- High efficiency in terms of running speed and memory usage with highly concordant results compared to existing methods.