E-spatial

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

Power analyses are considered important factors in designing high-quality experiments. However, such analyses remain a challenge in single-cell RNA-seq studies due to the presence of hierarchical structure within the data (Zimmerman et al., 2021). As cells sampled from the same individual share genetic and environmental backgrounds, these cells are more correlated than cells sampled from different individuals. Currently, most power analyses and hypothesis tests (e.g., differential expression) in scRNA-seq data treat cells as if they were independent, thus ignoring the intra-sample correlation, which could lead to incorrect inferences. Hierarchicell (Zimmerman, K.D. and Langefeld, C.D., 2021) is an R package proposed to estimate power for testing hypotheses of differential expression in scRNA-seq data while considering the hierarchical correlation structure that exists in the data. The method offers four important categories of functions: data loading and cleaning, empirical estimation of distributions, simulating expression data, and computing type 1 error or power. In this notebook, we will illustrate an example workflow of Hierarchicell. The notebook is inspired by Hierarchicell's vignette and modified to demonstrate how the tool works on BioTuring's platform.

The development of large-scale single-cell atlases has allowed describing cell states in a more detailed manner. Meanwhile, current deep leanring methods enable rapid analysis of newly generated query datasets by mapping them into reference atlases. expiMap (‘explainable programmable mapper’) Lotfollahi, Mohammad, et al. is one of the methods proposed for single-cell reference mapping. Furthermore, it incorporates prior knowledge from gene sets databases or users to analyze query data in the context of known gene programs (GPs).

Expanded CRISPR-compatible CITE-seq (ECCITE-seq) which is built upon pooled CRISPR screens, allows to simultaneously measure transcriptomes, surface protein levels, and single-guide RNA (sgRNA) sequences at single-cell resolution. The technique enables multimodal characterization of each perturbation and effect exploration. However, it also encounters heterogeneity and complexity which can cause substantial noise into downstream analyses. Mixscape (Papalexi, Efthymia, et al., 2021) is a computational framework proposed to substantially improve the signal-to-noise ratio in single-cell perturbation screens by identifying and removing confounding sources of variation. In this notebooks, we demonstrate Mixscape's features using pertpy - a Python package offering a range of tools for perturbation analysis. The original pipeline of Mixscape implemented in R can be found here.