E-spatial

CellRank2 (Weiler et al, 2023) is a powerful framework for studying cellular fate using single-cell RNA sequencing data. It can handle millions of cells and different data types efficiently. This tool can identify cell fate and probabilities across various data sets. It also allows for analyzing transitions over time and uncovering key genes in developmental processes. Additionally, CellRank2 estimates cell-specific transcription and degradation rates, aiding in understanding differentiation trajectories and regulatory mechanisms. In this notebook, we will use a primary tumor sample of patient T71 from the dataset GSE137804 (Dong R. et al, 2020) as an example. We have performed RNA-velocity analysis and pseudotime calculation on this dataset in scVelo (Bergen et al, 2020) notebook. The output will be then loaded into this CellRank2 notebook for further analysis. This notebook is based on the tutorial provided on CellRank2 documentation. We have modified the notebook and changed the input data to show how the tool works on BioTuring's platform.

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

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.

Advances in multi-omics have led to an explosion of multimodal datasets to address questions from basic biology to translation. While these data provide novel opportunities for discovery, they also pose management and analysis challenges, thus motivating the development of tailored computational solutions. `muon` is a Python framework for multimodal omics. It introduces multimodal data containers as `MuData` object. The package also provides state of the art methods for multi-omics data integration. `muon` allows the analysis of both unimodal omics and multimodal omics.