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
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.
BioTuring
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.
BioTuring
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.
Trends
BioTuring
Computational methods have been proposed to leverage spatially resolved transcriptomic data, pinpointing genes with spatial expression patterns and delineating tissue domains. However, existing approaches fall short in uniformly quantifying spatially variable genes (SVGs). Moreover, from a methodological viewpoint, while SVGs are naturally associated with depicting spatial domains, they are technically dissociated in most methods.
Here, PROST is a flexible framework to quantify gene spatial expression patterns and detect spatial tissue domains using spatially resolved transcriptomics with various resolutions. PROST consists of two independent workflows: PROST Index (PI) and PROST Neural Network (PNN).
Using PROST you can do:
* Quantitative identification of spatial patterns of gene expression changes by the proposed PROST Index (PI).
* Unsupervised identification of spatial tissue domains using a PROST Neural Network (PNN) via a self-attention mechanism.