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

The development of immune checkpoint-based immunotherapies has been a major advancement in the treatment of cancer, with a subset of patients exhibiting durable clinical responses. A predictive biomarker for immunotherapy response is the pre-existing T-cell infiltration in the tumor immune microenvironment (TIME). Bulk transcriptomics-based approaches can quantify the degree of T-cell infiltration using deconvolution methods and identify additional markers of inflamed/cold cancers at the bulk level. However, bulk techniques are unable to identify biomarkers of individual cell types. Although single-cell RNA sequencing (scRNAseq) assays are now being used to profile the TIME, to our knowledge there is no method of identifying patients with a T-cell inflamed TIME from scRNAseq data. Here, we describe a method, iBRIDGE, which integrates reference bulk RNAseq data with the malignant subset of scRNAseq datasets to identify patients with a T-cell inflamed TIME. Utilizing two datasets with matched bulk data, we show iBRIDGE results correlated highly with bulk assessments (0.85 and 0.9 correlation coefficients). Using iBRIDGE, we identified markers of inflamed phenotypes in malignant cells, myeloid cells, and fibroblasts, establishing type I and type II interferon pathways as dominant signals, especially in malignant and myeloid cells, and finding the TGFβ-driven mesenchymal phenotype not only in fibroblasts but also in malignant cells. Besides relative classification, per-patient average iBRIDGE scores and independent RNAScope quantifications were utilized for threshold-based absolute classification. Moreover, iBRIDGE can be applied to in vitro grown cancer cell lines and can identify the cell lines that are adapted from inflamed/cold patient tumors.

Single-cell RNA sequencing (scRNA-seq) protocols often face challenges in measuring the expression of all genes within a cell due to various factors, such as technical noise, the sensitivity of scRNA-seq techniques, or sample quality. This limitation gives rise to a need for the prediction of unmeasured gene expression values (also known as dropout imputation) from scRNA-seq data. ADImpute (Leote A, 2023) is an R package combining several dropout imputation methods, including two existing methods (DrImpute, SAVER), two novel implementations: Network, a gene regulatory network-based approach using gene-gene relationships learned from external data, and Baseline, a method corresponding to a sample-wide average.. This notebook is to illustrate an example workflow of ADImpute on sample datasets loaded from the package. The notebook content is inspired from ADImpute's vignette and modified to demonstrate how the tool works on BioTuring's platform.

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.