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.

Spatially resolved gene expression profiles are key to understand tissue organization and function. However, spatial transcriptomics (ST) profiling techniques lack single-cell resolution and require a combination with single-cell RNA sequencing (scRNA-seq) information to deconvolute the spatially indexed datasets. Leveraging the strengths of both data types, we developed SPOTlight, a computational tool that enables the integration of ST with scRNA-seq data to infer the location of cell types and states within a complex tissue. SPOTlight is centered around a seeded non-negative matrix factorization (NMF) regression, initialized using cell-type marker genes and non-negative least squares (NNLS) to subsequently deconvolute ST capture locations (spots). Simulating varying reference quantities and qualities, we confirmed high prediction accuracy also with shallowly sequenced or small-sized scRNA-seq reference datasets. SPOTlight deconvolution of the mouse brain correctly mapped subtle neuronal cell states of the cortical layers and the defined architecture of the hippocampus. In human pancreatic cancer, we successfully segmented patient sections and further fine-mapped normal and neoplastic cell states. Trained on an external single-cell pancreatic tumor references, we further charted the localization of clinical-relevant and tumor-specific immune cell states, an illustrative example of its flexible application spectrum and future potential in digital pathology.