hussenmi/scimilarity_expanded_model

GeneJEPA is a Joint-Embedding Predictive Architecture (JEPA) trained for self-supervised representation learning on scRNA-seq. It uses a Perceiver-style encoder to handle sparse, high-dimensional gene count vectors and a Fourier-feature tokenizer for numerical tokenization.

A package for the annotation and gene expression data download from Bgee database, and TopAnat analysis: GO-like enrichment of anatomical terms, mapped to genes by expression patterns.

BgeeCall allows to generate present/absent gene expression calls without using an arbitrary cutoff like TPM<1. Calls are generated based on reference intergenic sequences. These sequences are generated based on expression of all RNA-Seq libraries of each species integrated in Bgee (https://bgee.org).

For a convenient overview and download list, visit our model page for this model.

A diffusion language model for genome-scale perturbation prediction across diverse cellular contexts.

Automated cell type annotation tool for single-cell transcriptomics using gradient boosting and logistic regression with reference atlases, enabling standardized classification across datasets (Wellcome Sanger Institute, Nature Biotechnology 2022)