elonlit/GeneJEPA
https://huggingface.co/elonlit/GeneJEPAGeneJEPA 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.
Sourced from
- HuggingFace — elonlit/GeneJEPA
Related resources
jlu-wsj/scRep
by jlu-wsjscRep is a PyTorch model for extracting cell embeddings from single-cell RNA-seq AnnData (.h5ad) inputs. This repository is a standalone Hugging Face release bundle: it includes checkpoint weights, the exact paired gene vocabulary, the inference implementation, and runnable examples.
autoencodix/Ontix-Dim16-KimiK3
by autoencodixAn Ontix autoencoder with an explainable, 16-dimensional latent space, trained on single-cell RNA-seq data. Each latent dimension is constrained by a gene ontology term generated with Kimi K3, making the embedding directly interpretable in terms of biological processes.
hussenmi/scimilarity_expanded_model
by hussenmiAn extended version of SCimilarity, a metric-learning model for single-cell RNA-seq that maps cells to a unified 128-dimensional embedding space. The original model and method are described in:
An Ontix autoencoder with an explainable, 16-dimensional latent space, trained on single-cell RNA-seq data. Each latent dimension is constrained by a gene ontology term generated with Claude Opus 5, making the embedding directly interpretable in terms of biological processes.
autoencodix/Ontix-Dim16-GPT5-6
by autoencodixAn Ontix autoencoder with an explainable, 16-dimensional latent space, trained on single-cell RNA-seq data. Each latent dimension is constrained by a gene ontology term generated with GPT-5.6 TerraPro, making the embedding directly interpretable in terms of biological processes.