theislab / cpa
The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.
☆82Updated last month
Related projects: ⓘ
- scPerturb: A resource and a python/R tool for single-cell perturbation data☆101Updated 3 weeks ago
- Models and datasets for perturbational single-cell omics☆141Updated 2 years ago
- Code for "Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution", NeurIPS 2022.☆96Updated last month
- A generative topic model that facilitates integrative analysis of large-scale single-cell RNA sequencing data.☆48Updated 2 years ago
- PerturbNet is a deep generative model that can predict the distribution of cell states induced by chemical or genetic perturbation☆28Updated last year
- ☆55Updated last year
- A unifying representation of single cell expression profiles that quantifies similarity between expression states and generalizes to repr…☆84Updated this week
- A model developed for the generation of scRNA-seq data☆27Updated last week
- ☆17Updated 3 years ago
- Accelerated, Python-only, single-cell integration benchmarking metrics☆45Updated last week
- Additional code and analysis from the single-cell integration benchmarking project☆52Updated last year
- Codes for paper: Evaluating the Utilities of Large Language Models in Single-cell Data Analysis.☆45Updated 3 weeks ago
- single cell foundation model for Gene network inference and more☆13Updated last week
- High-Dimensional Gene Expression and Morphology Profiles of Cells across 28,000 Genetic and Chemical Perturbations☆47Updated last year
- ☆66Updated last month
- spatial transcriptome, single cell☆63Updated last year
- Repository for Nicheformer: a foundation model for single-cell and spatial omics☆50Updated 4 months ago
- Formalizing and benchmarking open problems in single-cell genomics☆56Updated 2 weeks ago
- DIALOGUE is a dimensionality reduction method that uses cross-cell-type associations to identify multicellular programs (MCPs) and map th…☆102Updated 7 months ago
- This repository implements Graph Variational Causal Inference (graphVCI), a framework that integrates prior knowledge of relational infor…☆15Updated last year
- ☆96Updated last year
- Diffusion model for gene regulatory network inference.☆12Updated 3 months ago
- End-to-end analysis of spatial multi-omics data☆32Updated 3 weeks ago
- ☆44Updated last year
- TCRconv is a deep learning model for predicting recognition between T cell receptors and epitopes. It uses protBERT embeddings for the TC…☆22Updated last year
- Learning Single-Cell Perturbation Responses using Neural Optimal Transport☆112Updated 6 months ago
- ☆104Updated 2 months ago
- CellBox: Interpretable Machine Learning for Perturbation Biology☆54Updated last year
- ☆71Updated last year
- ☆12Updated 3 weeks ago