facebookresearch / 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.
☆180Updated last year
Alternatives and similar repositories for CPA:
Users that are interested in CPA are comparing it to the libraries listed below
- Code for "Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution", NeurIPS 2022.☆112Updated 2 months ago
- The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell leve…☆99Updated 8 months ago
- Learning Single-Cell Perturbation Responses using Neural Optimal Transport☆128Updated 5 months ago
- Models and datasets for perturbational single-cell omics☆153Updated 2 years ago
- Perturbation Analysis in the scverse ecosystem.☆169Updated this week
- GEARS is a geometric deep learning model that predicts outcomes of novel multi-gene perturbations☆249Updated 2 months ago
- Images and other data from the JUMP Cell Painting Consortium☆168Updated 2 months ago
- Reference mapping for single-cell genomics☆360Updated last month
- Machine Learning for Genomics and Therapeutics Resources (Cell Patterns)☆77Updated 3 years ago
- Sequential Optimal Experimental Design of Perturbation Screens Guided by Multimodal Priors☆40Updated 10 months ago
- Learning cell communication from spatial graphs of cells☆109Updated last year
- ☆60Updated last year
- Formalizing and benchmarking open problems in single-cell genomics☆330Updated this week
- Discovering novel cell types across heterogenous single-cell experiments☆123Updated 2 years ago
- ☆77Updated 8 months ago
- ☆19Updated 2 years ago
- A generative topic model that facilitates integrative analysis of large-scale single-cell RNA sequencing data.☆49Updated 3 years ago
- A unifying representation of single cell expression profiles that quantifies similarity between expression states and generalizes to repr…☆184Updated 2 months ago
- PerturbNet is a deep generative model that can predict the distribution of cell states induced by chemical or genetic perturbation☆32Updated 2 months ago
- gReLU is a python library to train, interpret, and apply deep learning models to DNA sequences.☆256Updated this week
- scPerturb: A resource and a python/R tool for single-cell perturbation data☆119Updated last month
- Accelerated, Python-only, single-cell integration benchmarking metrics☆56Updated this week
- P-NET, Biologically informed deep neural network for prostate cancer classification and discovery☆149Updated 3 years ago
- ☆59Updated 7 months ago
- DeepRC: Immune repertoire classification with attention-based deep massive multiple instance learning☆118Updated last year
- CpG Transformer for imputation of single-cell methylomes☆38Updated last year
- Multi-omic single-cell optimal transport tools☆151Updated this week
- ☆12Updated 7 months ago
- Variational Auto-Encoder that generates synthetic gene expression data☆23Updated 2 years ago
- High-Dimensional Gene Expression and Morphology Profiles of Cells across 28,000 Genetic and Chemical Perturbations☆48Updated 2 months ago