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.
☆175Updated last year
Related projects ⓘ
Alternatives and complementary repositories for CPA
- Code for "Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution", NeurIPS 2022.☆104Updated 3 months ago
- Models and datasets for perturbational single-cell omics☆142Updated 2 years ago
- Learning Single-Cell Perturbation Responses using Neural Optimal Transport☆115Updated last week
- The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell leve…☆88Updated 2 months ago
- GEARS is a geometric deep learning model that predicts outcomes of novel multi-gene perturbations☆207Updated 2 months ago
- ☆176Updated 7 months ago
- Biological Network Integration using Convolutions☆59Updated 9 months ago
- Images and other data from the JUMP Cell Painting Consortium☆160Updated last week
- Reference mapping for single-cell genomics☆335Updated last week
- ☆56Updated last year
- Discovering novel cell types across heterogenous single-cell experiments☆120Updated last year
- scPerturb: A resource and a python/R tool for single-cell perturbation data☆107Updated 2 months ago
- Perturbation Analysis in the scverse ecosystem.☆141Updated 2 weeks ago
- ☆19Updated last year
- Variational Auto-Encoder that generates synthetic gene expression data☆22Updated last year
- Assorted tools for interacting with .gct, .gctx files and other Connectivity Map (Broad Institute) data/tools☆126Updated 2 years ago
- Formalizing and benchmarking open problems in single-cell genomics☆320Updated this week
- Implementation of Neural Distance Embeddings for Biological Sequences (NeuroSEED) in PyTorch (NeurIPS 2021)☆71Updated last year
- Training and evaluating a variational autoencoder for pan-cancer gene expression data☆164Updated 5 years ago
- Machine Learning for Genomics and Therapeutics Resources (Cell Patterns)☆74Updated 3 years ago
- Learning cell communication from spatial graphs of cells☆102Updated 9 months ago
- Evaluation suite for transcriptomic perturbation effect prediction models. Includes support for single-cell foundation models.☆15Updated this week
- Single cell perturbation prediction☆266Updated 4 months ago
- P-NET, Biologically informed deep neural network for prostate cancer classification and discovery☆150Updated 2 years ago
- 1st place solution of Kaggle Open Problems - Multimodal Single-Cell Integration☆42Updated last year
- CellBox: Interpretable Machine Learning for Perturbation Biology☆54Updated last year
- Multi-omic single-cell optimal transport tools☆115Updated this week
- A generative topic model that facilitates integrative analysis of large-scale single-cell RNA sequencing data.☆48Updated 2 years ago
- Model zoo for genomics☆165Updated 3 months ago
- PerturbNet is a deep generative model that can predict the distribution of cell states induced by chemical or genetic perturbation☆29Updated this week