Repository Index

Repository for Nicheformer: a foundation model for single-cell and spatial omics

OpenBioLink is a resource and evaluation framework for evaluating link prediction models on heterogeneous biomedical graph data.

🏃 The go-to single-cell Foundation Model

• batch-correction
• cell-biology
• celltype-annotation
• denoising

A collection of tasks to probe the effectiveness of protein sequence representations in modeling aspects of protein design

• protein
• protein-sequences
• protein-design
• representation-learning

Learning cell communication from spatial graphs of cells

• tensorflow
• gnn
• glm
• cvae

Official repo for CellPLM: Pre-training of Cell Language Model Beyond Single Cells.

PRnet is a flexible and scalable perturbation-conditioned generative model predicting transcriptional responses to unseen complex perturbations at bulk and single-cell levels.

BulkFormer: A large-scale foundation model for human bulk transcriptomes

PyTorch implementation of the MIDAS algorithm for single-cell multimodal data integration (Nature Biotechnology 2024).

• deep-generative-model
• deep-learning
• single-cell-data-integration
• single-cell-multiomics

Repository for paper scMulan: a multitask generative pre-trained language model for single-cell analysis.

• foundation-models
• gpt
• single-cell

Deep learning model for single-cell inference of multi-omic profiles from a single input modality.

• single-cell
• scrna-seq
• scatac-seq
• deep-neural-networks

MCP server for spatial transcriptomics analysis through natural language interfaces.

• bioinformatics
• cell-communication
• deconvolution
• machine-learning

CancerFoundation: A single-cell RNA sequencing foundation model to decipher drug resistance in cancer

• cancer
• foundation-model
• single-cell

A versatile single-cell cross-modality translation method via dual-aligned variational autoencoders

Official implementation of JAMIE, Joint variational Autoencoders for Multimodal Imputation and Embedding

• autoencoder
• imputation
• integration
• multimodal

scPair: Boosting single cell multimodal analysis by leveraging single cell atlases and implicit feature selection

DetecDiv provides a comprehensive set of tools to analyze time microscopy images using deep learning methods. The software structure is such that data can be processed either at the command line or using a graphical user-interface. Detecdiv classification models include : image classification and regression, semantic segmentation, LSTM networks to analyze data and image timeseries.

Interpretable modeling of cellular responses to drug perturbations using cycle consistence learning

DeepAEG: A model for predicting cancer drug response based on data enhancement and edge-collaborative update strategies

GNN-based gene-selection deep learning model for drug response prediction