Single-cell perturbation analysis
-
Updated
Sep 7, 2026 - Python
Single-cell perturbation analysis
Single cell Perturbations - Analysis of Differential gene Expression
Recovering gene regulatory networks from Perturb-seq by fitting steady-state ODEs through frozen single-cell foundation models (GenBio @ ICML 2026)
Integrated time-series analysis and high-content CRISPR screening delineate the dynamics of macrophage immune regulation
Epigenetic regulators of fibrotic transformation in cardiac fibroblasts
Agentic gene perturbation prediction system for the MLGenX BioReasoning Challenge – Track B.
A single-cell RNAseq pipeline for perturb-seq data
Reproducible computational vignettes for the CRISPR-perturbation multi-omics identifiability review (Asediya, Briefings in Bioinformatics)
A reproducible computational pipeline for processing and analyzing single-cell RNA-seq data with CRISPR perturbations (Perturb-seq), designed for the Virtual Cell Challenge 2025. Features automated quality control, normalization, class balancing, and batch integration using Snakemake.
Analysis code for Perturb-ME: scalable mechanism discovery from phenotype-enriched genome-wide CRISPR screens (Wang, Gu, Frangieh et al., bioRxiv 2026)
Runnable Perturb-seq analysis pipeline (guide assignment, Mixscape, pseudobulk-vs-per-cell DE, E-distance) on the Papalexi 2021 ECCITE-seq CRISPR screen — pertpy + scanpy
A hands-on virtual cell perturbation prediction course for experimental biologists.
Fast exact short-DNA known-target assignment for CRISPR guides, barcodes, primers, panels, and whitelists.
JCAP CRISPR Mixscape Pipeline is a user-friendly R Shiny application for interactive single-cell CRISPR screen analysis. It enables rapid quality control, visualization, and differential expression discovery using Mixscape and Seurat, all in a point-and-click environment. Ideal for researchers working with Perturb-seq data.
Rigorous benchmark of single-cell CRISPR perturbation x condition response prediction (melanoma Perturb-CITE-seq): effect-level (delta) metrics, random forest vs linear vs CPA.
Perturbation Prediction Model for the Kaggle Challenge: "Myllia| Echoes of Silenced Genes: A Cell Challenge"
Ask a meta-analysis in plain English and it tells you whether the statistics support one combined number, refusing when they do not. Every number is computed by a tested toolkit, never the model. Also a Model Context Protocol server.
To associate your repository with the perturb-seq topic, visit your repo's landing page and select "manage topics."