perturbation screen

GRAFT predicts drug responses across cell types without direct measurements by transferring genetic perturbation data to chemical perturbations.

The paper introduces distributed AI agents to analyze large-scale biological datasets, demonstrating their ability to rapidly extract insights and predict outcomes across a Perturb-seq atlas.

The paper shows that additive-input models fail to generalize in Perturb-seq screens when predicting new perturbation targets.

The paper develops a framework combining perturbation screens and transfer learning to reconstruct signaling histories in cells and optimize differentiation protocols.

A set-aware latent transport model predicts treated cell populations from unpaired controls, keeps perturbation-specific signal in CRISPR, drug and cytokine data, and guided a cytokine choice tested in three donors.

Across 13 single-cell foundation models and 94 datasets, PCA and established methods usually match or beat them; pretrained embeddings help mainly with scarce labels, rare cells and open-set detection.

State, a set-based transformer trained on over 100 million perturbed cells, predicts perturbation responses in new cellular contexts better than mean, linear and deep learning baselines.

DRiF-Seq, a sequencing-optimized RNAi platform with a posteriori noise estimation, quantifies clone-resolved fitness genome-wide in pleomorphic Trypanosoma brucei; over half of core genes carry fitness costs.

OCellus is a language model that addresses limitations in single-cell, spatial, and perturbation biology by integrating natural-language reasoning across multiple tasks.

The paper introduces OttoSeq, an automated optical pooled screen platform that completes a genome-wide cell painting screen in eight days, analyzing over 5 million cells across 21,732 gene knockouts.

Cell Painting in primary human hepatocytes exposed to 1,085 compounds detects bioactivity at lower concentrations than cytotoxicity assays and predicts cell-based, but not cell-free, ToxCast endpoints across feature extractors.

The paper evaluates experimental design in Perturb-seq, finding that correlated designs are robust in systems with signal amplification and introduces a metric to predict optimal designs.

BrainBridge integrates single-cell transcriptomic data with phenotypes to model brain biology, prioritizing genes and cell types linked to Alzheimer's, aging, and sex differences.

The paper identifies genomic targets for improving anaerobic chemical tolerance in Zymomonas mobilis using orthogonal gene perturbation screens and validates findings through gene deletions.

This paper introduces a consensus clustering method to identify robust signals from high-throughput screens by analyzing multi-scale data organization in cancer cell lines and bacterium models.

This paper introduces PeML, a similarity metric learning method for perturbational datasets, improving the identification of perturbation mechanisms and biological relationships.

DepLink links genetic and pharmacologic dependencies in cancer by integrating CRISPR, pharmacologic, and expression data through an R Shiny app.

MultiCPA predicts multimodal perturbation responses at the single-cell level using a generative model trained on CRISPR perturbation data.

The paper develops a model to infer pairwise epistatic gene interactions from siRNA perturbation screens, showing that glinternet outperforms xyz in accuracy for high-dimensional data.

The paper links transcriptomic, proteomic, and peptidomic brain data to their original brain regions using digital atlas mapping techniques, focusing on the hypothalamus.