perturbation screen

Cross-modal transfer enables zero-shot prediction of drug responses across cell types

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

MYC targeted de novo binders impair tumor growth

Designed protein binders to conserved MYC regions reach low-nanomolar affinity, reduce MYC-MAX proximity in cells, and are depleted from MYC-dependent cancer cells in culture and mouse pancreatic tumors.

De novo macrocyclic peptide discovery produces potent class A GPCR ligands with diverse pharmacology

This study discovers potent, selective macrocyclic peptide ligands for CXCR4, a class A GPCR, demonstrating the feasibility of de novo peptide design for this receptor family.

Distributed AI agents enable comprehensive discovery of biological insights at scale

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.

Additive-input encoding fails operator-level target-held-out prediction on current Perturb-seq screens

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

PIE: Generalizing perturbation effects across unseen perturbations, contexts and datasets

Predicting differentially expressed genes and expression shifts per condition from database embeddings plus per-gene evidence, PIE reaches 1.2–3.2 times the best baseline's AUPRC on unseen contexts, perturbations and datasets.

Engineering phenotypic heterogeneity for functional organization in microbial populations

This paper introduces PROMETEO, a genetic-circuit framework that programs microbial population composition through asymmetric circuits, enabling functional organization and efficient biotransformation.

Reconstructing signaling histories of single cells via perturbation screens and transfer learning

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

SCALE: Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction

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.

Accessible and reproducible deployment reveals the practical boundaries of single-cell foundation models

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.

Predicting cellular responses to perturbation across diverse contexts with STATE

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.

Genome-scale perturb-seq in primary human CD4+ T cells maps context-specific regulators of T cell programs and human immune traits

Genome-scale CRISPRi perturb-seq in 22 million primary human CD4+ T cells maps stimulation-specific regulators and links perturbation signatures to T cell states and autoimmune genetics.

KSTITCH links cellular morphology and gene expression in spatial transcriptomics

STITCH pairs size-independent tangent-PCA contour shape modes with expression factors by canonical correlation, recovering keratinocyte, fibroblast and melanoma shape-expression links in Xenium and CosMx data.

The diverse functions of viral microproteins

A >50,000-element viral smORF library screened by growth, MHC-I, ER stress, Perturb-seq and mass spectrometry yields >2,000 active microproteins and shows EBV BNLF2b inhibits PKA by mimicry.

Functional pocketomes and complete allosteric maps of five protein kinases

Energy-model maps of five human kinases show conserved distance-dependent decay of inhibitory allostery, but distal allosteric pockets and activating sites diverge between kinases.

A platform for robust quantitative functional genomics reveals temporal fitness landscapes in African trypanosomes

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.

Pan-cancer proteogenomic interrogation of the Ubiquitin Proteasome System

Proteogenomic analysis of up to 11 CPTAC cohorts shows ubiquitin-proteasome proteins often diverge from transcripts; TP53-mutant tumors elevate UBR5 protein, while TRIM28 prognosis is lineage-dependent.

OCellus: A Language-Model Framework for Single-Cell, Spatial, and Perturbation Biology with Natural-Language Reasoning

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

Galvanin (TMEM154) is an electric-field sensor for directed cell migration

A CRISPRi migration screen in neutrophil-like HL-60 cells identified Galvanin (TMEM154), a single-pass membrane protein whose negatively charged ectodomain electrophoreses anodally to steer cathodal electrotaxis.

STRAIGHT-IN Dual: a platform for dual, single-copyintegrations of DNA payloads and gene circuits into human induced pluripotent stem cells

STRAIGHT-IN Dual enables efficient, single-copy integration of two DNA payloads into hiPSCs, improving genetic engineering for synthetic biology applications.

The one-week automated genome-wide optical pooled screen

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 for cytotoxicity and mode-of-action analysis in primary human hepatocytes

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.

Design-of-Experiments for Nonlinear, Multivariate Biology: Rethinking Experimental Design through Perturb-seq

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 Characterizes Key Factors affecting Alzheimer's Disease and Associated Phenotypes

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.

Orthogonal chemical genomics approaches reveal genomic targets for increasing anaerobic chemical tolerance in Zymomonas mobilis

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

Novel reporter of the PINK1-Parkin mitophagy pathway identifies its damage sensor in the import gate

A HaloTagged MFN2 reporter enabled CRISPRi screens showing diverse mitochondrial damage activates PINK1-Parkin via membrane potential loss, with TOM retaining PINK1 when TIM23 is blocked.

Unified multimodal learning enables generalized cellular response prediction to diverse perturbations

X-Pert is a unified framework for predicting cellular responses to diverse perturbations, outperforming existing methods across genetic and chemical perturbations and enabling generalization across cell types.

Gene-embedding-based prediction and functional evaluation of perturbation expression responses with PRESAGE

PRESAGE predicts perturbation expression responses using gene embeddings and outperforms existing methods in functional evaluations.

A Plug-and-Play Platform for Automated Azapeptide Synthesis: Case study of Azapeptide-based GLP-1

This paper introduces an automated platform for azapeptide synthesis that overcomes synthetic challenges by using pre-activated building blocks and microwave-assisted synthesis, enabling efficient and scalable production of stabilized peptide therapeutics.

Tahoe-100M: A Giga-Scale Single-Cell Perturbation Atlas for Context-Dependent Gene Function and Cellular Modeling

A 100-million-cell atlas: 50 cancer lines pooled as spheroid villages, treated with 379 drugs at several doses, profiled by combinatorial-barcoding scRNA-seq and embedded with a 10-dimensional scVI model.