perturbation response prediction

APEX automates recombinant protein production in E. coli, enabling high-throughput and reproducible expression with minimal setup.

The paper compares perturbation outcomes in in vivo and ex vivo hematopoietic stem cell models, finding systematic biases and challenges in predicting in vivo effects from ex vivo data.

The paper identifies BORC as a modifier of TDP-43 protein levels in neurons, showing lysosome transport is required for TDP-43 turnover.

The paper introduces CRITR-seq, a CRISPR-based method to measure transcriptional effects, and identifies NELF as a regulator of influenza transcription and interferon response.

EASY-CRISPR enables high-throughput, single-step genetic editing in E. coli using optimized guide RNAs and repair templates to construct genetic tools and mutant libraries.

The paper uses single-cell perturbation screens to decode splicing factor regulatory networks, revealing cross-regulatory loops and MYC's role in linking cancer mutations to splicing regulation.

This study shows humans predictively adjust arm stiffness before movement to optimize task success, even at the cost of energy efficiency.

The paper uses CRISPRa Perturb-seq to perturb transcription factors in fibroblasts, recapitulating in vivo transcriptional states and identifying key regulators.

The paper benchmarks deep learning models against linear baselines for predicting gene perturbation effects and finds they do not outperform simple models.

HLAIIPred predicts HLAII-presented peptides using a Transformer-based model, outperforming existing methods and identifying core interaction residues.

The paper develops an exact linear theory to predict cortical network responses to perturbations by analyzing space- and feature-dependent connectivity.

DrugPT predicts gene expression changes after drug treatment using a Transformer-based framework integrating gene and chemical representations.

The paper optimizes the iMAP CRISPR platform to reduce recombination bias, profiles RNA modification factors across mouse tissues, and identifies context-specific functions with therapeutic implications.

This study tests assumptions about cTBS effects on neural inhibition and disinhibition in macaques, finding no behavioral or neural evidence supporting these hypotheses.

The paper identifies peptides based on the autoinhibitory XY linker of PLCβ isoforms that inhibit PLCβ activity and reduce inflammation and pain in a mouse model.

This study identifies mRNA deadenylation as a key mechanism regulating body plan formation in mouse gastruloids by affecting mesoderm and endoderm differentiation.

COALA identifies optimal counterfactual interventions for individuals using gradient boosted trees on NHANES data, achieving 85.4% accuracy in predicting feature changes.

The paper establishes a cause-and-effect relationship between DNA methylation at the IL1RN promoter and gene expression, showing its impact on myeloid cell fate and inflammatory response.

The paper compares CRISPRi screens in human stem cells and their derivatives to show cell type-dependent roles of translation-coupled quality control factors.

PerturbNet predicts cell state changes from unseen chemical and genetic perturbations using deep learning and perturbation response data.

HiCGen predicts and perturbs chromatin organization, revealing loop domains' role in higher-order structures like TADs and compartments.

This paper introduces SGE, a method for screening metabolic pathways in mammalian cells, and finds that mitochondrial localization and large synthetic DNA constructs are key for successful pathway engineering.

GREmLN is a foundation model that uses graph structure to improve gene embeddings in single-cell transcriptomics, outperforming baselines in cell type annotation and perturbation prediction.

OmniPert predicts responses to genetic and chemical perturbations in single cancer cells using a deep learning model trained on diverse cellular profiles.

MORPH predicts cellular responses to genetic perturbations across data modalities and conditions using a variational autoencoder and attention mechanism.

CIPHER uses gene co-fluctuations in unperturbed cells to predict transcriptome-wide responses to perturbations, outperforming existing methods and revealing key regulatory structures.

This paper benchmarks foundation model representations for predicting cellular perturbation responses, identifying effective representation learning strategies.

MintFlow is a generative AI algorithm that predicts how tissue perturbations reprogram cell states in disease, revealing novel cell populations and therapeutic targets in three human conditions.

The paper develops CXCR2-homing nanoparticles to specifically target PMN-MDSCs in PDAC, reducing arginase activity and enhancing T-cell activity without causing neutropenia.

EEG-GAN generates synthetic EEG data to improve classification accuracy across multiple datasets and classifiers, achieving up to 16% improvement in decoding accuracy.