@naturemethods @SingleCellMedia.

different yet complementary approach, offering a robust deep learning framework designed specifically for analyzing novel, small to medium-sized datasets. *The photograph was taken by Sergio Starodubtsev from the Video Lab, Faculty of Medicine, Tel Aviv University.

In recent years, deep learning applications in scRNA-seq analysis have advanced significantly, largely due to breakthroughs in large language models (LLMs). While many current methods focus on training foundational models on large-scale atlas datasets, scNET takes a . .

accelerating drug discovery, and advancing personalized medicine. scNET’s ability to incorporate PPI networks plays a key role in identifying enriched pathways, potential drug targets, and disease-specific biomarkers. .

How would it help.scNET has the potential to be a valuable tool in single-cell genomics. By integrating scRNA-seq data with PPI networks, it provides deeper insights into complex biological systems. This integration is particularly beneficial for studying disease mechanisms, . .

mechanism to enhance cell clustering. scNET reduces zero inflation, improves differential pathway analysis, and enhances the identification of distinct cell communities. .

Easy.scNET, a novel graph neural network (GNN) framework, integrates scRNA-seq data with PPI networks to improve gene and cell relationship analysis. It employs a dual-view architecture combining a PPI network and a cell k-nearest neighbors (KNN) graph, refined by an attention . .

issue but often rely on gene expression data alone and do not leverage the functional context provided by protein-protein interaction (PPI) networks. PPIs offer complementary insights but lack specificity to particular cell types or conditions. .

We all know.Single-cell RNA sequencing (scRNA-seq) reveals cellular heterogeneity but suffers from zero inflation—false zero read counts that obscure biological signals. Traditional imputation methods and graph-based clustering approaches have made strides in addressing this . .

This work was led by Ron Sheinin and in collaboration with Prof. Roded Sharan. .

Happy to share our recent work @nature_methods, scNET, a graph neural network (GNN) framework, combining scRNA-seq data with PPI networks using a dual-view architecture, reducing zero inflation and improving cell clustering and pathway analysis.

RT @KuchrooLab: Neuroimmune crosstalk directs T cell differentiation for optimal viral clearance. With our collaborators, we show that neur….

RT @AnaAndersonlab: Our work "Pan-cancer mapping of single CD8+ T cells profiles reveals a TCF1:CXCR6 axis regulating CD28 co-stimulation a….

RT @LabWaggoner: Pan-cancer CD8+ T cell gene regulatory axis where TCF1 represses CXCR6 expression necessary for tumor control and promotes….

This work was led by Ron Sheinin and was done in collaboration with Koren Salomon, Eilam Yeini, Shai Dulberg, Ayelet Kaminitz, @RSFLab Ronit Satchi-Fainaro and Prof. Roded Sharan.

Our new bioinformatics framework interFLOW. Not only does it do a good job predicting cell-cell interactions based on scRNAseq data, but it also identifies key transcription factors that converge the intracellular signaling following this interaction.

RT @TAUMedFaculty: Congratulations to Professor Asaf Madi from the Department of Pathology for his promotion to Associate Professor & Tenur….

RT @BenDavidLab: A new program at TAU for summer internship fellowships for international students

RT @rolls_asya: Aviv is 2.5 years old and she is a hostage. Use your voice!.Act to bring the hostages home.#HamasisISIS . .