Regulation of phospholipid distribution in the lipid bilayer by flippases and scramblases

Nature Reviews Molecular Cell Biology, Journal Year: 2023, Volume and Issue: 24(8), P. 576 - 596

Published: April 27, 2023

Language: Английский

---

Large-scale foundation model on single-cell transcriptomics

Nature Methods, Journal Year: 2024, Volume and Issue: 21(8), P. 1481 - 1491

Published: June 6, 2024

Language: Английский

---

Single-cell genomics meets human genetics

Nature Reviews Genetics, Journal Year: 2023, Volume and Issue: 24(8), P. 535 - 549

Published: April 21, 2023

Language: Английский

---

Automatic cell-type harmonization and integration across Human Cell Atlas datasets

Cell, Journal Year: 2023, Volume and Issue: 186(26), P. 5876 - 5891.e20

Published: Dec. 1, 2023

Harmonizing cell types across the single-cell community and assembling them into a common framework is central to building standardized Human Cell Atlas. Here, we present CellHint, predictive clustering tree-based tool resolve cell-type differences in annotation resolution technical biases datasets. CellHint accurately quantifies cell-cell transcriptomic similarities places relationship graph that hierarchically defines shared unique subtypes. Application multiple immune datasets recapitulates expert-curated annotations. also reveals underexplored relationships between healthy diseased lung states eight diseases. Furthermore, workflow for fast cross-dataset integration guided by harmonized hierarchy, which uncovers underappreciated adult human hippocampus. Finally, apply 12 tissues from 38 datasets, providing deeply curated cross-tissue database with ∼3.7 million cells various machine learning models automatic tissues.

Language: Английский

---

Large Scale Foundation Model on Single-cell Transcriptomics

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: May 31, 2023

Abstract Large-scale pretrained models have become foundation leading to breakthroughs in natural language processing and related fields. Developing life science for deciphering the “languages” of cells facilitating biomedical research is promising yet challenging. We developed a large-scale model scFoundation with 100M parameters this purpose. was trained on over 50 million human single-cell transcriptomics data, which contain high-throughput observations complex molecular features all known types cells. currently largest terms size trainable parameters, dimensionality genes number used pre-training. Experiments showed that can serve as achieve state-of-the-art performances diverse array downstream tasks, such gene expression enhancement, tissue drug response prediction, classification, perturbation prediction.

Language: Английский

---

Mapping cells through time and space with moscot

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: May 11, 2023

Abstract Single-cell genomics technologies enable multimodal profiling of millions cells across temporal and spatial dimensions. Experimental limitations prevent the measurement all-encompassing cellular states in their native dynamics or tissue niche. Optimal transport theory has emerged as a powerful tool to overcome such constraints, enabling recovery original context. However, most algorithmic implementations currently available have not kept up pace with increasing dataset complexity, so that current methods are unable incorporate information scale single-cell atlases. Here, we introduce multi-omics optimal (moscot), general scalable framework for applications genomics, supporting multimodality all applications. We demonstrate moscot’s ability efficiently reconstruct developmental trajectories 1.7 million mouse embryos 20 time points identify driver genes first heart field formation. The moscot formulation can be used dimensions well: To this, enrich transcriptomics datasets by mapping from profiles liver sample, align multiple coronal sections brain. then present moscot.spatiotemporal, new approach leverages gene expression uncover spatiotemporal embryogenesis. Finally, disentangle lineage relationships novel murine, time-resolved pancreas development using paired measurements chromatin accessibility, finding evidence shared ancestry between delta epsilon cells. Moscot is an easy-to-use, open-source python package extensive documentation at https://moscot-tools.org .

Language: Английский

---

Transitioning single-cell genomics into the clinic

Nature Reviews Genetics, Journal Year: 2023, Volume and Issue: 24(8), P. 573 - 584

Published: May 31, 2023

Language: Английский

---

Universal Cell Embeddings: A Foundation Model for Cell Biology

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: Nov. 29, 2023

Developing a universal representation of cells which encompasses the tremendous molecular diversity cell types within human body and more generally, across species, would be transformative for biology. Recent work using single-cell transcriptomic approaches to create definitions in form atlases has provided necessary data such an endeavor. Here, we present Universal Cell Embedding (UCE) foundation model. UCE was trained on corpus atlas from other species completely self-supervised way without any annotations. offers unified biological latent space that can represent cell, regardless tissue or species. This embedding captures important variation despite presence experimental noise diverse datasets. An aspect UCE's universality is new organism mapped this with no additional labeling, model training fine-tuning. We applied Integrated Mega-scale Atlas, 36 million cells, than 1,000 uniquely named types, hundreds experiments, dozens tissues eight uncovered insights about organization space, leveraged it infer function newly discovered types. exhibits emergent behavior, uncovering biology never explicitly for, as identifying developmental lineages novel not included set. Overall, by enabling every state type, provides valuable tool analysis, annotation hypothesis generation scale single datasets continues grow.

Language: Английский

---

Profiling cell identity and tissue architecture with single-cell and spatial transcriptomics

Nature Reviews Molecular Cell Biology, Journal Year: 2024, Volume and Issue: 26(1), P. 11 - 31

Published: Aug. 21, 2024

Language: Английский

---

Single-cell sequencing to multi-omics: technologies and applications

Biomarker Research, Journal Year: 2024, Volume and Issue: 12(1)

Published: Sept. 27, 2024

Abstract Cells, as the fundamental units of life, contain multidimensional spatiotemporal information. Single-cell RNA sequencing (scRNA-seq) is revolutionizing biomedical science by analyzing cellular state and intercellular heterogeneity. Undoubtedly, single-cell transcriptomics has emerged one most vibrant research fields today. With optimization innovation technologies, intricate details concealed within cells are gradually unveiled. The combination scRNA-seq other multi-omics at forefront field. This involves simultaneously measuring various omics data individual cells, expanding our understanding across a broader spectrum dimensions. precisely captures aspects transcriptomes, immune repertoire, spatial information, temporal epitopes, in diverse contexts. In addition to depicting cell atlas normal or diseased tissues, it also provides cornerstone for studying differentiation development patterns, disease heterogeneity, drug resistance mechanisms, treatment strategies. Herein, we review traditional technologies outline latest advancements multi-omics. We summarize current status challenges applying biological clinical applications. Finally, discuss limitations potential strategies address them.

Language: Английский

---