Generalized and scalable trajectory inference in single-cell omics data with VIA

Stassen, Shobana V.; Yip, Gwinky G. K.; Wong, Kenneth K. Y.; Ho, Joshua W. K.; Tsia, Kevin K.

doi:10.1038/s41467-021-25773-3

Cited by 60 publications

(47 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, we apply UMAP [39] to reduce these 640 dimensional vectors into 2 dimension, and project them on a plane. Furthermore, we explore if the embeddings contain evolutionary information of RNA by applying trajectory inference, which is implemented by VIA [42]. We take embeddings of lncRNA as input, and get the stream-plot of RNA evolutionary trend.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

Chen¹,

Hu²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations. These are all among the core problems in the RNA field. With the rapid growth of sequencing technology, we have accumulated a massive amount of unannotated RNA sequences. On the other hand, expensive experimental observatory results in only limited numbers of annotated data and 3D structures. Hence, it is still challenging to design supervised computational methods for predicting their structures and functions. Lack of annotated data and systematic study causes inferior performance. To resolve the issue, we propose a novel RNA foundation model (RNA-FM) to take advantage of all the 23 million non-coding RNA sequences through self-supervised learning. Within this approach, we discover that the pre-trained RNA-FM could infer sequential and evolutionary information of non-coding RNAs without using any labels. Furthermore, we demonstrate RNA-FM's effectiveness by applying it to the downstream secondary/3D structure prediction, protein-RNA binding preference modeling, and 5' UTR-based mean ribosome loading prediction. The comprehensive experiments show that the proposed method improves the RNA structural and functional modeling results significantly and consistently. Despite only trained with unlabelled data, RNA-FM can serve as the foundational model for the field.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Here we obtain their evolutionary relationship from an evolutionary study of lncRNA repertoires and expression patterns [41]. We first generate RNA-FM embeddings for the lncRNA subset, then trajectory inference is carried out via VIA [42] and the stream-plot is shown in Fig. 2c.…”

Section: Rna-fm Learns Multi-dimension Biological Information Of Rna ...mentioning

confidence: 99%

Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

Chen¹,

Hu²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Several algorithms were developed to reconstruct differentiation pathways by using scRNA-seq. In 2019 Saelens et al reported the existence of more than 70 trajectory analysis techniques [4] and in the recent years many more have emerged [5,6,7]. Many techniques require prior information to infer the trajectory, such as a starting or root cell [8,9].…”

Section: Methods Details Backgroundmentioning

confidence: 99%

ORIGINS: a protein network-based approach to quantify cell pluripotency from scRNA-seq data

Senra¹,

Guisoni²,

Diambra³

2022

Preprint

View full text Add to dashboard Cite

Trajectory inference is a common application of scRNA-seq data. However, it is often necessary to previously determine the origin of the trajectories, the stem or progenitor cells. In this work, we propose a computational tool to quantify pluripotency from single cell transcriptomics data. This approach uses the protein-protein interaction (PPI) network associated with the differentiation process as a scaffold and the gene expression matrix to calculate a score that we call differentiation activity. This score reflects how active the differentiation network is for each cell. We benchmark the performance of our algorithm with two previously published tools, LandSCENT [1] and CytoTRACE [2], for four data sets: breast, colon, hematopoietic and lung. We show that our algorithm is more efficient than LandSCENT and requires less RAM memory than the other programs. We also illustrate a complete workflow from the count matrix to trajectory inference using the breast data set.Graphical abstract

show abstract

“…These techniques have been successfully applied to study the developmental trajectories of different cell types and TMEs ( Zhang et al, 2019 ; Chen et al, 2020 ; Qian et al, 2020 ; He et al, 2021 ; Liu et al, 2021 ). With the improvement in single-cell omics technology performance and their integration ability, we need to address the problem of cell number scalability and the generalizability of these methods to different omics ( Stassen et al, 2021 ).…”

Section: Computational Approaches To Analyze Single-cell Data Of the Tmementioning

confidence: 99%

Breaking the Immune Complexity of the Tumor Microenvironment Using Single-Cell Technologies

et al. 2022

View full text Add to dashboard Cite

Tumors are not a simple aggregate of transformed cells but rather a complicated ecosystem containing various components, including infiltrating immune cells, tumor-related stromal cells, endothelial cells, soluble factors, and extracellular matrix proteins. Profiling the immune contexture of this intricate framework is now mandatory to develop more effective cancer therapies and precise immunotherapeutic approaches by identifying exact targets or predictive biomarkers, respectively. Conventional technologies are limited in reaching this goal because they lack high resolution. Recent developments in single-cell technologies, such as single-cell RNA transcriptomics, mass cytometry, and multiparameter immunofluorescence, have revolutionized the cancer immunology field, capturing the heterogeneity of tumor-infiltrating immune cells and the dynamic complexity of tenets that regulate cell networks in the tumor microenvironment. In this review, we describe some of the current single-cell technologies and computational techniques applied for immune-profiling the cancer landscape and discuss future directions of how integrating multi-omics data can guide a new “precision oncology” advancement.

show abstract

Generalized and scalable trajectory inference in single-cell omics data with VIA

Cited by 60 publications

References 76 publications

Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

ORIGINS: a protein network-based approach to quantify cell pluripotency from scRNA-seq data

Breaking the Immune Complexity of the Tumor Microenvironment Using Single-Cell Technologies

Contact Info

Product

Resources

About