A multi-view latent variable model reveals cellular heterogeneity in complex tissues for paired multimodal single-cell data

Wang, Yuwei; Lian, Bin; Zhang, Haohui; Zhong, Yuanke; He, Jie; Wu, Fashuai; Reinert, Knut; Shang, Xuequn; Yang, Hui; Hu, Jialu

doi:10.1093/bioinformatics/btad005

Cited by 10 publications

(4 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the works used CNN as the DL method for classifying metagenomic samples. There are few works which used GCN and variational auto encoders (VAE) for feature extraction and reduction from genomic data [ 22 – 25 ]. However, to the best of our knowledge, we observed that GNNs, such as GraphSAGE, have not been widely applied in the area of microbiome analysis to predict diseases.…”

Section: Introductionmentioning

confidence: 99%

Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE

2023

View full text Add to dashboard Cite

Background The human microbiome plays a critical role in maintaining human health. Due to the recent advances in high-throughput sequencing technologies, the microbiome profiles present in the human body have become publicly available. Hence, many works have been done to analyze human microbiome profiles. These works have identified that different microbiome profiles are present in healthy and sick individuals for different diseases. Recently, several computational methods have utilized the microbiome profiles to automatically diagnose and classify the host phenotype. Results In this work, a novel deep learning framework based on boosting GraphSAGE is proposed for automatic prediction of diseases from metagenomic data. The proposed framework has two main components, (a). Metagenomic Disease graph (MD-graph) construction module, (b). Disease prediction Network (DP-Net) module. The graph construction module constructs a graph by considering each metagenomic sample as a node in the graph. The graph captures the relationship between the samples using a proximity measure. The DP-Net consists of a boosting GraphSAGE model which predicts the status of a sample as sick or healthy. The effectiveness of the proposed method is verified using real and synthetic datasets corresponding to diseases like inflammatory bowel disease and colorectal cancer. The proposed model achieved a highest AUC of 93%, Accuracy of 95%, F1-score of 95%, AUPRC of 95% for the real inflammatory bowel disease dataset and a best AUC of 90%, Accuracy of 91%, F1-score of 87% and AUPRC of 93% for the real colorectal cancer dataset. Conclusion The proposed framework outperforms other machine learning and deep learning models in terms of classification accuracy, AUC, F1-score and AUPRC for both synthetic and real metagenomic data.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE

2023

View full text Add to dashboard Cite

show abstract

“…Single-cell multi-view data has emerged in recent years, driven by advancements in sequencing technology that enable researchers to collect information from various views of the same cell [35]. The integration of data from multiple views provides a comprehensive understanding of cell characterization.…”

Section: B Multi-view Clustering Methods For Single-cell Datamentioning

confidence: 99%

What is the cause(s) of ozone trends in three megacity clusters in eastern China during 2015–2020?

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. Thanks to a strong emission control policy, major air pollutants in China, including PM2.5, SO2, NO2 and CO had shown remarkable reductions in 2015–2020. However, ozone (O3) had increased significantly and emerged as a major air pollutant in eastern China at the same time. The annual mean concentration of maximum daily 8-hour average O3 (MDA8) in three megacity clusters in eastern China, namely Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD) and Pearl River Delta (PRD), showed alarming large upward linear trends of 2.4, 1.1 and 2.0 ppb yr-1, respectively during the period 2015–2020. Furthermore, drastic trends of approximately three-fold increase in the number of O3-exceeding days (defined as MDA8 O3 >75 ppb) were observed during the same period. Our analysis of the upward trends of the annual mean concentration of MDA8 found that the trends were almost entirely attributable to the increase in the number of consecutive O3-exceeding days. In addition, a widespread expansion of high O3 from urban centers to surrounding rural regions was found in 2015–2017, which had made the O3 spatial distribution becoming more uniform after 2017. Finally, we found that the O3 episodes with four or more consecutive O3-exceeding days in the three megacity clusters were closely associated with the position and strength of the West Pacific subtropical high (WPSH), which contributed to the meteorological conditions characterized by clear sky, sinking motion and high vertical stability in the lower troposphere, and high solar radiation and positive temperature anomaly at the surface. These meteorological conditions were highly conducive to O3 formation. Hence we hypothesize that the cause of the worsening O3 trends in BTH, YRD and PRD from 2015 to 2020 is attributable to the increased occurrence of meteorological conditions of high solar radiation and positive temperature anomaly under the influence of WPSH, tropical cyclones as well as mid-high latitude wave activities.

show abstract

“…These techniques have demonstrated their effectiveness in various applications and experimental setups. Simultaneously, several algorithms have been put forth for paired data, which encompass Seurat v4 ( Hao et al 2021 ), totalVI ( Gayoso et al 2021 ), and VIMCCA ( Wang et al 2023 ), along with various others. It is important to note that while these methods excel in many scenarios, they are often customized to specific modalities or application contexts.…”

Section: Introductionmentioning

confidence: 99%

Scbean: a python library for single-cell multi-omics data analysis

Zhang,

Wang,

Lian

et al. 2024

Bioinformatics

Self Cite

View full text Add to dashboard Cite

Summary Single-cell multi-omics technologies provide a unique platform for characterizing cell states and reconstructing developmental process by simultaneously quantifying and integrating molecular signatures across various modalities, including genome, transcriptome, epigenome, and other omics layers. However, there is still an urgent unmet need for novel computational tools in this nascent field, which are critical for both effective and efficient interrogation of functionality across different omics modalities. Scbean represents a user-friendly Python library, designed to seamlessly incorporate a diverse array of models for the examination of single-cell data, encompassing both paired and unpaired multi-omics data. The library offers uniform and straightforward interfaces for tasks, such as dimensionality reduction, batch effect elimination, cell label transfer from well-annotated scRNA-seq data to scATAC-seq data, and the identification of spatially variable genes. Moreover, Scbean’s models are engineered to harness the computational power of GPU acceleration through Tensorflow, rendering them capable of effortlessly handling datasets comprising millions of cells. Availability and implementation Scbean is released on the Python Package Index (PyPI) (https://pypi.org/project/scbean/) and GitHub (https://github.com/jhu99/scbean) under the MIT license. The documentation and example code can be found at https://scbean.readthedocs.io/en/latest/.

show abstract

A multi-view latent variable model reveals cellular heterogeneity in complex tissues for paired multimodal single-cell data

Cited by 10 publications

References 63 publications

Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE

Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE

What is the cause(s) of ozone trends in three megacity clusters in eastern China during 2015–2020?

Scbean: a python library for single-cell multi-omics data analysis

Contact Info

Product

Resources

About