AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders

Xu, Li; Xu, Yin; Xue, Ting; Zhang, Xinyu; Li, Jin

doi:10.3389/fgene.2021.739677

Cited by 12 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…While the number of missing values may be inflated by technical issues 52 , this is simply a function of the technique, and all informatics pipelines have ways to compensate or utilize zero values. [53][54][55] Optimized methods for pasefRiQ can provide quantifiable data over an extremely wide dynamic range as demonstrated by the accurate quantification values obtained for the TNAa E. coli protein was observed in the 9 technical replicates of 2.4 ng on column. As each labeled peptide channel contributes to the total peptide load on column, approximately 267 picograms of peptide are present in each of the 9 TMT channels.…”

mentioning

confidence: 98%

See 1 more Smart Citation

Single Cell Proteomics Using a Trapped Ion Mobility Time-of-Flight Mass Spectrometer Provides Insight into the Post-translational Modification Landscape of Individual Human Cells

Orsburn

Yuan

Bumpus

2022

Preprint

View full text Add to dashboard Cite

Single cell proteomics is a powerful tool with potential for markedly enhancing understanding of cellular processes. Previously reported single cell proteomics innovations employ Orbitrap mass spectrometers. In this study we describe the development, optimization, and application of multiplexed single cell proteomics to the analysis of human-derived cells using trapped ion mobility time-of-flight mass spectrometry. This method, denoted as pasefRiQ is an advance as it allows accurate peptide quantification as demonstrated by a two-proteome standard model, with little variation in accuracy in samples at picogram peptide concentrations. When employing a peptide carrier channel to boost protein sequence coverage, we obtain over 40,000 tandem mass spectra in 30 minutes, providing unprecedented sequence coverage of each identified protein. Using NCI-H-358 cells, which are a human bronchioalveolar carcinoma and KRASG12C model cell line, we demonstrate that the level of coverage achieved using this method enables the quantification of up to 1,255 proteins per cell and the detection of multiple classes of post-translational modifications in single cells. Further, when the cells were treated with AMG510, a KRASG12C covalent inhibitor, pasefRiQ revealed cell-to-cell variability in the impact of the drug on the NCI-H-358 proteome. In fact, when examining proteins that changed in protein abundance in response to AMG510 we can identify those that are disproportionately increased or decreased in a small number of cells relative to the total population of cells that were cultured and treated simultaneously. These results suggest single cell proteomics through pasefRiQ can provide powerful insight for cellular and drug mechanism studies.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 98%

Single Cell Proteomics Using a Trapped Ion Mobility Time-of-Flight Mass Spectrometer Provides Insight into the Post-translational Modification Landscape of Individual Human Cells

Orsburn

Yuan

Bumpus

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Rarefaction curves were estimated using the R package vegan (Oksanen et al, 2020). The relative abundances of MAGs were calculated using the mean coverage across the MAG and then normalised using the length of the MAG using TMP normalisation with the R package ADI-impute(Xu et al, 2021) . Microbiota composition analyses was performed using the R package phyloseq (McMurdie & Holmes, 2013) .…”

Section: Methodsmentioning

confidence: 99%

Sampling the Zebrafish gut Microbiota – A Genome Resolved Metagenomic Approach

Thormar,

Hansen,

Jørgensen

et al. 2023

Preprint

View full text Add to dashboard Cite

The zebrafish is a promising model organism in the field of functional microbiota research. However, studies on the functional landscape of the zebrafish gut microbiota through shotgun based metagenomics are scarce. Thus, there is a lack of consensus regarding an appropriate sampling method that accurately represents the zebrafish gut microbiota. To address this, we sought to systematically test and evaluate four different methods of sampling the zebrafish gut microbiota: collection of feces from the tank, the whole gut, intestinal content and the application of ventral pressure to facilitate extrusion of gut material. In addition, we included water samples as an environmental control to address the potential influence of the environmental microbiota on the data interpretation. To compare these sampling methods in a context of microbiota-based studies we employed a combination of genome resolved metagenomics and 16S metabarcoding techniques. We observed differences among sample types on all levels including sampling, bioinformatic processing, metagenome co-assemblies, generation of metagenome-assembled genomes (MAGs), functional potential, MAG coverage and micro-diversity. Furthermore, our comparison to the environmental control demonstrated the potential impact of the environmental contamination on data interpretation. The findings emphasise the importance of considering the choice of sampling method. While all sample types tested are informative about the zebrafish gut microbiota, the optimal sample type depends on the specific objectives of the study.

show abstract

“…However, they are usually computationally intensive and limited in capturing non-linearity in scRNA-seq data. To better address this issue, deep learning approaches have been developed for scRNA-seq data imputation and denoising [37] , [38] , [39] , [40] , [41] , [42] , [43] , [44] , [45] , [46] , [47] , [48] , [49] . Based on an idea similar to regression imputation [50] , i.e.…”

Section: Applications Of Deep Learning In Scrna-seq Data Analysismentioning

confidence: 99%

Application of Deep Learning on Single-Cell RNA Sequencing Data Analysis: A Review

Brendel

Bai

et al. 2022

Genomics, Proteomics &Amp; Bioinformatics

View full text Add to dashboard Cite

Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.

show abstract

AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders

Cited by 12 publications

References 24 publications

Single Cell Proteomics Using a Trapped Ion Mobility Time-of-Flight Mass Spectrometer Provides Insight into the Post-translational Modification Landscape of Individual Human Cells

Single Cell Proteomics Using a Trapped Ion Mobility Time-of-Flight Mass Spectrometer Provides Insight into the Post-translational Modification Landscape of Individual Human Cells

Sampling the Zebrafish gut Microbiota – A Genome Resolved Metagenomic Approach

Application of Deep Learning on Single-Cell RNA Sequencing Data Analysis: A Review

Contact Info

Product

Resources

About