Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

scAMZI: attention-based deep autoencoder with zero-inflated layer for clustering scRNA-seq data.

Lin Yuan^1,2,3, Zhijie Xu^1,2,3, Boyuan Meng^1,2,3

¹Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), 3501 Daxue Road, Jinan, 250353, China.

|April 8, 2025

Summary

Related Concept Videos

RNA-seq

RNA-seq

RNA sequencing, or RNA-Seq, is a high-throughput sequencing technology used to study the transcriptome of a cell. Transcriptomics helps to interpret the functional elements of a genome and identify the molecular constituents of an organism. Additionally, it also helps in understanding the development of an organism and the occurrence of diseases.
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Extraction and characterization of microcrystalline cellulose from kelp (Laminaria japonica) waste.

PloS one·2026

Same author

A mechanism of target mRNA selection and activity regulation in meiosis-related RBM46-MEIOC-YTHDC2 complex.

iScience·2026

Same author

Do We Need to Monitor B-Vitamins and Homocysteine During Initiation of Foslevodopa/Foscarbidopa Therapy?

Movement disorders : official journal of the Movement Disorder Society·2026

Same author

Blood pressure variability plays a critical role in determining the prognosis of acute ischemic stroke combined with hypertension.

Frontiers in neurology·2026

Same author

Long-term LDL cholesterol burden and stroke: mechanistic insights and emerging strategies for personalized lipid management.

Frontiers in neurology·2026

Same author

When bad turns good: a systematic review on cholesterol and LDL in longitudinal patient cohorts with Parkinson's disease.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2026

Same journal

Genome-wide analysis across Indian camel populations reveals genetic distinctiveness of the Kharai camel breed.

BMC genomics·2026

Same journal

Different genomic footprint of small insertion-deletion and structural variants determines the genetic divergence of indica and japonica rice.

BMC genomics·2026

Same journal

From nurse bee to queen egg: RNA-seq analysis of Apis mellifera eggs shows dietary protein-dependent gene regulation.

BMC genomics·2026

Same journal

A genome-wide association study to identify the genetic loci underlying carbapenem resistance in Acinetobacter baumannii.

BMC genomics·2026

Same journal

Comparative transcriptome analysis to reveal key drought stress-responsive genes in sorghum (Sorghum bicolor (L.) Moench).

BMC genomics·2026

Same journal

Tissue identity is the dominant determinant of cross-species transferability of a porcine developmental programme.

BMC genomics·2026

See all related articles

This summary is machine-generated.

scAMZI, a novel deep learning model, effectively clusters single-cell RNA sequencing (scRNA-seq) data by integrating cellular features and relationships while addressing dropout events. This advanced method outperforms existing approaches for scRNA-seq analysis.

Area of Science:

Computational biology
Bioinformatics
Genomics

Background:

Clustering single-cell RNA sequencing (scRNA-seq) data is crucial for biological discovery.
Existing methods often fail to fully leverage cellular features, intercellular relationships, and are susceptible to data sparsity (dropout events).

Purpose of the Study:

To introduce scAMZI, a novel deep learning model for enhanced scRNA-seq data clustering.
To address limitations of current methods by integrating cellular features, intercellular relationships, and handling dropout events.

Main Methods:

scAMZI utilizes an attention autoencoder with a zero-inflated (ZI) layer.
Key components include SimAM (Simple, parameter-free Attention Module), autoencoder, and a Zero-Inflated Negative Binomial (ZINB) model.

Keywords:

Autoencoder Clustering scRNA-seq data SimAM ZINB model Zero-inflated layer

Related Experiment Videos

The model reduces dimensionality, learns cell representations and relationships, and specifically handles zero values inherent in scRNA-seq data.

Main Results:

scAMZI was evaluated against nine other methods on fourteen diverse scRNA-seq datasets.
The model demonstrated superior performance across datasets of varying sizes.
Experimental results confirm scAMZI's effectiveness in clustering scRNA-seq data.

Conclusions:

scAMZI surpasses existing methods in scRNA-seq data clustering.
The model facilitates downstream analyses including cell annotation, marker gene discovery, and trajectory inference.
The scAMZI package is publicly available for research use.