scDeepHash: An automatic cell type annotation and cell retrieval method for large-scale scRNA-seq datasets using neural network-based hashing
Ma, S.; Zhang, Y.; Wang, B.; Hu, Z.; Zhang, J.; Wang, B.
Show abstract
Single-cell RNA-sequencing technologies measure transcriptomic expressions, which quantifies cell-to-cell heterogeneity at an unprecedented resolution. As these technologies become more readily available, the number of scRNA-seq datasets increases drastically. Prior works have demonstrated that bias-free, holistic single-cell profiling infrastructures are essential to the emerging automatic cell-type annotation methods. We propose scDeepHash, a scalable scRNA-seq analytic tool that employs content-based deep hashing to index single-cell gene expressions. scDeepHash allows for fast and accurate automated cell-type annotation and similar-cell retrieval. We also demonstrate the performance of scDeepHash by benchmarking it against current state-of-the-art methods across multiple public scRNA-seq datasets.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Graph Contrastive Learning as a Versatile Foundation for Advanced scRNA-seq Data Analysis 97%
- A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification 97%
- Graph Contrastive Learning of Subcellular-resolution Spatial Transcriptomics Improves Cell Type Annotation and Reveals Critical Molecular Pathways 97%
Similar papers in this journal
- scDesign2: a transparent simulator that generates high-fidelity single-cell gene expression count data with gene correlations captured 96%
- Learning latent embedding of multi-modal single cell data and cross-modality relationship simultaneously 96%
- Sequences Dimensionality-Reduction by K-mer Substring Space Sampling Enables Effective Resemblance- and Containment-Analysis for Large-Scale omics-data 96%
Similar papers in this journal
- scGCN: a Graph Convolutional Networks Algorithm for Knowledge Transfer in Single Cell Omics 97%
- CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells 96%
- Deep autoencoder for interpretable tissue-adaptive deconvolution and cell-type-specific gene analysis 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.