The DOI matches its Crossref record; 64 of the 65 references it cites were found in a registry or an index.
Using neural networks for reducing the dimensions of single-cell RNA-Seq data
Open accessPublished version of a preprint
Abstract
While only recently developed, the ability to profile expression data in single cells (scRNA-Seq) has already led to several important studies and findings. However, this technology has also raised several new computational challenges. These include questions about the best methods for clustering scRNA-Seq data, how to identify unique group of cells in such experiments, and how to determine the state or function of specific cells based on their expression profile. To address these issues we develop and test a method based on neural networks (NN) for the analysis and retrieval of single cell RNA-Seq data. We tested various NN architectures, some of which incorporate prior biological knowledge, and used these to obtain a reduced dimension representation of the single cell expression data. We show that the NN method improves upon prior methods in both, the ability to correctly group cells in experiments not used in the training and the ability to correctly infer cell type or state by querying a database of tens of thousands of single cell profiles. Such database queries (which can be performed using our web server) will enable researchers to better characterize cells when analyzing heterogeneous scRNA-Seq samples.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This idea was recently explored by Lin et al. (2017), who predicted cell type and state using a deep neural network for which the structure was determined based on the hierarchical organization of transcriptional regulatory factors in the nucleus.”
From Visible Machine Learning for Biomedicine (2018) · cites this paper as Lin et al., 2017
In the citing paper
“In contrast, direct incorporation of the biological structure of cells and tissues, such as explored by Lin et al. (2017) and Ma et al. (2018), leads to a ready-made working model of how biological inputs, such as genotype, are compressed to determine outcomes.”
From Visible Machine Learning for Biomedicine (2018) · cites this paper as Lin et al., 2017
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 1×
“These networks are universal function approximators (17) and, while training such networks takes longer than the unsupervised methods discussed above, they are very scalable in terms of training when using GPUs.”
BackgroundReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
(2010) · Cited by 14,134
(2016) · Cited by 11,679
NCBI GEO: archive for functional genomics data sets—update
Barrett, T., Wilhite, S. E., Ledoux, P., Evangelista, C., Kim, I. F., Tomashevsky, M., Marshall, K. A., Phillippy, K. H., Sherman, P. M., Holko, M., et al. (2012) · Nucleic Acids Research · doi:10.1093/nar/gks1193 · Cited by 10,418 · cited 2×
“We collected a total of 33 datasets with more than 17 000 single cell expression profiles from published papers and from the Gene Expression Omnibus (21) (GEO).”
MethodMultilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,266
Hubert, L., & Arabie, P. (1985) · Journal of Classification · doi:10.1007/bf01908075 · Cited by 8,219
(2007) · doi:10.5555/1283383.1283494 · Cited by 7,364
Trapnell, C., Cacchiarelli, D., Grimsby, J., Pokharel, P., Li, S., Morse, M., Lennon, N. J., Livak, K. J., Mikkelsen, T. S., & Rinn, J. L. (2014) · Nature Biotechnology · doi:10.1038/nbt.2859 · Cited by 7,314
Missing Value Estimation Methods for DNA Microarrays
Troyanskaya, O., Cantor, M., Sherlock, G., Brown, P., Hastie, T., Tibshirani, R., Botstein, D., & Altman, R. B. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.6.520 · Cited by 4,230
Flagged first, then by citations
1 of the 65 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 101–198 of 198
SLRRSC: Single-Cell Type Recognition Method Based on Similarity and Graph Regularization Constraints
Zhang, N.-N., Liu, J., Zheng, C.-H., & Wang, J. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3148286 · Cited by 16
“2) Data Processing: Data preprocessing methods include gene filter, imputation [14], [15], dimensionality reduction [39], [40], etc.”
MethodDiscovering Pathway and Cell Type Signatures in Transcriptomic Compendia with Machine Learning
Way, G. P., & Greene, C. S. (2019) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-072018-021348 · Cited by 13
“10 approach can also be used to predict cellular state and cell type (46).”
MethodCellular State Transformations Using Deep Learning for Precision Medicine Applications
Targonski, C., Bender, M. R., Shealy, B. T., Husain, B., Paseman, B., Smith, M. C., & Feltus, F. A. (2020) · Patterns · doi:10.1016/j.patter.2020.100087 · Cited by 14
Li, Z., Tang, C., Zheng, X., Li, Z., Zhang, W., & Cao, L. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.046 · Cited by 14
AI in Health Science: A Perspective
Mishra, R., Chaudhary, K., & Mishra, I. (2022) · Current Pharmaceutical Biotechnology · doi:10.2174/1389201023666220929145220 · Cited by 14
Application of Deep Learning for Single Cell Multi-Omics: A State-of-the-Art Review
Wani, S. A., Khan, S. A., & Quadri, S. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10230-x · Cited by 13
“Lin et al. [140], scDGN [141] implements DNN for reducing dimensions and Gundogdu et al. [142] uses DNN with biological pathway information for the reducing the dimensions.”
Identifying cell types from single-cell data based on similarities and dissimilarities between cells
Li, Y., Luo, P., Lu, Y., & Wu, F. (2021) · BMC Bioinformatics · doi:10.1186/s12859-020-03873-z · Cited by 11
“[15] incorporated prior biological knowledge to test various neural networks architectures and used these to obtain a reduced dimension representation of the single-cell expression data for identifying a unique group of cells.”
MethodDeep Learning Benchmarks on L1000 Gene Expression Data
McDermott, M. B. A., Wang, J., Zhao, W.-N., Sheridan, S. D., Peter Szolovits, B., Kohane, I. S., Haggarty, S. J., & Perlis, R. H. (2020) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2019.2910061 · Cited by 12
“In [32], the authors explore neural network mediated dimensionality reduction for single cell RNA-Seq data, augmenting traditional networks by adding nodes to the first hidden layer according to known transcription factor or protein-protein interactions, and only connecting input gene nodes to those…”
BackgroundChoi, J. M., Rhee, J., & Chae, H. (2021) · IEEE Access · doi:10.1109/access.2021.3052923 · Cited by 11
“For studies using scRNA-seq data, Lin, et al. employed DNN models combining prior biological information to reduce the dimensions of expression values, and evaluated performance by comparing their model to prior clustering and dimensionality reduction methods [33].”
MethodSingle-Cell RNA Sequencing: A New Window into Cell Scale Dynamics
Dasgupta, S., Bader, G. D., & Goyal, S. (2018) · Biophysical Journal · doi:10.1016/j.bpj.2018.07.003 · Cited by 12
“This approach has been successfully implemented on sequencing data sets using machine learning to build an algorithm that can learn and classify (55,56) and to describe states of memory in the context of neuroscience (57).”
MethodShallow Sparsely-Connected Autoencoders for Gene Set Projection
Gold, M. P., LeNail, A., & Fraenkel, E. (2018) · Pacific Symposium on Biocomputing (PSB) · doi:10.1142/9789813279827_0034 · Cited by 11
Innovation on Machine Learning in Healthcare Services—An Introduction
Pattnayak, P., & Panda, A. R. (2021) · Studies in computational intelligence · doi:10.1007/978-981-33-4698-7_1 · Cited by 10
NeuroDAVIS: A neural network model for data visualization
Maitra, C., Seal, D. B., & De, R. K. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127182 · Cited by 10
Computational tools for analyzing single-cell data in pluripotent cell differentiation studies
Ding, J., Alavi, A., Ebrahimkhani, M. R., & Bar‐Joseph, Z. (2021) · Cell Reports Methods · doi:10.1016/j.crmeth.2021.100087 · Cited by 10
scSSA: A clustering method for single cell RNA-seq data based on semi-supervised autoencoder
Zhao, J., Hou, T., Su, Y., et al. (2022) · Methods · doi:10.1016/j.ymeth.2022.10.006 · Cited by 10
Nature-Inspired Compressed Sensing for Transcriptomic Profiling From Random Composite Measurements
Zhang, S., Li, X., Lin, Q., & Wong, K. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2951402 · Cited by 10
Deep learning benchmarks on L1000 gene expression data
McDermott, M. B. A. (2019) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 10
Obimba, D. C., Esteva, C., Tsicheu, E. N. N., & Wong, R. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13174979 · Cited by 8
“They face difficulties when analyzing somatic cancer mutations [64], RNA sequencing data [65], methylation [66], and single cells [67].”
Backgroundde Weerd, H. A., Guala, D., Gustafsson, M., Synnergren, J., Tegner, J. N., Lubovac-Pilav, Z., & Magnusson, R. (2024) · Patterns · doi:10.1016/j.patter.2024.101093 · Cited by 10
Semi-Supervised Deep Learning for Cell Type Identification From Single-Cell Transcriptomic Data
Dong, X., Chowdhury, S., Victor, U., Li, X., & Qian, L. (2022) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2022.3173587 · Cited by 11
“Moreover, autoencoder techniques such as denoising autoencoder (DAE) [49] and variational autoencoder (VAE) [50] have also been applied to reduce dimensions of scRNAseq data [44], [49], [51].”
MethodArtificial Intelligent in Healthcare
Meiliana, A., Dewi, N. M., & Wijaya, A. (2019) · The Indonesian Biomedical Journal · doi:10.18585/inabj.v11i2.844 · Cited by 9
“Open-source algorithms mostly in single -omic approach are available for classifying or analyzing whole-genome sequence pathogenic variants (89-91), somatic cancer mutations (92), gene–gene interactions (93), RNA sequencing data (94), methylation (95), prediction of protein structure and protein–protein interactions (…”
BackgroundGCNG: Graph convolutional networks for inferring cell-cell interactionsPreprint
Yuan, Y., & Bar‐Joseph, Z. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2019.12.23.887133 · Cited by 9
“While the identification of pairwise interactions was the goal of several studies that relied on such methods, others used the results as features in a classification framework [15] or as pre-processing steps for the reconstruction of biological interaction networks [4].”
MethodWang, L., Nie, R., Zhang, J., & Cai, J. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-05098-8 · Cited by 7
Large-Scale Integrative Analysis of Soybean Transcriptome Using an Unsupervised Autoencoder Model
Su, L., Xu, C., Zeng, S., Su, L., Joshi, T., Stacey, G. S., & Xu, D. H. (2022) · Frontiers in Plant Science · doi:10.3389/fpls.2022.831204 · Cited by 7
Jiao, L., Ren, Y., Wang, L., Gao, C., Wang, S., & Song, T. (2023) · Frontiers in Genetics · doi:10.3389/fgene.2023.1179859 · Cited by 8
“Additionally, traditional clustering methods perform poorly in high dimensions due to the “ curse of dimensionality, ” while deep learning methods can convert high-dimensional raw scRNA-seq data into low-dimensional representations (Lin et al., 2017; Li et al., 2020).”
MethodFeng, H., Cottrell, S., Hozumi, Y., & Wei, G. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108211 · Cited by 8
“…scRNA-seq data include independent components analysis (ICA) [14], Laplacian eigenmaps [15], t-distributed stochastic neighbor embedding(t-SNE) [16], uniform manifoldapproximation and projection (UMAP) [17], deep learning methods [3,18], and non-negative matrix factorization (NMF) methods [19,20].”
MethodDeep Learning Models for Predicting Phenotypic Traits and Diseases from Omics Data
Islam, M. M., Wang, Y., & Hu, P. (2018) · InTech eBooks · doi:10.5772/intechopen.75311 · Cited by 9
“Using the CNA profiles of 991 and 984 patients as training and test sets, respectively, which was separated in original study [56 ] based on the patients collected at different periods, we classified the status of estrogen-receptor as a supervised binary classification problem.”
MethodJia, S., & Hu, P. (2021) · Genomics · doi:10.1016/j.ygeno.2021.04.037 · Cited by 8
Way, G. P., Zietz, M., Rubinetti, V., Himmelstein, D. S., & Greene, C. S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/573782 · Cited by 7
Raghavan, V., Zheng, Y., Li, Y., & Ding, J. (2025) · Genome Research · doi:10.1101/gr.279771.124 · Cited by 12
LRSK: a low-rank self-representation K -means method for clustering single-cell RNA-sequencing data
Sun, Y., Ou-Yang, L., & Dai, D. (2020) · Molecular Omics · doi:10.1039/d0mo00034e · Cited by 7
Shen, Y., Chu, Q., Timko, M. P., & Fan, L. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab410 · Cited by 7
AAE-SC: A scRNA-Seq Clustering Framework Based on Adversarial Autoencoder
Wu, Y., Guo, Y., Xiao, Y., & Lao, S. (2020) · IEEE Access · doi:10.1109/access.2020.3027481 · Cited by 7
“Lin et al. [37] tried to reduce the dimensions of scRNA-seq data by neural networks with prior biological knowledge.”
BackgroundExploring the optimization of autoencoder design for imputing single-cell RNA sequencing data
Xi, N. M., & Li, J. J. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.07.041 · Cited by 7
Review: Deep Learning-Based Survival Analysis of Omics and Clinicopathological Data
Sidorova, J., & Lozano, J. J. (2024) · Inventions · doi:10.3390/inventions9030059 · Cited by 6
“The method is biologically interpretable in the sense that input genes with high weights to the input nodes can be further analyzed with the methods designed to interpret gene function [30], such as the GO and KEGG.”
MethodGundogdu, P., Álamo-Álvarez, I., Nepomuceno-Chamorro, I. A., Dopazo, J., & Loucera, C. (2023) · Biology · doi:10.3390/biology12040579 · Cited by 6
“In the context of cell annotation [20] uses algorithmically crafted clusters of protein-protein and protein-DNA interactions to provide the sparse structure, but cannot classify unknown cells.”
BackgroundSupervised Adversarial Alignment of Single-Cell RNA-seq DataPreprint
Ge, S., Wang, H., Alavi, A., Xing, E., & Bar‐Joseph, Z. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.01.06.896621 · Cited by 5
Enhanced integration of single-cell multi-omics data using graph attention networks
Liao, X., Li, Y., Li, S., Wen, L., Li, X., & Yu, B. (2025) · ACS Synthetic Biology · doi:10.1021/acssynbio.4c00864 · Cited by 5
Tan, J., Xie, J., Huang, J., Deng, W., Chai, H., & Yang, Y. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.07.019 · Cited by 5
“Although machine learning algorithms have achieved widespread application and recognition in the biomedical field [21,22], they still face the specific challenge of lacking mechanistic interpretations [23, 24].”
BackgroundSupervised Adversarial Alignment of Single-Cell RNA-seq Data
Ge, S., Wang, H., Alavi, A., Xing, E. P., & Bar‐Joseph, Z. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45257-5_5 · Cited by 4
Deep learning for biomedical applications
Freitas, J. D., Glicksberg, B. S., Johnson, K. W., & Miotto, R. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-820273-9.00004-x · Cited by 4
MultiCapsNet: A General Framework for Data Integration and Interpretable Classification
Wang, L., Miao, X., Nie, R., Zhang, Z., Zhang, J., & Cai, J. (2021) · Frontiers in Genetics · doi:10.3389/fgene.2021.767602 · Cited by 4
Guo, X., Han, J., Song, Y., Yin, Z., Liu, S., & Shang, X. (2022) · Frontiers in Genetics · doi:10.3389/fgene.2022.921775 · Cited by 4
“This method evolved from the feature selection method proposed by Chieh Lin et al. (Lin et al., 2017), combined with SNP data characteristics.”
MethodscFED: Clustering Identifying Cell Types of scRNA-Seq Data Based on Feature Engineering Denoising
Liu, Y., Li, F., Shang, J., Liu, J., Wang, J., & Ge, D. (2023) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-023-00574-y · Cited by 4
“That is to say, while maintaining the real differences, the number of dimensions should be reduced as much as possible, and the original characteristics should be as closely as feasible projected to the dimensions with the most projected information [24].”
BackgroundMarucci, L., Barberis, M., Karr, J. R., Ray, O., Race, P. R., Andrade, M. D. S., Grierson, C., Hoffmann, S. A., Landon, S., Rech, E. L., et al. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00942 · Cited by 5
“, 2018) showed that deep neural networks are well placed to reconstruct the architecture of living systems [namely, the hierarchical organization of nuclear transcriptional factors in the nucleus (Lin et al., 2017) and of a basic eukaryotic cell (Ma et al.”
BackgroundA deep generative model for gene expression profiles from single-cell RNA sequencingPreprint
Lopez, R., Regier, J., Cole, M. B., Jordan, M. I., & Yosef, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.02082 · Cited by 12
A Hybrid Convolutional Network for Prediction of Anti-cancer Drug Response
Bai, J., Han, R., & Guo, C. (2021) · International Conference on Information Science and Technology · doi:10.1109/icist52614.2021.9440620 · Cited by 3
“The deep learning techniques have been successfully applied in the bioinformatics research of regulatory genomics, such as predicting binding motif [21], studying DNA variation [22], deciphering single-cell omics [23], and extracting genomic features for survival prediction [24].”
MethodAn End-to-End Deep Hybrid Autoencoder Based Method for Single-Cell RNA-Seq Data Analysis
Ji, C., Yu, N., Wang, Y., Qi, R., & Zheng, C.-H. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3328029 · Cited by 3
“The earliest methods are use traditional dimensionality reduction techniques and clustering methods, which usually first reduce the dimension and then apply baseline clustering methods such as k-means to low-dimensional data to identify cell types [6].”
MethodInnovation on Machine Learning in Healthcare Services–An Introduction
Pattnayak, P., & Jena, O. P. (2021) · Wiley eBooks · doi:10.1002/9781119792611.ch1 · Cited by 4
Sharma, P., Mishra, S. R., Kurban, H., & Dalkilic, M. M. (2025) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00709-4 · Cited by 2
“While successfully implemented in single-cell transcriptomics analyses [15, 16], t-SNE exhibits notable limitations: quadratic computational complexity O ( n 2 ) impeding scalability, stochastic initialization leading to non-deterministic outputs, and potential loss of global topological…”
MultiCapsNet: a interpretable deep learning classifier integrate data from multiple sourcesPreprint
Wang, L., Miao, X., Zhang, J., & Cai, J. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/570507 · Cited by 3
“In short, protein-protein interactions (PPI) information store in BIOGRID[20] and HPRD[21], and protein-DNA interactions (PDI) comes from [22], are used as prior knowledge to specify network connections [9].”
BackgroundMethodInfluentialStatistical Methods for Single‐Cell RNA‐Sequencing
Andrews, T. S., Kiselev, V. Y., & Hemberg, M. (2019) · Wiley eBooks · doi:10.1002/9781119487845.ch26 · Cited by 2
Cell Type Identification from Single-Cell Transcriptomic Data via Semi-supervised LearningPreprint
Dong, X., Chowdhury, S., Victor, U., Li, X., & Qian, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.03994 · Cited by 2
“Moreover, autoencoder techniques such as denoising autoen-coder (DAE) [33] and variational autoencoder (VAE) [34] have also been applied to reduce dimensions of scRNAseq data [28], [33], [35].”
MethodDeepFoldit -- A Deep Reinforcement Learning Neural Network Folding ProteinsPreprint
Panou, D. N., & Reczko, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03442 · Cited by 5
Zhu, Q., Li, A., Zhang, Z., Zheng, C., Zhao, J., Liu, J., Zhang, D., & Shao, W. (2024) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3487574 · Cited by 1
Human genetics across levels of biological organization
Trip, D. S. L., & Beltrão, P. (2026) · Nature Reviews Genetics · doi:10.1038/s41576-026-00991-x · Cited by 2
Wang, Y., & Yang, B. (2020) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai50040.2020.00109 · Cited by 1
“T-distributed random neighbor embedding (t-SNE) [8] is a non-linear dimensionality reduction technique, which has recently been used to reduce the dimensionality of single-cell sequencing data [6], [7].”
MethodTrannscriptomics and Immune Response in Human Cancer
Chaves, L. P., Melo, C. M., Lautert-Dutra, W., Caliari, A. L., & Squire, J. A. (2022) · Springer eBooks · doi:10.1007/978-3-030-87821-4_13 · Cited by 1
Computational Analysis of DNA and RNA Sequencing Data Obtained from Liquid Biopsies
Marass, F., Castro-Giner, F., Szczerba, B. M., Jahn, K., Kuipers, J., Aceto, N., & Beerenwinkel, N. (2019) · Recent results in cancer research/Recent Results in Cancer Research · doi:10.1007/978-3-030-26439-0_18 · Cited by 1
Can artificial neural replicators be useful for studying RNA replicators?
Ezhov, A. A. (2020) · Archives of Virology · doi:10.1007/s00705-020-04779-0 · Cited by 1
Methods of Identifying Cell Type from Single Cell RNA-seq Data and the Interpretation
Zhang, W., Jin, W., & Yang, J. (2020) · International Conference on Mechanical, Control and Computer Engineering (ICMCCE) · doi:10.1109/icmcce51767.2020.00367 · Cited by 1
ScSSC: Semi-supervised Single Cell Clustering Based on 2D Embedding
Shi, N., Wu, Y., Du, L., Liu, B., Wang, Y., & Li, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-84532-2_43 · Cited by 1
DCA-CLA: A scRNA-seq Classification Framework based on Deep Count Autoencoder
Wu, Y., Guo, Y., Li, J., Lao, S., Guo, J., & Wang, H. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533488 · Cited by 1
Guo, J., & Gao, J. (2022) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp54964.2022.9778439 · Cited by 1
Cellular State Transformations using Generative Adversarial NetworksPreprint
Targonski, C., Shealy, B. T., Smith, M. C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.00118 · Cited by 1
“Modern machine learning and deep learning approaches have begun to surmount these obstacles and are increasingly used to cluster and classify gene expression profiles into meaningful groups that correspond with metadata labels [2, 3, 4].”
BackgroundDeveloping machine learning tools to understand transcriptional regulation in plants
Song, Q. (2019) · VTechWorks (Virginia Tech) · Cited by 1
MCNET: Multi-Omics Integration for Gene Regulatory Network Inference from scRNA-seqPreprint
Tiwari, A., & Trankatwar, S. (2023) · medRxiv · doi:10.1101/2023.05.29.23290691 · Cited by 3
“A previous study by (Lin et al., 2017) showed that more accurate cell representations could be achieved by guiding the neural network architecture with a GRN structure derived from the literature and databases.”
MethodGraSP Gene Targets to Hierarchically Infer Sub-Classes with CuttleNetPreprint
Budoff, S. A., & Poleg-Polsky, A. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.04.26.591410 · Cited by 1
“For example, Lin et al. [16] successfully used NNs for scRNAseq data clustering.”
MethodWall, M. K., Dreisbach, C., Zaidi, A. H., Flower, A. A., & Overall, C. C. (2018) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds.2018.8374718
“Previous studies have attempted to discern cell type and sub-population characteristics, but these have focused largely on linear methods in bulk cell samples [1], [4]-[7].”
BackgroundRedes Neurais Multicamadas Perceptron na Identificação de Proteínas Efetoras
da Silva, G. J., da Silva, R. G. T. M., & Remédio, R. V. D. C. (2018) · doi:10.5753/encompif.2018.3564
Janßen, R., Zabel, J., von Lukas, U. F., et al. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/711309
“The general principle was already demonstrated by Lin et al. (2017) who, employing a CNN, improved the assignment of single-cell RNAseq reads to their cell types of origin.”
BackgroundNetskar, H. (2019) · NORA - Norwegian Open Research Archives
scCapsNet-mask: an automatic version of scCapsNetPreprint
Wang, L., Zhang, J., & Cai, J. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.11.02.365346
Deep Denoising Subspace Single-Cell Clustering
Wang, Y., & Yang, B. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63823-8_36
Jia, S. (2020) · Mspace (University of Manitoba)
Interpretation of Biological Data at a Glance
Cho, S. (2020) · Journal of Biotechnology and Bioindustry · doi:10.37503/jbb.2020.8.38
Automated Cell Recognition using Single-cell RNA Sequencing with Machine Learning
Xu, C., Chen, Y., & Cao, Y. (2021) · International Conference on Computational Biology and Bioinformatics (ICCBB) · doi:10.1145/3512452.3512455
“Based on this classification evidence, Chieh Lin et al. [2.] constructs a shallow-layered fully connected neural network to predict the labels, and it can even correctly group cells not included in the training.”
MethodWang, L., Nie, R., Zhang, J., & Cai, J. (2022) · Research Square · doi:10.21203/rs.3.rs-1763879/v1
Determination of Neuron Activation States Facilitated by Artificial Intelligence
Topasna, A., Xie, E., Park, S., Huang, S. W., Wu, X., & Xie, H. (2022) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm55620.2022.9995647
“For instance, Lin, et al. examined the effectiveness of four different ANN architectures to identify different cell types [12].”
BackgroundSingle Cell Type Prediction from Gene Profiles - An Overview of Different Computational Methods
Li, J., Liu, X., & Xu, K. (2023) · Applied and Computational Engineering · doi:10.54254/2755-2721/2/20220532
A Survey of Survival Analysis with Deep Learning: Models, Applications and ChallengesPreprint
Sidorova, J., & Lozano, J. J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4488863
Saeed, S., Hussain, M., Naqvi, M., et al. (2023) · Advances in intelligent systems and computing · doi:10.1007/978-981-99-3611-3_28
Vis-SPLIT: Interactive Hierarchical Modeling for mRNA Expression Classification
Roper, B., Mathews, J. C., Nadeem, S., & Park, J. H. (2023) · Visualization · doi:10.1109/vis54172.2023.00030
“Some machine learning techniques have found some success in improving classifications by training data-driven models [4, 5, 17].”
BackgroundRecent advances in computational modeling
Pinky, P., Neha, N., & Parvez, S. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13222-3.00006-x
Denoising autoencoder-based soft K-medoid clustering for single-cell RNA sequence data
Zihad, Z. A. K., Ahamed, M. F., & Islam, R. (2024) · International Conference on Computing Advancements (ICCA) · doi:10.1145/3723178.3723263
“Through the utilization of the ZINB model’s properties and their integration into the autoencoder’s design and loss function, this method permits reliable parameter estimation and efficient denoising of scRNA-seq data for subsequent examination and comprehension[19].”
Network-Guided Sparse Subspace Clustering on Single-Cell Data
Yuan, C., Jiang, S., Li, S., Fan, J., & Yu, T. (2025) · Journal of Computational Biology · doi:10.1177/15578666251359688
“CIDR (Clustering through Imputation and Dimensionality Reduction) (Lin et al., 2017) and scImpute (Li and Li, 2018) improve clustering performance by imputing dropout events in scRNA-seq data.”
Li, W., Li, X., Guo, W., Gu, B., Du, J., Chi, N., Shao, D., Xiao, K. J., & Mo, R. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1661318 · Cited by 1
Way, G. P., Zietz, M., Rubinetti, V., Himmelstein, D. S., & Greene, C. S. (2020) · Figshare · doi:10.6084/m9.figshare.12285521
Wang, L., Nie, R., Zhang, J., & Cai, J. (2024) · Figshare · doi:10.6084/m9.figshare.26553392
Yuan, Y., & Bar‐Joseph, Z. (2020) · Figshare · doi:10.6084/m9.figshare.13364592
Yuan, Y., & Bar‐Joseph, Z. (2020) · Figshare · doi:10.6084/m9.figshare.13364595
Way, G. P., Zietz, M., Rubinetti, V., Himmelstein, D. S., & Greene, C. S. (2020) · Figshare · doi:10.6084/m9.figshare.12285494
Way, G. P., Zietz, M., Rubinetti, V., Himmelstein, D. S., & Greene, C. S. (2020) · Figshare · doi:10.6084/m9.figshare.12285500
Gundogdu, P., Loucera, C., Álamo-Álvarez, I., Dopazo, J., & Nepomuceno, I. (2022) · DIGITAL.CSIC (Spanish National Research Council (CSIC)) · doi:10.6084/m9.figshare.17798457
Anas, M., Basri, S., Chaurasiya, N., & Ali, M. (2026) · CABI biotechnology series. · doi:10.1079/9781800628649.0007 · Cited by 1
Unsupervised representation learning for single-cell transcriptomic and epigenomic data
Raimundo, F. (2022) · theses.fr (ABES) · doi:10.70675/760cd5d0z17c6z4f4ezb476z68bd387daf22
Kontolati, K., Gladstone, R. J., Davis, I., & Pickering, E. M. (2026) · The Plant Journal · doi:10.1111/tpj.71076 · Cited by 3
“Lin et al. (2017) used biologically sparse networks for dimensionality reduction of single-cell RNA-Seq data, finding they outperformed fully connected models.”
AI integration with omics and CRISPR to decipher complex traits in plants
Talakayala, A., Mediga, K. R., Naik, S. R., & Mallikarjuna, G. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44079-3.00015-2
Metadata
- Authors
- Lin, C., Jain, S., Kim, H., & Bar-Joseph, Z.
- Affiliations
- Carnegie Mellon University (US)
- Machine Learning Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA
- Venue
- Nucleic Acids Research
- Publisher
- Oxford University Press (OUP)
- Published
- 2017-07-31
- Volume
- 45
- Issue
- 17
- Pages
- e156-e156
- ISSN
- 0305-1048 (ISSN-L)
- 1362-4962
- PMC
- PMC5737331
- OpenAlex
- W2741564801
- Semantic Scholar
- c4d33e602615608d29bb296591591fe4e51b7bf2
- Cited by
- 197
- References
- 65
- Citations by year
- 2026: 4 · 2025: 8 · 2024: 15 · 2023: 14 · 2022: 21 · 2021: 31 · 2020: 43 · 2019: 37 · 2018: 23 · 2017: 1
- FWCI
- 11.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Nucleic Acids Research (publishedVersion, cc-by-nc)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Funders
- National Science Foundation (1356505)
- National Institutes of Health
- National Heart, Lung, and Blood Institute (U01HL122626)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Keywords
- single-cell RNA sequencing, dimensionality reduction, artificial neural networks, cell clustering, cell type annotation, heterogeneous cell populations, web server
- MeSH terms
- Gene Expression Regulation, Humans, RNA, Software, Cluster Analysis, Neural Networks, Computer, Sequence Analysis, RNA, Computational Biology, Gene Expression Profiling, Protein Interaction Mapping, Databases, Genetic, Multifactor Dimensionality Reduction, Single-Cell Analysis, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
