pith. machine review for the scientific record. sign in

arxiv: 2603.24626 · v2 · submitted 2026-03-25 · 🧬 q-bio.GN · cs.LG· stat.ML

Recognition: no theorem link

A Large-Scale Comparative Analysis of Imputation Methods for Single-Cell RNA Sequencing Data

Yuichiro Iwashita , Ahtisham Fazeel Abbasi , Koichi Kise , Andreas Dengel , Muhammad Nabeel Asim
Authors on Pith no claims yet

Pith reviewed 2026-05-15 01:15 UTC · model grok-4.3

classification 🧬 q-bio.GN cs.LGstat.ML
keywords scRNA-seqimputationdropoutbenchmarktraditional methodsdeep learningdownstream analysisgene expression
0
0 comments X

The pith

Traditional statistical methods generally outperform deep learning approaches when imputing dropout events in single-cell RNA sequencing data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper benchmarks 15 imputation methods spanning traditional statistical models and deep learning techniques across 30 datasets drawn from 10 experimental protocols. It shows that model-based, smoothing-based, and low-rank matrix methods recover gene expression values more accurately than diffusion-based, GAN-based, GNN-based, or autoencoder-based methods. Numerical recovery success does not reliably translate into better results on biological tasks such as cell clustering, differential expression, or trajectory inference. No method wins consistently across all datasets and analyses, so selection should be driven by the specific downstream objective rather than a universal ranking.

Core claim

Across 30 datasets from 10 protocols, traditional imputation methods such as model-based, smoothing-based, and low-rank matrix-based approaches generally outperform deep learning-based methods including diffusion-based, GAN-based, GNN-based, and autoencoder-based methods. Strong numerical recovery of gene expression does not necessarily improve biological interpretability in downstream analyses including cell clustering, differential expression analysis, marker gene analysis, trajectory analysis, and cell type annotation. Method performance varies substantially across datasets, protocols, and analyses, with no single method consistently outperforming the others.

What carries the argument

Large-scale comparative benchmark of 15 methods across 30 datasets and 6 downstream analyses.

Load-bearing premise

The 30 chosen datasets from 10 protocols and the 6 downstream analyses are representative enough to support broad claims about method superiority.

What would settle it

A new benchmark on an independent collection of datasets or protocols in which deep learning methods consistently exceed traditional methods on both numerical recovery and downstream biological metrics would refute the central claim.

read the original abstract

Background: Single-cell RNA sequencing (scRNA-seq) enables gene expression profiling at cellular resolution but is inherently affected by sparsity caused by dropout events, where expressed genes are recorded as zeros due to technical limitations. These artifacts distort gene expression distributions and compromise downstream analyses. Numerous imputation methods have been proposed to recover latent transcriptional signals. These methods range from traditional statistical models to deep learning (DL)-based methods. However, their comparative performance remains unclear, as existing benchmarks evaluate only a limited subset of methods, datasets, and downstream analyses. Results: We present a comprehensive benchmark of 15 scRNA-seq imputation methods spanning 7 methodological categories, including traditional and DL-based methods. Methods are evaluated across 30 datasets from 10 experimental protocols on 6 downstream analyses. Results show that traditional methods, such as model-based, smoothing-based, and low-rank matrix-based methods, generally outperform DL-based methods, including diffusion-based, GAN-based, GNN-based, and autoencoder-based methods. In addition, strong performance in numerical gene expression recovery does not necessarily translate into improved biological interpretability in downstream analyses, including cell clustering, differential expression analysis, marker gene analysis, trajectory analysis, and cell type annotation. Furthermore, method performance varies substantially across datasets, protocols, and downstream analyses, with no single method consistently outperforming others. Conclusions: Our findings provide practical guidance for selecting imputation methods tailored to specific analytical objectives and underscore the importance of task-specific evaluation when assessing imputation performance in scRNA-seq data analysis.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript presents a large-scale empirical benchmark of 15 scRNA-seq imputation methods spanning 7 categories (traditional and DL-based) evaluated on 30 datasets from 10 experimental protocols across 6 downstream analyses. It claims that traditional methods (model-based, smoothing-based, low-rank matrix-based) generally outperform DL-based methods (diffusion-based, GAN-based, GNN-based, autoencoder-based), that strong numerical gene-expression recovery does not necessarily translate to improved performance in biological downstream tasks, and that method performance varies substantially across datasets, protocols, and tasks with no single method consistently best.

Significance. If the benchmark design and aggregation are robust, the work supplies useful practical guidance for method selection in scRNA-seq pipelines and underscores the value of task-specific rather than purely numerical evaluation. The scale (30 datasets, 10 protocols, 6 tasks) is a clear strength relative to prior narrower comparisons.

major comments (2)
  1. [Abstract] Abstract: The category-level claim that traditional methods 'generally outperform' DL-based methods is not supported by any reported aggregate statistics (win rates, mean ranks, or statistical tests across the 30 datasets), especially given the explicit statement that performance 'varies substantially' and 'no single method consistently outperforming others.' Without these quantifications the 'generally' qualifier cannot be evaluated.
  2. [Results] Results/Datasets section: The justification for selecting the 10 protocols and 30 datasets is absent; if these protocols share correlated technical features (dropout patterns, sequencing depth distributions, or gene-count characteristics), the observed category advantage may be selection-dependent rather than intrinsic, undermining the generalizability of the superiority conclusion.
minor comments (2)
  1. [Methods] Methods: Provide explicit definitions of all evaluation metrics, the precise statistical procedures used for method comparisons, and whether error bars or confidence intervals are shown in any figures or tables.
  2. [Abstract] Abstract and Results: List the exact 15 methods and their category assignments early to improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below and indicate the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The category-level claim that traditional methods 'generally outperform' DL-based methods is not supported by any reported aggregate statistics (win rates, mean ranks, or statistical tests across the 30 datasets), especially given the explicit statement that performance 'varies substantially' and 'no single method consistently outperforming others.' Without these quantifications the 'generally' qualifier cannot be evaluated.

    Authors: We agree that the abstract's use of 'generally outperform' requires quantitative support to be defensible. In the revised manuscript we will add aggregate metrics (mean ranks, win rates across the 30 datasets, and paired statistical tests such as Wilcoxon signed-rank tests on key performance measures) comparing the traditional and DL categories. These statistics will be reported in the abstract, a new summary table, and the Results section, while retaining the statements that performance varies substantially and that no single method is universally best. revision: yes

  2. Referee: [Results] Results/Datasets section: The justification for selecting the 10 protocols and 30 datasets is absent; if these protocols share correlated technical features (dropout patterns, sequencing depth distributions, or gene-count characteristics), the observed category advantage may be selection-dependent rather than intrinsic, undermining the generalizability of the superiority conclusion.

    Authors: We acknowledge the omission. In the revision we will add a dedicated paragraph in the Datasets subsection that explicitly states the selection criteria: coverage of major experimental protocols (droplet-based, plate-based, etc.), variation in dataset size, sparsity, sequencing depth, and biological context (species and tissue types). We will also include summary statistics on technical features across the 30 datasets and discuss how this diversity supports broader applicability. A brief sensitivity analysis excluding highly similar protocol subsets can be added if space permits. revision: yes

Circularity Check

0 steps flagged

No circularity: purely empirical benchmark on external data

full rationale

The paper conducts a large-scale empirical comparison of 15 imputation methods across 30 independent datasets and 6 downstream tasks using standard metrics. No derivations, fitted parameters, or self-referential equations are present; performance rankings emerge directly from external data rather than from any internal definition or self-citation chain. The central claim (traditional methods generally outperform DL methods) is an aggregate observation, not a constructed result. Minor self-citations, if any, are not load-bearing for the benchmark conclusions.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an empirical comparative study with no mathematical derivations, free parameters fitted to produce the central claim, or new postulated entities; all content rests on standard statistical evaluation practices and publicly available scRNA-seq datasets.

pith-pipeline@v0.9.0 · 5599 in / 1177 out tokens · 35678 ms · 2026-05-15T01:15:13.299422+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

121 extracted references · 121 canonical work pages · 2 internal anchors

  1. [1]

    Nature Methods6(5), 377–382 (2009) https://doi.org/10.1038/nmeth.1315

    Tang, F., Barbacioru, C., Wang, Y., Nordman, E., Lee, C., Xu, N., Wang, X., Bodeau, J., Tuch, B.B., Siddiqui, A., Lao, K., Surani, M.A.: mRNA-Seq whole- transcriptome analysis of a single cell. Nature Methods6(5), 377–382 (2009) https://doi.org/10.1038/nmeth.1315

    work page doi:10.1038/nmeth.1315 2009

  2. [2]

    Molecular Systems Biology15(6), 188746 (2019) https://doi

    Luecken, M.D., Theis, F.J.: Current best practices in single-cell RNA-seq anal- ysis: A tutorial. Molecular Systems Biology15(6), 188746 (2019) https://doi. org/10.15252/msb.20188746

    work page doi:10.15252/msb.20188746 2019

  3. [3]

    Computational Biology and Chemistry115, 108362 (2025) https://doi.org/10

    Rafi, F.R., Heya, N.R., Hafiz, M.S., Jim, J.R., Kabir, M.M., Mridha, M.F.: A systematic review of single-cell RNA sequencing applications and innovations. Computational Biology and Chemistry115, 108362 (2025) https://doi.org/10. 1016/j.compbiolchem.2025.108362

    work page arXiv 2025

  4. [4]

    Cells12(15), 1970 (2023) https://doi.org/10.3390/cells12151970

    Cheng,C.,Chen,W.,Jin,H.,Chen, X.:AReviewof Single-CellRNA-SeqAnno- tation, Integration, and Cell–Cell Communication. Cells12(15), 1970 (2023) https://doi.org/10.3390/cells12151970

    work page doi:10.3390/cells12151970 1970

  5. [5]

    Hwang, B., Lee, J.H., Bang, D.: Single-cell RNA sequencing technologies and bioinformaticspipelines.Experimental&MolecularMedicine50(8),1–14(2018) https://doi.org/10.1038/s12276-018-0071-8

    work page doi:10.1038/s12276-018-0071-8 2018

  6. [6]

    Molecular Cell 58(4), 610–620 (2015) https://doi.org/10.1016/j.molcel.2015.04.005

    Kolodziejczyk, A.A., Kim, J.K., Svensson, V., Marioni, J.C., Teichmann, S.A.: The Technology and Biology of Single-Cell RNA Sequencing. Molecular Cell 58(4), 610–620 (2015) https://doi.org/10.1016/j.molcel.2015.04.005

    work page doi:10.1016/j.molcel.2015.04.005 2015

  7. [7]

    Clinical and Translational Medicine12(3), 694 (2022) https://doi.org/10.1002/ctm2.694

    Jovic, D., Liang, X., Zeng, H., Lin, L., Xu, F., Luo, Y.: Single-cell RNA sequenc- ing technologies and applications: A brief overview. Clinical and Translational Medicine12(3), 694 (2022) https://doi.org/10.1002/ctm2.694

    work page doi:10.1002/ctm2.694 2022

  8. [8]

    Nature Communications8(1), 14049 (2017) https://doi.org/10.1038/ncomms14049

    Zheng, G.X.Y., Terry, J.M., Belgrader, P., Ryvkin, P., Bent, Z.W., Wilson, R., Ziraldo, S.B., Wheeler, T.D., McDermott, G.P., Zhu, J., Gregory, M.T., Shuga, 48 J., Montesclaros, L., Underwood, J.G., Masquelier, D.A., Nishimura, S.Y., Schnall-Levin, M., Wyatt, P.W., Hindson, C.M., Bharadwaj, R., Wong, A., Ness, K.D., Beppu, L.W., Deeg, H.J., McFarland, C.,...

    work page doi:10.1038/ncomms14049 2017

  9. [9]

    Trends in Genetics42(1), 46–62 (2026) https://doi.org/10.1016/j.tig

    Wen, L., Tang, F.: Single-cell omics sequencing technologies: The long-read gen- eration. Trends in Genetics42(1), 46–62 (2026) https://doi.org/10.1016/j.tig. 2025.07.012

    work page doi:10.1016/j.tig 2026

  10. [10]

    Human Immunology82(11), 801–811 (2021) https://doi.org/ 10.1016/j.humimm.2021.02.012

    Hu, T., Chitnis, N., Monos, D., Dinh, A.: Next-generation sequencing technolo- gies: An overview. Human Immunology82(11), 801–811 (2021) https://doi.org/ 10.1016/j.humimm.2021.02.012

    work page doi:10.1016/j.humimm.2021.02.012 2021

  11. [11]

    Nature 574(7778), 418–422 (2019) https://doi.org/10.1038/s41586-019-1654-9

    Kanton, S., Boyle, M.J., He, Z., Santel, M., Weigert, A., Sanchís-Calleja, F., Guijarro, P., Sidow, L., Fleck, J.S., Han, D., Qian, Z., Heide, M., Huttner, W.B., Khaitovich, P., Pääbo, S., Treutlein, B., Camp, J.G.: Organoid single-cell genomic atlas uncovers human-specific features of brain development. Nature 574(7778), 418–422 (2019) https://doi.org/10...

    work page doi:10.1038/s41586-019-1654-9 2019

  12. [12]

    Nature Communications7(1), 10706 (2016) https://doi.org/10.1038/ncomms10706

    Ramilowski, J.A., Goldberg, T., Harshbarger, J., Kloppmann, E., Lizio, M., Satagopam, V.P., Itoh, M., Kawaji, H., Carninci, P., Rost, B., Forrest, A.R.R.: Correction: Corrigendum: A draft network of ligand-receptor-mediated mul- ticellular signalling in human. Nature Communications7(1), 10706 (2016) https://doi.org/10.1038/ncomms10706

    work page doi:10.1038/ncomms10706 2016

  13. [13]

    Biology13(6), 451 (2024) https://doi.org/10.3390/biology13060451

    Huang, K., Xu, Y., Feng, T., Lan, H., Ling, F., Xiang, H., Liu, Q.: The Advance- mentandApplicationoftheSingle-CellTranscriptomeinBiologicalandMedical Research. Biology13(6), 451 (2024) https://doi.org/10.3390/biology13060451

    work page doi:10.3390/biology13060451 2024

  14. [14]

    eLife6, 27041 (2017) https: //doi.org/10.7554/eLife.27041

    Regev, A., Teichmann, S.A., Lander, E.S., Amit, I., Benoist, C., Birney, E., Bodenmiller, B., Campbell, P., Carninci, P., Clatworthy, M., Clevers, H., Deplancke, B., Dunham, I., Eberwine, J., Eils, R., Enard, W., Farmer, A., Fugger, L., Göttgens, B., Hacohen, N., Haniffa, M., Hemberg, M., Kim, S., Klenerman, P., Kriegstein, A., Lein, E., Linnarsson, S., L...

    work page doi:10.7554/elife.27041 2017

  15. [15]

    Science376(6594), 4896 (2022) https:// 49 doi.org/10.1126/science.abl4896

    The Tabula Sapiens Consortium: The Tabula Sapiens: A multiple-organ, single- cell transcriptomic atlas of humans. Science376(6594), 4896 (2022) https:// 49 doi.org/10.1126/science.abl4896

    work page doi:10.1126/science.abl4896 2022

  16. [16]

    Genome Biology21(1), 31 (2020) https://doi.org/10.1186/s13059-020-1926-6

    Lähnemann, D., Köster, J., Szczurek, E., McCarthy, D.J., Hicks, S.C., Robinson, M.D., Vallejos, C.A., Campbell, K.R., Beerenwinkel, N., Mahfouz, A., Pinello, L., Skums, P., Stamatakis, A., Attolini, C.S.-O., Aparicio, S., Baaijens, J., Balvert, M., Barbanson, B., Cappuccio, A., Corleone, G., Dutilh, B.E., Florescu, M., Guryev, V., Holmer, R., Jahn, K., Lo...

    work page doi:10.1186/s13059-020-1926-6 2020

  17. [17]

    BMC Bioinformatics24(1), 302 (2023) https:// doi.org/10.1186/s12859-023-05417-7

    Cheng, Y., Ma, X., Yuan, L., Sun, Z., Wang, P.: Evaluating imputation methods for single-cell RNA-seq data. BMC Bioinformatics24(1), 302 (2023) https:// doi.org/10.1186/s12859-023-05417-7

    work page doi:10.1186/s12859-023-05417-7 2023

  18. [18]

    Nucleic Acids Research50(9), 4877–4899 (2022) https://doi.org/10.1093/nar/gkac317

    Dai, C., Jiang, Y., Yin, C., Su, R., Zeng, X., Zou, Q., Nakai, K., Wei, L.: scIMC: A platform for benchmarking comparison and visualization analysis of scRNA- seq data imputation methods. Nucleic Acids Research50(9), 4877–4899 (2022) https://doi.org/10.1093/nar/gkac317

    work page doi:10.1093/nar/gkac317 2022

  19. [19]

    Genome Biology21(1), 218 (2020) https:// doi.org/10.1186/s13059-020-02132-x

    Hou, W., Ji, Z., Ji, H., Hicks, S.C.: A systematic evaluation of single-cell RNA- sequencing imputation methods. Genome Biology21(1), 218 (2020) https:// doi.org/10.1186/s13059-020-02132-x

    work page doi:10.1186/s13059-020-02132-x 2020

  20. [20]

    Nature Biotechnology37(5), 547–554 (2019) https://doi.org/10.1038/s41587-019-0071-9

    Saelens, W., Cannoodt, R., Todorov, H., Saeys, Y.: A comparison of single- cell trajectory inference methods. Nature Biotechnology37(5), 547–554 (2019) https://doi.org/10.1038/s41587-019-0071-9

    work page doi:10.1038/s41587-019-0071-9 2019

  21. [21]

    Scientific Reports9(1), 5233 (2019) https://doi

    Traag, V.A., Waltman, L., van Eck, N.J.: From Louvain to Leiden: Guaranteeing well-connected communities. Scientific Reports9(1), 5233 (2019) https://doi. org/10.1038/s41598-019-41695-z

    work page doi:10.1038/s41598-019-41695-z 2019

  22. [22]

    Journal of Statistical Mechanics: Theory and Experiment2008(10), 10008 (2008) https://doi.org/10.1088/1742-5468/2008/ 10/P10008

    Blondel, V.D., Guillaume, J.-L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment2008(10), 10008 (2008) https://doi.org/10.1088/1742-5468/2008/ 10/P10008

    work page doi:10.1088/1742-5468/2008/ 2008

  23. [23]

    Nature Methods13(10), 845–848 (2016) https://doi.org/10.1038/nmeth.3971

    Haghverdi, L., Büttner, M., Wolf, F.A., Buettner, F., Theis, F.J.: Diffusion pseudotime robustly reconstructs lineage branching. Nature Methods13(10), 845–848 (2016) https://doi.org/10.1038/nmeth.3971

    work page doi:10.1038/nmeth.3971 2016

  24. [24]

    50 Nature Biotechnology32(4), 381–386 (2014) https://doi.org/10.1038/nbt.2859

    Trapnell, C., Cacchiarelli, D., Grimsby, J., Pokharel, P., Li, S., Morse, M., Lennon,N.J.,Livak,K.J.,Mikkelsen,T.S.,Rinn,J.L.:Thedynamicsandregula- tors of cell fate decisions are revealed by pseudotemporal ordering of single cells. 50 Nature Biotechnology32(4), 381–386 (2014) https://doi.org/10.1038/nbt.2859

    work page doi:10.1038/nbt.2859 2014

  25. [25]

    Cell157(3), 714–725 (2014) https://doi.org/10.1016/j.cell.2014

    Bendall, S.C., Davis, K.L., Amir, E.-a.D., Tadmor, M.D., Simonds, E.F., Chen, T.J., Shenfeld, D.K., Nolan, G.P., Pe’er, D.: Single-Cell Trajectory Detec- tion Uncovers Progression and Regulatory Coordination in Human B Cell Development. Cell157(3), 714–725 (2014) https://doi.org/10.1016/j.cell.2014. 04.005

    work page doi:10.1016/j.cell.2014 2014

  26. [26]

    BMC Genomics19(1), 477 (2018) https://doi.org/10.1186/ s12864-018-4772-0

    Street, K., Risso, D., Fletcher, R.B., Das, D., Ngai, J., Yosef, N., Purdom, E., Dudoit, S.: Slingshot: Cell lineage and pseudotime inference for single-cell transcriptomics. BMC Genomics19(1), 477 (2018) https://doi.org/10.1186/ s12864-018-4772-0

    work page 2018

  27. [27]

    bioRxiv (2018)

    Lotfollahi, M., Wolf, F.A., Theis, F.J.: Generative Modeling and Latent Space Arithmetics Predict Single-Cell Perturbation Response across Cell Types, Studies and Species. bioRxiv (2018). https://doi.org/10.1101/478503

    work page doi:10.1101/478503 2018

  28. [28]

    Genome Biology25(1), 56 (2024) https: //doi.org/10.1186/s13059-024-03183-0

    Pullin, J.M., McCarthy, D.J.: A comparison of marker gene selection methods for single-cell RNA sequencing data. Genome Biology25(1), 56 (2024) https: //doi.org/10.1186/s13059-024-03183-0

    work page doi:10.1186/s13059-024-03183-0 2024

  29. [29]

    NatureBiotechnology34(11), 1145–1160 (2016)https: //doi.org/10.1038/nbt.3711

    Wagner, A., Regev, A., Yosef, N.: Revealing the vectors of cellular identity with single-cellgenomics. NatureBiotechnology34(11), 1145–1160 (2016)https: //doi.org/10.1038/nbt.3711

    work page doi:10.1038/nbt.3711 2016

  30. [30]

    In: Gentleman, R., Carey, V.J., Huber, W., Irizarry, R.A., Dudoit, S

    Scholtens, D., von Heydebreck, A.: Analysis of Differential Gene Expression Studies. In: Gentleman, R., Carey, V.J., Huber, W., Irizarry, R.A., Dudoit, S. (eds.) Bioinformatics and Computational Biology Solutions Using R and Bio- conductor, pp. 229–248. Springer, New York, NY (2005). https://doi.org/10. 1007/0-387-29362-0_14

    work page 2005

  31. [31]

    Nucleic Acids Research45(19), 10978–10988 (2017) https://doi.org/10.1093/ nar/gkx754

    Jia, C., Hu, Y., Kelly, D., Kim, J., Li, M., Zhang, N.R.: Accounting for techni- cal noise in differential expression analysis of single-cell RNA sequencing data. Nucleic Acids Research45(19), 10978–10988 (2017) https://doi.org/10.1093/ nar/gkx754

    work page 2017

  32. [33]

    Genome Research24(3), 496–510 (2014) https://doi.org/10.1101/gr.161034.113

    Marinov, G.K., Williams, B.A., McCue, K., Schroth, G.P., Gertz, J., Myers, R.M., Wold, B.J.: From single-cell to cell-pool transcriptomes: Stochasticity in gene expression and RNA splicing. Genome Research24(3), 496–510 (2014) https://doi.org/10.1101/gr.161034.113

    work page doi:10.1101/gr.161034.113 2014

  33. [34]

    Nature Methods11(2), 163–166 (2014) https://doi.org/10.1038/nmeth

    Islam, S., Zeisel, A., Joost, S., La Manno, G., Zajac, P., Kasper, M., Lönnerberg, 51 P., Linnarsson, S.: Quantitative single-cell RNA-seq with unique molecular iden- tifiers. Nature Methods11(2), 163–166 (2014) https://doi.org/10.1038/nmeth. 2772

    work page doi:10.1038/nmeth 2014

  34. [35]

    Nature Methods11(7), 740–742 (2014) https://doi.org/10.1038/nmeth.2967

    Kharchenko, P.V., Silberstein, L., Scadden, D.T.: Bayesian approach to single- cell differential expression analysis. Nature Methods11(7), 740–742 (2014) https://doi.org/10.1038/nmeth.2967

    work page doi:10.1038/nmeth.2967 2014

  35. [36]

    Applied Sciences12(20), 10684 (2022) https://doi.org/10.3390/app122010684

    Wang, M., Gan, J., Han, C., Guo, Y., Chen, K., Shi, Y.-z., Zhang, B.-g.: Impu- tation Methods for scRNA Sequencing Data. Applied Sciences12(20), 10684 (2022) https://doi.org/10.3390/app122010684

    work page doi:10.3390/app122010684 2022

  36. [37]

    Genome Biology23(1), 31 (2022) https: //doi.org/10.1186/s13059-022-02601-5

    Jiang, R., Sun, T., Song, D., Li, J.J.: Statistics or biology: The zero-inflation controversy about scRNA-seq data. Genome Biology23(1), 31 (2022) https: //doi.org/10.1186/s13059-022-02601-5

    work page doi:10.1186/s13059-022-02601-5 2022

  37. [38]

    Nature Reviews Genetics16(3), 133–145 (2015) https://doi.org/10.1038/nrg3833

    Stegle, O., Teichmann, S.A., Marioni, J.C.: Computational and analytical chal- lenges in single-cell transcriptomics. Nature Reviews Genetics16(3), 133–145 (2015) https://doi.org/10.1038/nrg3833

    work page doi:10.1038/nrg3833 2015

  38. [39]

    Frontiers in Genetics10(2019) https://doi.org/ 10.3389/fgene.2019.00317

    Chen, G., Ning, B., Shi, T.: Single-Cell RNA-Seq Technologies and Related Computational Data Analysis. Frontiers in Genetics10(2019) https://doi.org/ 10.3389/fgene.2019.00317

    work page doi:10.3389/fgene.2019.00317 2019

  39. [40]

    Journal of Chemical Information and Modeling65(5), 2670–2684 (2025) https://doi.org/ 10.1021/acs.jcim.4c02125

    Zhang, Y., Wang, Y., Liu, X., Feng, X.: PbImpute: Precise Zero Discrimina- tion and Balanced Imputation in Single-Cell RNA Sequencing Data. Journal of Chemical Information and Modeling65(5), 2670–2684 (2025) https://doi.org/ 10.1021/acs.jcim.4c02125

    work page doi:10.1021/acs.jcim.4c02125 2025

  40. [41]

    Nature Communications9(1), 997 (2018) https://doi

    Li, W.V., Li, J.J.: An accurate and robust imputation method scImpute for single-cell RNA-seq data. Nature Communications9(1), 997 (2018) https://doi. org/10.1038/s41467-018-03405-7

    work page doi:10.1038/s41467-018-03405-7 2018

  41. [42]

    Bioin- formatics41(3), 711 (2025) https://doi.org/10.1093/bioinformatics/btae711

    Zhang, W., Liu, T., Zhang, H., Li, Y.: AcImpute: A constraint-enhancing smooth-based approach for imputing single-cell RNA sequencing data. Bioin- formatics41(3), 711 (2025) https://doi.org/10.1093/bioinformatics/btae711

    work page doi:10.1093/bioinformatics/btae711 2025

  42. [43]

    Briefings in Bioinformatics26(3), 298 (2025) https: //doi.org/10.1093/bib/bbaf298

    Zhang, H., Li, W., Guan, J.: scTsI: An effective two-stage imputation method for single-cell RNA-seq data. Briefings in Bioinformatics26(3), 298 (2025) https: //doi.org/10.1093/bib/bbaf298

    work page doi:10.1093/bib/bbaf298 2025

  43. [44]

    Cell174(3), 716–72927 (2018) https://doi.org/10

    Dijk, D., Sharma, R., Nainys, J., Yim, K., Kathail, P., Carr, A.J., Burdziak, C., Moon, K.R., Chaffer, C.L., Pattabiraman, D., Bierie, B., Mazutis, L., Wolf, G., Krishnaswamy, S., Pe’er, D.: Recovering Gene Interactions from Single-Cell Data Using Data Diffusion. Cell174(3), 716–72927 (2018) https://doi.org/10. 1016/j.cell.2018.05.061 52

    work page 2018

  44. [45]

    Journal of Molecular Cell Biology 13(1), 29–40 (2021) https://doi.org/10.1093/jmcb/mjaa052

    Zhang, L., Zhang, S.: Imputing single-cell RNA-seq data by considering cell het- erogeneity and prior expression of dropouts. Journal of Molecular Cell Biology 13(1), 29–40 (2021) https://doi.org/10.1093/jmcb/mjaa052

    work page doi:10.1093/jmcb/mjaa052 2021

  45. [46]

    Pan, X., Li, Z., Qin, S., Yu, M., Hu, H.: ScLRTC: Imputation for single-cell RNA-seqdatavialow-ranktensorcompletion.BMCGenomics22(1),860(2021) https://doi.org/10.1186/s12864-021-08101-3

    work page doi:10.1186/s12864-021-08101-3 2021

  46. [47]

    Briefings in Bioinformatics22(5), 085 (2021) https://doi.org/10.1093/bib/bbab085

    Hu, Y., Li, B., Zhang, W., Liu, N., Cai, P., Chen, F., Qu, K.: WEDGE: Imputation of gene expression values from single-cell RNA-seq datasets using biased matrix decomposition. Briefings in Bioinformatics22(5), 085 (2021) https://doi.org/10.1093/bib/bbab085

    work page doi:10.1093/bib/bbab085 2021

  47. [48]

    Zhang, Z., Liu, L.: scIDPMs: Single-Cell RNA-Seq Imputation Using Diffusion ProbabilisticModels.IEEEJournalofBiomedicalandHealthInformatics29(4), 3057–3068 (2025) https://doi.org/10.1109/JBHI.2024.3430554

    work page doi:10.1109/jbhi.2024.3430554 2025

  48. [49]

    Briefings in Bioinformatics 25(3), 171 (2024) https://doi.org/10.1093/bib/bbae171

    Li, K., Li, J., Tao, Y., Wang, F.: stDiff: A diffusion model for imputing spatial transcriptomics through single-cell transcriptomics. Briefings in Bioinformatics 25(3), 171 (2024) https://doi.org/10.1093/bib/bbae171

    work page doi:10.1093/bib/bbae171 2024

  49. [50]

    Briefings in Bioinformatics26(1), 668 (2025) https: //doi.org/10.1093/bib/bbae668

    Zhang, Y., Wang, Y., Liu, X., Feng, X.: CPARI: A novel approach combining cell partitioning with absolute and relative imputation to address dropout in single-cell RNA-seq data. Briefings in Bioinformatics26(1), 668 (2025) https: //doi.org/10.1093/bib/bbae668

    work page doi:10.1093/bib/bbae668 2025

  50. [51]

    Briefings in Bioinformatics24(6), 384 (2023) https://doi.org/10.1093/bib/bbad384

    Wang, T., Zhao, H., Xu, Y., Wang, Y., Shang, X., Peng, J., Xiao, B.: scMulti- GAN: Cell-specific imputation for single-cell transcriptomes with multiple deep generative adversarial networks. Briefings in Bioinformatics24(6), 384 (2023) https://doi.org/10.1093/bib/bbad384

    work page doi:10.1093/bib/bbad384 2023

  51. [52]

    Briefings in Bioinformatics24(1), 580 (2023) https://doi.org/10.1093/bib/bbac580

    Chen, S., Yan, X., Zheng, R., Li, M.: Bubble: A fast single-cell RNA-seq impu- tation using an autoencoder constrained by bulk RNA-seq data. Briefings in Bioinformatics24(1), 580 (2023) https://doi.org/10.1093/bib/bbac580

    work page doi:10.1093/bib/bbac580 2023

  52. [53]

    Nature Communications12(1), 1882 (2021) https://doi

    Wang, J., Ma, A., Chang, Y., Gong, J., Jiang, Y., Qi, R., Wang, C., Fu, H., Ma, Q., Xu, D.: scGNN is a novel graph neural network framework for single- cell RNA-Seq analyses. Nature Communications12(1), 1882 (2021) https://doi. org/10.1038/s41467-021-22197-x

    work page doi:10.1038/s41467-021-22197-x 2021

  53. [54]

    Nucleic Acids Research 48(15), 85 (2020) https://doi.org/10.1093/nar/gkaa506

    Xu, Y., Zhang, Z., You, L., Liu, J., Fan, Z., Zhou, X.: scIGANs: Single-cell RNA- seq imputation using generative adversarial networks. Nucleic Acids Research 48(15), 85 (2020) https://doi.org/10.1093/nar/gkaa506

    work page doi:10.1093/nar/gkaa506 2020

  54. [55]

    Genome Biology16(1), 278 (2015) https://doi.org/10.1186/s13059-015-0844-5

    Finak, G., McDavid, A., Yajima, M., Deng, J., Gersuk, V., Shalek, A.K., Slichter, C.K., Miller, H.W., McElrath, M.J., Prlic, M., Linsley, P.S., Gottardo, R.: MAST: A flexible statistical framework for assessing transcriptional changes 53 and characterizing heterogeneity in single-cell RNA sequencing data. Genome Biology16(1), 278 (2015) https://doi.org/10...

    work page doi:10.1186/s13059-015-0844-5 2015

  55. [56]

    The Annals of Mathematical Statistics 18(1), 50–60 (1947) 2236101

    Mann,H.B.,Whitney,D.R.:OnaTestofWhetheroneofTwoRandomVariables is Stochastically Larger than the Other. The Annals of Mathematical Statistics 18(1), 50–60 (1947) 2236101

    work page 1947

  56. [57]

    Biometrics Bulletin , author =

    Wilcoxon, F.: Individual Comparisons by Ranking Methods. Biometrics Bulletin 1(6), 80–83 (1945) https://doi.org/10.2307/3001968 3001968

    work page doi:10.2307/3001968 1945

  57. [58]

    Genome Biology19(1), 15 (2018) https://doi.org/10

    Wolf, F.A., Angerer, P., Theis, F.J.: SCANPY: Large-scale single-cell gene expression data analysis. Genome Biology19(1), 15 (2018) https://doi.org/10. 1186/s13059-017-1382-0

    work page 2018

  58. [59]

    Nucleic acids research43(7), 47–47 (2015)

    Ritchie, M.E., Phipson, B., Wu, D., Hu, Y., Law, C.W., Shi, W., Smyth, G.K.: limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic acids research43(7), 47–47 (2015)

    work page 2015

  59. [60]

    Immunity15(3), 375– 385 (2001) https://doi.org/10.1016/S1074-7613(01)00194-7

    Shaffer, A.L., Rosenwald, A., Hurt, E.M., Giltnane, J.M., Lam, L.T., Pickeral, O.K., Staudt, L.M.: Signatures of the Immune Response. Immunity15(3), 375– 385 (2001) https://doi.org/10.1016/S1074-7613(01)00194-7

    work page doi:10.1016/s1074-7613(01)00194-7 2001

  60. [61]

    Nature Protocols (2025) https://doi.org/10.1038/s41596-025-01220-1

    Ding, S., Li, J., Luo, R., Cui, H., Wang, B., Chen, R.: scGPT: End-to-end protocol for fine-tuned retinal cell type annotation. Nature Protocols (2025) https://doi.org/10.1038/s41596-025-01220-1

    work page doi:10.1038/s41596-025-01220-1 2025

  61. [62]

    Molecular Cell65(4), 631–6434 (2017) https://doi.org/10.1016/j.molcel.2017.01.023

    Ziegenhain,C.,Vieth,B.,Parekh,S.,Reinius,B.,Guillaumet-Adkins,A.,Smets, M., Leonhardt, H., Heyn, H., Hellmann, I., Enard, W.: Comparative Analysis of Single-Cell RNA Sequencing Methods. Molecular Cell65(4), 631–6434 (2017) https://doi.org/10.1016/j.molcel.2017.01.023

    work page doi:10.1016/j.molcel.2017.01.023 2017

  62. [63]

    Nature Reviews Genetics20(5), 273–282 (2019) https://doi.org/10.1038/s41576-018-0088-9

    Kiselev, V.Y., Andrews, T.S., Hemberg, M.: Challenges in unsupervised cluster- ing of single-cell RNA-seq data. Nature Reviews Genetics20(5), 273–282 (2019) https://doi.org/10.1038/s41576-018-0088-9

    work page doi:10.1038/s41576-018-0088-9 2019

  63. [64]

    Computational and Structural Biotechnology Journal19, 961–969 (2021) https://doi.org/10.1016/j.csbj.2021

    Pasquini, G., Rojo Arias, J.E., Schäfer, P., Busskamp, V.: Automated meth- ods for cell type annotation on scRNA-seq data. Computational and Structural Biotechnology Journal19, 961–969 (2021) https://doi.org/10.1016/j.csbj.2021. 01.015

    work page doi:10.1016/j.csbj.2021 2021

  64. [65]

    Nature Neuroscience22(12), 2087–2097 (2019) https://doi.org/10.1038/s41593-019-0539-4 54

    Grubman, A., Chew, G., Ouyang, J.F., Sun, G., Choo, X.Y., McLean, C., Simmons, R.K., Buckberry, S., Vargas-Landin, D.B., Poppe, D., Pflueger, J., Lister, R., Rackham, O.J.L., Petretto, E., Polo, J.M.: A single-cell atlas of entorhinal cortex from individuals with Alzheimer’s disease reveals cell-type- specific gene expression regulation. Nature Neuroscien...

    work page doi:10.1038/s41593-019-0539-4 2087

  65. [66]

    Nature Methods16(6), 479–487 (2019) https://doi.org/10

    Tian, L., Dong, X., Freytag, S., Lê Cao, K.-A., Su, S., JalalAbadi, A., Amann- Zalcenstein, D., Weber, T.S., Seidi, A., Jabbari, J.S., Naik, S.H., Ritchie, M.E.: Benchmarking single cell RNA-sequencing analysis pipelines using mixture con- trol experiments. Nature Methods16(6), 479–487 (2019) https://doi.org/10. 1038/s41592-019-0425-8

    work page 2019

  66. [67]

    PLOS Computational Biology 14(8), 1006361 (2018) https://doi.org/10.1371/journal.pcbi.1006361

    Tian, L., Su, S., Dong, X., Amann-Zalcenstein, D., Biben, C., Seidi, A., Hilton, D.J., Naik, S.H., Ritchie, M.E.: scPipe: A flexible R/Bioconductor preprocess- ing pipeline for single-cell RNA-sequencing data. PLOS Computational Biology 14(8), 1006361 (2018) https://doi.org/10.1371/journal.pcbi.1006361

    work page doi:10.1371/journal.pcbi.1006361 2018

  67. [68]

    Nature Communications11(1), 3924 (2020) https: //doi.org/10.1038/s41467-020-17834-w

    Guo, C., Li, B., Ma, H., Wang, X., Cai, P., Yu, Q., Zhu, L., Jin, L., Jiang, C., Fang, J., Liu, Q., Zong, D., Zhang, W., Lu, Y., Li, K., Gao, X., Fu, B., Liu, L., Ma, X., Weng, J., Wei, H., Jin, T., Lin, J., Qu, K.: Single-cell analysis of two severe COVID-19 patients reveals a monocyte-associated and tocilizumab- responding cytokine storm. Nature Communi...

    work page doi:10.1038/s41467-020-17834-w 2020

  68. [69]

    Nature Communications10(1), 687 (2019) https://doi.org/10.1038/ s41467-019-08604-4

    Gutierrez-Arcelus, M., Teslovich, N., Mola, A.R., Polidoro, R.B., Nathan, A., Kim, H., Hannes, S., Slowikowski, K., Watts, G.F.M., Korsunsky, I., Bren- ner, M.B., Raychaudhuri, S., Brennan, P.J.: Lymphocyte innateness defined by transcriptional states reflects a balance between proliferation and effector functions. Nature Communications10(1), 687 (2019) h...

    work page 2019

  69. [70]

    Quantum processor-inspired machine learning in the biomedical sciences

    Zheng, C., Zheng, L., Yoo, J.-K., Guo, H., Zhang, Y., Guo, X., Kang, B., Hu, R., Huang, J.Y., Zhang, Q., Liu, Z., Dong, M., Hu, X., Ouyang, W., Peng, J., Zhang, Z.: Landscape of Infiltrating T Cells in Liver Cancer Revealed by Single- Cell Sequencing. Cell169(7), 1342–135616 (2017) https://doi.org/10.1016/j. cell.2017.05.035

    work page doi:10.1016/j 2017

  70. [71]

    Cell165(4), 1012–1026 (2016) https://doi.org/10.1016/j.cell.2016.03

    Petropoulos, S., Edsgärd, D., Reinius, B., Deng, Q., Panula, S.P., Codeluppi, S., Plaza Reyes, A., Linnarsson, S., Sandberg, R., Lanner, F.: Single-Cell RNA- Seq Reveals Lineage and X Chromosome Dynamics in Human Preimplantation Embryos. Cell165(4), 1012–1026 (2016) https://doi.org/10.1016/j.cell.2016.03. 023

    work page doi:10.1016/j.cell.2016.03 2016

  71. [72]

    Genome Biology17(1), 173 (2016) https://doi.org/10.1186/s13059-016-1033-x

    Chu, L.-F., Leng, N., Zhang, J., Hou, Z., Mamott, D., Vereide, D.T., Choi, J., Kendziorski, C., Stewart, R., Thomson, J.A.: Single-cell RNA-seq reveals novel regulators of human embryonic stem cell differentiation to definitive endoderm. Genome Biology17(1), 173 (2016) https://doi.org/10.1186/s13059-016-1033-x

    work page doi:10.1186/s13059-016-1033-x 2016

  72. [73]

    Cell Reports18(13), 3227–3241 (2017) https://doi.org/10

    Chen, R., Wu, X., Jiang, L., Zhang, Y.: Single-Cell RNA-Seq Reveals Hypotha- lamic Cell Diversity. Cell Reports18(13), 3227–3241 (2017) https://doi.org/10. 1016/j.celrep.2017.03.004

    work page 2017

  73. [74]

    Nature Neuroscience20(2), 176–188 (2017) https://doi.org/10.1038/nn.4462

    Romanov, R.A., Zeisel, A., Bakker, J., Girach, F., Hellysaz, A., Tomer, R., 55 Alpár, A., Mulder, J., Clotman, F., Keimpema, E., Hsueh, B., Crow, A.K., Martens, H., Schwindling, C., Calvigioni, D., Bains, J.S., Máté, Z., Szabó, G., Yanagawa, Y., Zhang, M.-D., Rendeiro, A., Farlik, M., Uhlén, M., Wulff, P., Bock, C., Broberger, C., Deisseroth, K., Hökfelt,...

    work page doi:10.1038/nn.4462 2017

  74. [75]

    Nature Neuroscience18(1), 145–153 (2015) https://doi

    Usoskin, D., Furlan, A., Islam, S., Abdo, H., Lönnerberg, P., Lou, D., Hjerling- Leffler, J., Haeggström, J., Kharchenko, O., Kharchenko, P.V., Linnarsson, S., Ernfors, P.: Unbiased classification of sensory neuron types by large-scale single- cell RNA sequencing. Nature Neuroscience18(1), 145–153 (2015) https://doi. org/10.1038/nn.3881

    work page doi:10.1038/nn.3881 2015

  75. [76]

    Science347(6226), 1138–1142 (2015) https://doi.org/10.1126/science.aaa1934

    Zeisel, A., Muñoz-Manchado, A.B., Codeluppi, S., Lönnerberg, P., La Manno, G., Juréus, A., Marques, S., Munguba, H., He, L., Betsholtz, C., Rolny, C., Castelo-Branco, G., Hjerling-Leffler, J., Linnarsson, S.: Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq. Science347(6226), 1138–1142 (2015) https://doi.org/10.1126/science.aaa1934

    work page doi:10.1126/science.aaa1934 2015

  76. [77]

    Cell Systems3(4), 346–3604 (2016) https://doi.org/10.1016/j.cels.2016.08.011

    Baron, M., Veres, A., Wolock, S.L., Faust, A.L., Gaujoux, R., Vetere, A., Ryu, J.H., Wagner, B.K., Shen-Orr, S.S., Klein, A.M., Melton, D.A., Yanai, I.: A Single-Cell Transcriptomic Map of the Human and Mouse Pancreas Reveals Inter- and Intra-cell Population Structure. Cell Systems3(4), 346–3604 (2016) https://doi.org/10.1016/j.cels.2016.08.011

    work page doi:10.1016/j.cels.2016.08.011 2016

  77. [78]

    Nature Genetics49(5), 708–718 (2017) https://doi.org/10

    Li, H., Courtois, E.T., Sengupta, D., Tan, Y., Chen, K.H., Goh, J.J.L., Kong, S.L., Chua, C., Hon, L.K., Tan, W.S., Wong, M., Choi, P.J., Wee, L.J.K., Hillmer, A.M., Tan, I.B., Robson, P., Prabhakar, S.: Reference component anal- ysis of single-cell transcriptomes elucidates cellular heterogeneity in human colorectal tumors. Nature Genetics49(5), 708–718 ...

    work page 2017

  78. [79]

    Cell172(5), 1091–110717 (2018) https://doi.org/10.1016/j.cell

    Han, X., Wang, R., Zhou, Y., Fei, L., Sun, H., Lai, S., Saadatpour, A., Zhou, Z., Chen, H., Ye, F., Huang, D., Xu, Y., Huang, W., Jiang, M., Jiang, X., Mao, J., Chen, Y., Lu, C., Xie, J., Fang, Q., Wang, Y., Yue, R., Li, T., Huang, H., Orkin, S.H., Yuan, G.-C., Chen, M., Guo, G.: Mapping the Mouse Cell Atlas by Microwell-Seq. Cell172(5), 1091–110717 (2018...

    work page doi:10.1016/j.cell 2018

  79. [80]

    https://www.10xgenomics.com/datasets

    10x Genomics: 10x Genomics Dataset Repository. https://www.10xgenomics.com/datasets

    work page

  80. [81]

    Nucleic Acids Research 30(1), 207–210 (2002) https://doi.org/10.1093/nar/30.1.207 56

    Edgar, R., Domrachev, M., Lash, A.E.: Gene Expression Omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Research 30(1), 207–210 (2002) https://doi.org/10.1093/nar/30.1.207 56

    work page doi:10.1093/nar/30.1.207 2002

Showing first 80 references.