Single-cell RNA-seq has inspired new discoveries and innovation in the field of developmental and cell biology for the past few years and is useful for studying cellular responses at individual cell resolution. But, due to the paucity of starting RNA, the data acquired have dropouts. To address this, we propose a deep matrix factorization-based method, deepMc, to impute missing values in gene expression data. For the deep architecture of our approach, we draw our motivation from great success of deep learning in solving various machine learning problems. In this study, we support our method with positive results on several evaluation metrics such as clustering of cell populations, differential expression analysis, and cell type separability.
Get full access to this article
View all access options for this article.
References
1.
ArisdakessianC., PoirionO., YunitsB., et al.2018. DeepImpute: An accurate, fast and scalable deep neural network method to impute single-cell RNA-Seq data. bioRxiv 353607.
2.
BiaseF.H., CaoX., and ZhongS.2014. Cell fate inclination within 2- cell and 4-cell mouse embryos revealed by single-cell RNA sequencing. Genome Res., 24:1787–1796.
3.
BlakeleyP., FogartyN.M., Del ValleI., et al.2015. Dening the three cell lineages of the human blastocyst by single-cell RNA-seq. Development, 142, 3151–3165.
4.
CandesE.J., and TaoT.2010. The power of convex relaxation: Near-optimal matrix completion. IEEE Trans Inf Theory, 56, 2053–2080.
5.
GongW., KwakI.-Y., Koyano-NakagawaN., et al.2018. DrImpute: Imputing dropout events in single cell RNA sequencing data. BMC Bioinformatics, 19, 220.
6.
HuangM., WangJ., TorreE., et al.2018. SAVER: Gene expression recovery for single-cell RNA sequencing. Nat. Methods, 15, 539–542.
7.
KapurA., MarwahK., and AlterovitzG.2016. Gene expression prediction using low-rank matrix completion. BMC Bioinformatics, 17, 243.
8.
KharchenkoP.V., SilbersteinL., and ScaddenD.T.2014. Bayesian approach to single-cell differential expression analysis. Nat. Methods, 11, 740–742.
9.
KnightJ.M., IvanovI., TriK., et al.2018. Detecting multivariate gene interactions in RNA-Seq data using optimal Bayesian Classification. IEEE/ACM Trans. Comput. Biol. Bioinform. 15, 484–493.
10.
KolodziejczykA.A., KimJ.K., SvenssonV., et al.2015. The technology and biology of single-cell RNA sequencing. Mol. Cell, 58, 610–620.
11.
KorenY., BellR., and VolinskyC.2009. Matrix factorization techniques for recommender systems. Computer, 42, 30–37.
12.
LawC.W., ChenY., ShiW., et al.2014. voom: Precision weights unlock linear model analysis tools for RNA-seq read counts. Genome Biol. 15, R29.
13.
LeeD.D., and SeungH.S.1999. Learning the parts of objects by non-negative matrix factorization. Nature, 401, 788.
14.
LiH, CourtoisE.T., SenguptaD., et al.2017. Reference component analysis of single-cell transcriptomes elucidates cellular heterogeneity in human colorectal tumors. Nat. Genet. 49, 708–718.
15.
LiJ., J. HuM. Newman, et al. 2014. RNA-Seq analysis pipeline based on Oshell environment. IEEE/ACM Trans. Comput. Biol. Bioinform. 11, 973–978.
16.
LiW.V., and LiJ.J.2018. An accurate and robust imputation method scImpute for single-cell RNA-seq data. Nat. Commun. 9, 97.
17.
LiZ., and TangJ.2017. Weakly supervised deep matrix factorization for social image understanding. IEEE Trans. Image Process. 26, 276–288.
18.
LiaoB., GuoC., HuangL., et al.2016. Matrix completion based direction-of-arrival estimation in nonuniform noise. In 2016 IEEE International Conference on Digital Signal Processing (DSP), IEEE, Imperial College, London. 66–69.
19.
LiuK., YeJ., YangY., et al.2018. A Unified Model for joint normalization and differential gene expression detection in RNA-Seq data. IEEE/ACM Trans. Comput. Biol. Bioinform. 16, 442–454.
20.
LoveM.I., HuberW., and AndersS.2014. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15, 550.
21.
MarkovskyI.2013. Exact system identification with missing data. In 2013 IEEE 52nd Annual Conference on Decision and Control (CDC), IEEE, Florence, Italy. 151–155.
22.
MinS., LeeB., and YoonS.2017. Deep learning in bioinformatics. Brief Bioinform. 18, 851–869.
23.
OlshausenB.A., and FieldD.J.1996. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381, 607.
24.
PatelA.P., TiroshI., TrombettaJ.J., et al.2014. Single-cell RNA-seq highlights intratumoral heterogeneity in primary glioblastoma. Science, 344, 1396–1401.
25.
RechtB., FazelM., and ParriloP.A.2010. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev. 52, 471–501.
26.
RitchieM.E., PhipsonB., WuD., et al.2015. limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 43, e47–e47.
27.
RizzettoS., EltahlaA.A., LinP., et al.2017. Impact of sequencing depth and read length on single cell RNA sequencing data of T cells. Sci. Rep. 7, 12781.
28.
SenguptaD., RayanN.A., LimM., et al.2016. Fast, scalable and accurate differential expression analysis for single cells. bioRxiv p. 049734.
29.
TangF., BarbacioruC., BaoS., et al.2010. Tracing the derivation of embryonic stem cells from the inner cell mass by single-cell RNA-Seq analysis. Cell Stem Cell, 6, 468–478.
30.
TariyalS., MajumdarA., SinghR., et al.2016. Deep dictionary learning. IEEE Access, 4, 10096–10109.
31.
TiroshI., IzarB., PrakadanS.M., et al.2016. Dissecting the multicellular ecosystem of metastatic melanoma by single-cell RNA-seq. Science, 352, 189–196.
32.
TrigeorgisG., BousmalisK., ZafeiriouS., et al.2017. A deep matrix factorization method for learning attribute representations. IEEE Trans. Pattern Anal. Mach. Intell. 393, 417–429.
33.
TungP.-Y., BlischakJ.D., HsiaoC.J., et al.2017. Batch effects and the effective design of single-cell gene expression studies. Sci. Rep. 7, 39921.
34.
van DijkD., NainysJ., SharmaR., et al.2017. MAGIC: A diffusion-based imputation method reveals gene-gene interactions in single-cell RNA sequencing data. BioRxivp. 111591.
35.
WagnerA., RegevA., and YosefN.2016. Revealing the vectors of cellular identity with single-cell genomics. Nat. Biotechnol. 34, 1145–1160.
36.
WanL., and SunF.2012. CEDER: Accurate detection of differentially expressed genes by combining significance of exons using RNA-Seq. IEEE/ACM Trans. Comput. Biol. Bioinform. 9, 1281–1292.
37.
WangZ., GersteinM., and SnyderM.2009. RNA-Seq: A revolutionary tool for transcriptomics. Nat. Rev. Genet. 10, 57–63.
38.
WenZ., YinW., and ZhangY.2012. Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm. Math. Program. Comput. 4, 333–361.
39.
YanL., YangM., GuoH., et al.2013. Single-cell RNA-Seq profiling of human preimplantation embryos and embryonic stem cells. Nat. Struct. Mol. Biol. 20, 1131–1139.
40.
ZhangL., and ZhangS.2018. Comparison of computational methods for imputing single-cell RNA-sequencing data. IEEE/ACM Trans. Comput. Biol. Bioinform. DOI:10.1109/TCBB.2018.2848633
41.
ZhengG.X.Y., TerryJ.M., BelgraderP., et al.2017. Massively parallel digital transcriptional profiling of single cells. Nat. Commun. 8, 14049.
42.
ZhouX., LindsayH., and RobinsonM.D.2014. Robustly detecting differential expression in RNA sequencing data using observation weights. Nucleic Acids Res. 42, e91.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
